Method and device for generating prediction model

Abstract

A method and apparatus for generating a predictive model includes operating a radio signal receiving device while collecting data corresponding to at least one frequency-related parameter associated with a frequency source associated with the receiving device, at least one operational characteristic of the receiving device, and / or at least one environmental event associated with the receiving device, wherein the at least one frequency-related parameter varies with a variation in the at least one operating characteristic and / or a variation in the at least one environmental event, and processing the data to generate a predictive model for compensating for a variation in the at least one frequency-related parameter corresponding to the at least one operating characteristic and / or the at least one environmental event.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of and priority to U.S. Provisional Patent Application Serial No. 63 / 445,757, filed February 15, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0003] Embodiments of the present principles relate generally to radio signal processing, and more particularly to methods and apparatus for generating a prediction model to compensate for frequency-related parameter errors. Background Art

[0004] Radio transmissions are used in a variety of communication and positioning systems. For example, in a cell phone (e.g., a mobile phone), a frequency source (e.g., an oscillator, synthesizer, etc.) generates an oscillating signal that is used by various components of the phone to process data and facilitate the operation of various signal receivers (e.g., WiFi modems, cellular modems, Bluetooth modems, GNSS receivers, etc.). Unfortunately, in most cell phones, the stability of the oscillating signal varies significantly depending on the phone's environment and operating conditions. This frequency variation can affect the receiver's ability to accurately process received radio signals.

[0005] A technique for motion compensation of received radio signals to improve the accuracy of local frequency sources is called SUPERCORRELATION TM , and are described in commonly assigned U.S. Patents 9,780,829, issued October 3, 2017; 10,321,430, issued June 11, 2019; 10,816,672, issued October 27, 2020; U.S. Patent Publication 2020 / 0264317, published August 20, 2020; 2020 / 0319347, published October 8, 2020; U.S. Patent Application 63 / 394667, filed August 3, 2022; and U.S. Patent Application 63 / 424185, filed November 10, 2022. SUPERCORRELATION TM The technology can be used to compensate the phase of the received signal for the motion of the mobile phone and the instability of the local frequency source. TM When using this technology, the processor in the phone generates a number of phase compensation hypotheses that correct the received signal for instabilities in the local frequency source and for motion of the receiver.

[0006] Initially, the hypotheses cover a large search space, and over time, as the frequency source stabilizes, the number and density of hypotheses decreases, and the hypotheses track and correct for variations in the frequency source output. Unfortunately, the output of a frequency source, especially an inexpensive oscillator, can vary significantly given the operating characteristics of the phone and / or environmental events. For example, external and internal temperature variations and / or physical shocks to the phone can cause significant and rapid variations in the frequency source output frequency. Such unexpected variations require supercorrelations. TM Techniques are used to expand the hypothesis search space to find, for example, a preferred hypothesis that maximizes the receiver's signal correlation output. This search space expansion may slow down signal acquisition, increase receiver power consumption, or cause positioning using GNSS signals to be inaccurate for a period of time.

[0007] Therefore, there is a need for a method and apparatus for generating a predictive model to anticipate frequency changes caused by environmental events and equipment operating characteristics. Summary of the Invention

[0008] Embodiments of the present principles generally relate to a method and apparatus for generating a predictive model to anticipate frequency changes caused by environmental events and / or equipment operating characteristics.

[0009] The various features and advantages of the present disclosure can be understood by reading the following detailed description of the disclosure along with the accompanying drawings, wherein like reference numerals refer to like parts throughout. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order that the various features of the present principles may be understood in detail, a more particular description of the principles briefly summarized above may be given with reference to embodiments, some of which are illustrated in the accompanying drawings. It should be noted, however, that the drawings illustrate only typical embodiments in accordance with the present principles and are therefore not to be considered limiting of their scope, as these principles may admit to other equally effective embodiments.

[0011] Figure 1 depicts a high-level block diagram of an exemplary test platform for generating predictive models in accordance with at least one embodiment of the present principles;

[0012] Figure 2 A flowchart depicting a method of generating a test data set according to at least one embodiment of the present principles; and

[0013] Figure 3 Describes at least one alternative embodiment according to the present principles, using Figure 2 Flowchart of a method for generating a prediction model based on a dataset.

[0014] To facilitate understanding, identical reference numerals are used, where possible, to denote identical elements common to the accompanying drawings. The accompanying drawings are not drawn to scale and may be simplified for clarity. It is contemplated that elements and features of one embodiment may be advantageously incorporated into other embodiments without further narration. DETAILED DESCRIPTION

[0015] Embodiments of the present principles generally relate to methods and apparatus for generating a predictive model to anticipate frequency changes caused by environmental events and / or device operating characteristics. While the concepts of the present principles are susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the accompanying drawings and described in detail below. It should be understood that the concepts of the present principles are not intended to be limited to the particular form disclosed. On the contrary, the intention is to cover all modifications, equivalents, and alternatives consistent with the present principles and the appended claims.

[0016] As used herein, the phrase device under test (DUT) is intended to describe a receiving device, such as a radio signal receiving device, that can implement embodiments of the present principles to generate a predictive model to anticipate frequency changes caused by environmental events and / or device operating characteristics, and implement such a predictive model to correct the frequency response of a frequency source associated with the DUT for changes in environmental events and / or device operating characteristics of the DUT. The phrase "device under test" is not intended to limit any receiving device to collecting data during a test mode, as embodiments of the present principles described herein include collecting data during normal operation of the receiving device.

[0017] In an embodiment of the present principles, a generated prediction model may be used during signal processing within a device (i.e., a user device) to compensate for expected frequency-related parameter changes that occur in response to device operating characteristics and / or environmental events. Frequency-related parameters may include, but are not limited to, phase, frequency, rate of change of frequency, or higher order terms of the device frequency source. Changes in frequency-related parameters caused by environmental and operating conditions may be modeled by a priori empirical studies and / or by updating the model in real time as the device is used. In some embodiments, the model of the present principles may include a lookup table or a machine learning model that correlates environmental or operating events with changes in frequency-related parameters. In some embodiments of the present principles, changes in frequency-related parameters may be represented by one or more phasors (i.e., assumptions about the phase of the signal), such as in a SUPERCORRELATION TM technique to compensate for predicted frequency-dependent parameter variations.

[0018] In some embodiments, one or more models may be populated using a priori empirical data generated through, for example, testing of mobile phones using a test platform. For example, embodiments of the present principles may be used to create a dataset of frequency variation information as a mobile phone (e.g., a device under test (DUT)) experiences various environmental conditions (e.g., temperature changes, physical shock, vibration) and / or operational events (e.g., activating and deactivating a screen, modem, GNSS receiver, etc.). TM The technology can be used to accurately measure frequency-dependent parameter changes. The data set can then be processed to create a predictive model that anticipates specific frequency-dependent parameter changes that will occur when specific environmental or operational events occur. When receiving signals during normal use, the model of the present principles enables, for example, SUPERCORRELATION TM The number and density of assumptions used in the technique are constrained. In an embodiment of the present principles, a data set of information containing conditions / events and frequency-related parameters can be created. Such a data set can include information representing changes in at least one frequency-related parameter (phase, frequency, rate of change of frequency, or higher order terms) that occur based on a combination of conditions / events (e.g., changes in frequency and rate of change of frequency caused when a cell phone is dropped on a hot day). In some embodiments, the model created from the data set can be in the form of a lookup table, or the data set can be used to train a machine learning model. In some embodiments, the model of the present principles can be used to predict frequency-related parameters that occur due to the occurrence of a condition / event or a combination of conditions / events.

[0019] In some embodiments, the model of the present principles can be initially created using prior experience information ported to a new device as an initial prediction model. This initial prediction model of the present principles can be updated and / or corrected over time as the device is used. Thus, as the device is used, the prediction model becomes more accurate in predicting changes in the frequency of device use.

[0020] Alternatively, in some embodiments, the model of the present principles can be generated in real time while using a device (e.g., a cell phone / mobile communication device) without the need for implementing a dataset created a priori. For example, in such an embodiment, the predictive model generator of the present principles can be embedded in the cell phone rather than as part of a test platform.

[0021] In other embodiments, the models of the present principles and / or information about the models can be shared between devices to improve the accuracy of the models and / or device functionality. In such embodiments, sharing can be achieved on a peer-to-peer basis and / or via a server that distributes available model information. For a particular model of a device, the server can include a reference model developed based on the shared information, which can be regularly shared with currently used devices and / or can be used as an initial model in new or reset devices.

[0022] Figure 1 A block diagram of an exemplary test platform 100 for creating a frequency source prediction model in accordance with at least one embodiment of the present principles is depicted. Figure 1 In some embodiments of the present principles, the platform 100 includes a device under test (DUT) 102, which is coupled to a predictive model generator 128 and an environmental event controller 126. The predictive model generator 128 runs a test script to collect empirical data from the DUT 102 regarding frequency changes in response to specific environmental and operational events. Figure 1 The platform 100 may be implemented, for example, at a DUT fabrication facility.

[0023] In some embodiments, the predictive model generator 128 may be embedded in the DUT 102 and may be executed as a software application of the DUT 102. In such embodiments, the generator 128 may be used to update the predictive model while the DUT 102 is being used in the field.

[0024] In some embodiments, the DUT 102 may include, but is not limited to, a laptop computer, a mobile phone, a tablet computer, an Internet of Things (IoT) device, a dedicated positioning device, etc. and / or a combination thereof. Figure 1 The DUT 102 may include a TM Any device that uses technology to enhance the signal reception and / or integrity of local frequency sources.

[0025] exist Figure 1 In the embodiment of the present invention, the DUT 102 illustratively includes at least one processor 104, support circuits 108, and memory 110. The at least one processor 104 may include any form of processor or combination of processors, including but not limited to a central processing unit, a microprocessor, a microcontroller, a field programmable gate array, a graphics processing unit, and a digital signal processor. The support circuits 108 may include well-known circuits and devices that facilitate the functions of one or more processors. In other words, the support circuits 108 may include one or more of a power supply, a clock circuit, an analog-to-digital converter, a communication circuit, a cache, a display, and / or a combination thereof.

[0026] exist Figure 1 In embodiments, operation and / or operational variations of the GNSS receiver 112, the graphical user interface display 114, and the modem 116 (e.g., a receiver and transmitter of signals such as WiFi, cellular, and Bluetooth) may result in temperature variations in the DUT 102, thereby causing frequency drift in the frequency source 118.

[0027] exist Figure 1 In an embodiment of the present invention, the memory 110 may include one or more forms of non-transitory computer-readable media, including one or more of read-only memory and random access memory, or any combination thereof. The memory 110 may store software and data, including, for example, but not limited to, an operating system (OS) 120, application software 122, test software 124 and data 106, signal processing software 146, and SUPERCORRELATION TM Software 148.

[0028] exist Figure 1 In an embodiment, the predictive model generator 128 includes at least one processor 130, support circuits 132, and memory 134. The at least one processor 130 may include any form of processor or combination of processors, including but not limited to a central processing unit, a microprocessor, a microcontroller, a field programmable gate array, a graphics processing unit, a digital signal processor, etc. Figure 1 The support circuits 132 may include well-known circuits and devices that facilitate the functions of one or more processors. Figure 1 In an embodiment, the support circuits 108 may include one or more of a power supply, clock circuits, analog-to-digital converters, communication circuits, caches, displays, test sensors, DUT interface and control ports and circuits, environmental event controller interfaces, etc., or a combination thereof.

[0029] Figure 1 The memory 134 of the predictive model generator 128 may include one or more forms of non-transitory computer-readable media, including one or more of read-only memory and random access memory, or any combination thereof. The memory 134 stores software and data, including, for example, but not limited to, test software 136, data sets 138, predictive models 140, and model generators 142. Figure 1 As shown, in some embodiments, the memory 134 of the model generator 128 may include an artificial intelligence machine learning algorithm (AI 144).

[0030] In some embodiments, Figure 1 The generator 128 may be coupled to the environmental event controller 126 and control its operation. Figure 1The environmental event controller 126 may include multiple subsystems that generate controllable environmental events, such as, but not limited to, heat application, cold application, shock application, vibration application, etc.

[0031] As described above, in various embodiments, the generator 128 operates the DUT 102 via, for example, the environmental event generator 126 to induce operational and environmental events that may cause frequency changes. As the events are applied, the generator 128 causes the DUT to collect data 106 regarding changes in at least one frequency-related parameter. In some embodiments, the collected data 106 is transmitted to the generator 128 to create a data set of frequency-related parameters associated with the operational and environmental events, as well as parameters of these events (e.g., temperature, shock level, modem on time, positioning rate, etc.).

[0032] In this disclosure, reference is made to Figure 2 The operation of the test software 136 and the DUT test software 124 executed by the processors 130 and 124, respectively, is described in detail. Figure 3 The operation of the model generator software 142 executed by the processor 130 is described in more detail.

[0033] In some embodiments of the present principles, the test signals of the modem 116 and / or the GNSS receiver 112 can be simulated as real-world signals so that the signal processing software 146 utilizes SUPERCORRELATION TM Software 148, with SUPERCORRELATION TM The technique monitors at least one frequency-dependent parameter in the same manner that it operates in a real-world environment, such as by processing signals received in a multipath environment.

[0034] In some embodiments, the predictive model generator 128 may be embedded in the DUT 102, and all signal processing performed by the DUT 102 and the predictive model generator 28 is performed by the DUT 102. In such embodiments, the predictive model generation process may begin without a model, or alternatively, it may begin with a model (e.g., a reference model) produced by, for example, the manufacturer or a third party. The reference model may be adjusted and altered by the predictive model generator 128 when the DUT 102 is used under normal operating conditions. In such embodiments, the SUPERCORRELATION MODEL may be used to generate the prediction model when the DUT 102 is used in good and poor signal reception environments. TM Techniques may be used to determine at least one frequency-dependent parameter in accordance with the present principles.

[0035] Alternatively or additionally, in some embodiments, the predictive model generator 128 may be remotely located (i.e., in a cloud-based server) from the DUT 102 or multiple DUTs that collect frequency-dependent parameter data and environmental / operational event information. Processing of frequency-dependent parameter data and environmental / operational event information in accordance with present principles may be performed to generate reference models for many different DUTs, or may be processed to generate a model for a specific DUT 102 that provides specific frequency-dependent parameter data and environmental / operational event information.

[0036] Figure 2 A flow chart of a method 200 for generating a test data set according to at least one embodiment of the present principles is depicted. The method 200 may be performed by Figure 1 The predictive model generator 128 may be implemented using the test software 136 and / or the DUT test software 124. In embodiments where the predictive model generator 128 is a separate computing device coupled to the DUT 102, the test software 136 and the DUT test software 124 may communicate with each other to generate the data set. In some embodiments, if the predictive model generator 128 is embedded in the DUT, the test software 136 and DUT test software 124 functionality may be combined into a single process and executed on the DUT to generate the data set.

[0037] Return Reference Figure 2 Method 200 may begin at 202 and proceed to 204, during which test parameters are applied to the DUT. As described above, in some embodiments, the test parameters control various operations of the DUT, such as, but not limited to, display activity, display brightness, modem activity, CPU activity, crystal age, battery voltage, and combinations of operations. Method 200 may proceed to optional 206 or 208.

[0038] Similar to 204, at 206, an environmental event, such as, but not limited to, heating, cooling, vibration, and dropping, is applied to the DUT. That is, in some embodiments, the predictive model generator of the present principles sends control parameters to the environmental event controller to generate an environmental event, including the severity and duration of the environmental event. Method 200 may proceed to 208.

[0039] At 208, frequency-related parameter data is collected as operations and / or combinations of operations (i.e., from 204 and 206 above) are performed at the DUT. As described above, in some embodiments, the frequency-related parameter data may include, for example, frequency and frequency rate of change information related to the operation of the frequency source of the UDT. According to the present principles, frequency is defined as the frequency source output oscillation rate (e.g., cycles per second), and frequency rate of change is defined as the rate of change of frequency over time. In some embodiments, according to the present principles, other higher-order frequency-related parameters may also be used. Additionally, in some embodiments, the frequency-related parameter data may include the temperature of the frequency source during operation.

[0040] As described above, in some embodiments, determining at least one frequency-dependent parameter of interest may use SUPERCORRELATION TM The present invention is performed using a technique to enable signal processing even in harsh signal reception environments, such as urban canyons where multipath interference is high. For example, at least one frequency-related parameter may be related to signal processing of GNSS signals from multiple satellites. These signals are highly sensitive to multipath interference but are important for generating an accurate frequency source in the DUT of the present principles. TM The technology uses robust receiver motion compensation and joint correlation process to enable the reception of GNSS signals in poor reception environments and to generate accurate frequency-related parameters using these GNSS signals. Figure 2 , method 200 can proceed to 210.

[0041] At 210, method 200 constructs a data set based on the collected and determined data. That is, in some embodiments, the data set includes a compilation of all collected data, including but not limited to operations, events, duration of operations and / or events, severity of operations and / or events, temperature information, frequency-related parameter information, time, etc. In some embodiments, data can be collected in the DUT by executing DUT test software. In such embodiments, the data can be collected into a file and transmitted to, for example, a predictive model generator. Alternatively or additionally, in some embodiments, the data can be streamed to the predictive model generator.

[0042] Method 200 may end at 212 .

[0043] In some embodiments, method 200 may also include generating data while the DUT is in use in the field. In such embodiments, the DUT may passively monitor operational activities and / or environmental events rather than actively controlling the occurrence of these events. In such embodiments, sensors such as accelerometers, gyroscopes, temperature sensors, etc. may be used to monitor the environment, and the operating system of the DUT may provide information about the operation of the DUT.

[0044] The collected data can then be used to train a model to predict the frequency response / variation of the frequency source due to a change in at least one of the operating characteristics of the DUT or the environment in which the DUT is operating. For example, Figure 3 A flow chart of a method 300 for creating a predictive model using a data set is depicted in accordance with at least one embodiment of the present invention. The method 300 may begin at 302 and proceed to 304, during which data is collected / accessed from a memory accessible to, for example, an associated device. Figure 2 The method 300 may proceed to 306.

[0045] At 306, it is determined which type of predictive model to create. For example, and as Figure 3 As shown in method 300, in some embodiments of the present principles, a user of an associated device may be given an opportunity to input a request, for example, via an input / output device of the device, requesting what type of model (e.g., LUT, AI / machine learning model, etc.) the user wishes to generate from the collected / stored data. Method 300 may proceed to 308.

[0046] At 308, the collected / accessed data (including at least one of data regarding a change in at least one of an operating characteristic of the associated device or a change in a characteristic of the environment in which the device is operating) is associated with the corresponding frequency response of the change to generate a frequency response model. For example, in some embodiments, a lookup table (LUT) may be generated to associate data parameters (e.g., event parameters) of at least one of the operating characteristic of the device and / or the characteristic of the environment in which the device is operating with corresponding frequency-related parameters, such as a frequency source.

[0047] A generative model of the present principles, such as a LUT, may include data and associated parameters related to environmental and / or operational events as inputs, and may include frequency-related parameters as outputs. For example, a LUT input event may include activation of a display associated with an associated device, and the output may include a final frequency of a frequency source (e.g., an oscillator) associated with the device, such as an increase in frequency. In this example, the DUT may use the known frequency increase of the associated frequency source to alter signal processing to compensate for the change in frequency. In other embodiments, the LUT input may include an increase in ambient temperature that causes the frequency increase. In other embodiments, a shock to the device may cause the frequency of the associated frequency source to "ring" with an initial increase, followed by an oscillatory change in frequency. All of these frequency-related parameter changes may be compensated for by the associated device, such as in signal processing.

[0048] Return Reference Figure 3 In the method, method 300 can proceed to 310. At 310, the generated prediction model, such as a LUT, can be output to be used to correct frequency-related parameter errors of a frequency source of an associated device, for example. In some embodiments, the generated prediction model of the present principles can be used to anticipate the behavior of the frequency-related parameters of the frequency source and compensate for the behavior during signal processing of received radio signals (e.g., GNSS signals, WiFi signals, Bluetooth signals, etc.). The prediction model of the present principles finds particular use in commonly assigned U.S. patent application serial number 63 / 424,185, entitled "Method and apparatus for determining frequency-related parameters of a frequency source using predictive control," filed on November 10, 2022.

[0049] Return reference and Figure 3 As shown, in some embodiments of method 300, the collected / stored data can be implemented to train a machine learning neural network (artificial intelligence (AI)) to create a predictive model of the present principles. For example, if a decision is made at 306 to generate a machine learning (artificial intelligence (AI)) model, method 300 can proceed to 312.

[0050] At 312 , a machine learning neural network is executed. Method 300 may proceed to 314 .

[0051] At 314, using e.g. Figure 2The neural network is trained using a dataset collected / accessed by the user. In some embodiments, the training model has as input data associated with at least one of an operational event and / or an environmental event, as described above, and has as output a frequency-related parameter, such as a change in the frequency of a frequency source associated with an associated device. For example, in some embodiments, the input event may include activating a display associated with the device, and the output may include an increase in the frequency of a frequency source (e.g., an oscillator). The device associated with the frequency source may then use information about the resulting frequency increase to modify the signal processing of the received signal to compensate for the change in frequency. Alternatively or additionally, in some embodiments, the input event may include an increase in ambient temperature, which causes an increase in the frequency of the frequency source associated with the receiving device. In some embodiments, the input event may include a shock to the device, which may cause the frequency of the frequency source to "ring" with an initial increase in frequency, followed by an oscillatory change in frequency. In such and other similar embodiments, such a change in the frequency-related parameter may be compensated for in the signal processing by, for example, the receiving device associated with the frequency source.

[0052] That is, in some embodiments of the present principles, data corresponding to at least one operating characteristic of the radio signal receiving device is collected while the device is in operation. A first training set is created that includes the collected data corresponding to the at least one operating characteristic of the radio signal receiving device. Additionally, data corresponding to at least one environmental event associated with the radio signal receiving device is collected while the device is in operation. A second training set is created that includes the collected data corresponding to the at least one environmental event associated with the radio signal receiving device. Additionally, data corresponding to at least one frequency-related parameter is collected that corresponds to at least one of the at least one operating characteristic and / or at least one environmental event associated with the radio signal receiving device, wherein the at least one frequency-related parameter varies with variations in the at least one operating characteristic and / or at least one environmental event. A third training set is created that includes the collected data corresponding to the at least one frequency-related parameter. In such embodiments, according to the present principles, a neural network is trained using the first, second, and third training sets to generate a predictive model that compensates for variations in the at least one frequency-related parameter corresponding to the at least one operating characteristic and / or at least one environmental event.

[0053] Return Reference Figure 3Method 300 of the present principles, method 300 may proceed to 316. At 316, method 300 outputs a machine learning (e.g., AI-based) prediction model. The model may then be used to predictively correct frequency-related parameter errors based on current operational or environmental events that affect the functionality of the frequency source. That is, in some embodiments, the prediction model of the present principles may be output for correcting frequency-related parameter errors of, for example, a frequency source of an associated device. In some embodiments, the generated prediction model of the present principles may be used to anticipate the behavior of the frequency-related parameters of the frequency source and compensate for that behavior during signal processing of received radio signals (e.g., GNSS signals, WiFi signals, and Bluetooth signals, etc.). Alternatively or in addition to modifying signal processing, the prediction model of the present principles may be used to compensate for frequency-related parameter errors by modifying the operation of the device, including but not limited to turning off / on a display, modifying CPU activity, turning a modem on / off, etc., and / or by adjusting environmental characteristics of the environment in which the device associated with the frequency source is operating, including but not limited to changing the temperature and / or humidity of the environment.

[0054] An embodiment of the predictive model of the present principles generated according to 312-316 above finds particular use in U.S. patent application serial number 63 / 424,185, filed on November 10, 2022, entitled "Method and apparatus for determining frequency-related parameters of a frequency source using predictive control."

[0055] Method 300 may end at 318 .

[0056] In some embodiments, organizing the collected / stored data sets according to the present principles may include processing the data, including but not limited to averaging, combining, filtering, and / or limiting the data in the data set. Alternatively or additionally, data in the data set may also be deleted or corrected if the data is deemed irrelevant, redundant, or inaccurate.

[0057] In some embodiments of the present principles, a method for generating a predictive model includes operating a device under test while collecting data corresponding to at least one frequency-dependent parameter, at least one operating characteristic, and / or at least one environmental event, wherein the at least one frequency-dependent parameter changes as the at least one operating characteristic and / or at least one environmental event changes, and processing the data to generate a predictive model that compensates for changes in the at least one frequency-dependent parameter corresponding to the at least one operating characteristic and / or at least one environmental event.

[0058] In some embodiments of the method, processing the data may include associating at least one of the at least one operating characteristic and / or at least one environmental event with a corresponding at least one frequency-related parameter to determine a frequency response of a frequency source associated with the device under test to a change in at least one of the at least one operating characteristic and / or at least one environmental event.

[0059] In some embodiments, the method may further include using the predictive model to correct a frequency response of a frequency source associated with the device under test for changes in at least one of the at least one operating characteristic and / or the at least one environmental event.

[0060] In some embodiments, the method of correcting the frequency response includes at least one of: adjusting frequency variations of a frequency source during signal processing of a signal received by an associated device under test; adjusting operating characteristics of the device under test; and / or adjusting environmental characteristics of an environment in which the device under test is operating.

[0061] In some embodiments, in the method, the predictive model includes at least one of a lookup table and / or a machine learning model.

[0062] In some embodiments, in the method, the machine learning model comprises a neural network that is trained using collected data corresponding to at least one frequency-related parameter, at least one operating characteristic, and / or at least one environmental event.

[0063] In some embodiments, in the method, the at least one operational characteristic includes at least one of: display activity of a display associated with the device under test, display brightness of a display associated with the device under test, modem activity of a modem associated with the device under test, CPU activity of a CPU associated with the device under test, crystal age of a crystal associated with the device under test, and / or battery voltage of a battery associated with the device under test.

[0064] In some embodiments, in the method, the at least one environmental event includes at least one of the following: heating, cooling, vibration, and / or dropping of the device under test.

[0065] In some embodiments of the present principles, an apparatus for generating a predictive model includes at least one processor and at least one memory, the at least one memory including at least one of a program and / or instructions that, when executed by the processor, causes the apparatus to perform operations comprising operating a device under test while collecting data corresponding to at least one frequency-related parameter, at least one operating characteristic, and / or at least one environmental event, wherein the at least one frequency-related parameter varies with changes in at least one operating characteristic and / or at least one environmental event, and processing the data to generate a predictive model that is used to compensate for changes in the at least one frequency-related parameter corresponding to the at least one operating characteristic and / or at least one environmental event.

[0066] In some embodiments, processing the data in the apparatus includes associating at least one of the at least one operating characteristic and / or at least one environmental event with a corresponding at least one frequency-related parameter to determine a frequency response of a frequency source associated with the device under test to a change in at least one of the at least one operating characteristic and / or at least one environmental event.

[0067] In the apparatus, the apparatus is configured to further use the predictive model to correct a frequency response of a frequency source associated with the device under test to changes in at least one of the at least one operating characteristic and / or the at least one environmental event.

[0068] In some embodiments, correcting the frequency response in the apparatus includes at least one of: adjusting for frequency variation of a frequency source during signal processing of a signal received by an associated device under test; adjusting an operating characteristic of the device under test; and / or adjusting an environmental characteristic of an environment in which the device under test is operating.

[0069] In some embodiments, in the apparatus, the predictive model comprises at least one of a lookup table and / or a machine learning model.

[0070] In some embodiments, in the apparatus, the machine learning model comprises a neural network trained using collected data corresponding to at least one frequency-related parameter, at least one operating characteristic, and / or at least one environmental event.

[0071] In some embodiments, in the apparatus, the at least one operational characteristic includes at least one of: display activity of a display associated with the device under test, display brightness of a display associated with the device under test, modem activity of a modem associated with the device under test, CPU activity of a CPU associated with the device under test, crystal age of a crystal associated with the device under test, and / or battery voltage of a battery associated with the device under test.

[0072] In some embodiments, in the apparatus, the at least one environmental event includes at least one of the following: heating, cooling, vibration, and / or dropping of the device under test.

[0073] In some embodiments, a computer-implemented method for training a neural network to generate a prediction model to compensate for frequency-related errors includes: collecting data corresponding to at least one operating characteristic of a radio signal receiving device in operation; creating a first training set including collected data corresponding to at least one operating characteristic of the radio signal receiving device; collecting data corresponding to at least one environmental event associated with the radio signal receiving device in operation, creating a second training set including collected data corresponding to at least one environmental event associated with the radio signal receiving device, collecting data corresponding to at least one frequency-related parameter, the at least one frequency-related parameter corresponding to at least one operating characteristic and / or at least one environmental event associated with the radio signal receiving device, wherein the at least one frequency-related parameter changes with changes in the at least one operating characteristic and / or at least one environmental event, creating a third training set including collected data corresponding to the at least one frequency-related parameter, and using the first training set, the second training set, and the third training set to train the neural network to generate a prediction model, wherein the prediction model is used to compensate for changes in the at least one frequency-related parameter corresponding to the at least one operating characteristic and / or at least one environmental event.

[0074] In such an embodiment, the generated prediction model may be used to correct a frequency response of a frequency source associated with the radio signal receiving device to changes in at least one of at least one operating characteristic and / or at least one environmental event. In such an embodiment, the correction of the frequency response may include at least one of: adjusting for frequency changes of the frequency source during signal processing of a signal received by the radio signal receiving device; adjusting an operating characteristic of the radio signal receiving device; and / or adjusting an environmental characteristic of an environment in which the radio signal receiving device is operating.

[0075] Those skilled in the art will appreciate that, although various items are shown as being stored in memory or on a storage device when in use, for the purpose of memory management and data integrity, these items or parts thereof can be transferred between memory and other storage devices. Alternatively, in other embodiments, some or all of the software components can be executed in a memory on another device and communicate with the computer system shown via inter-computer communication. Some or all of the system components or data structures can also be stored (e.g., as instructions or structured data) on a computer-accessible medium or portable item for reading by an appropriate drive, various examples of which are described above. In some embodiments, instructions stored separately on a computer-accessible medium can be transmitted to a computing device via a transmission medium or signal (such as an electrical, electromagnetic or digital signal), communicated via a communication medium (such as a network and / or wireless link). Various embodiments can also include receiving, sending or storing instructions and / or data implemented according to the foregoing description on a computer-accessible medium or via a communication medium. Generally speaking, computer accessible media may include storage media or memory media, such as magnetic or optical media, for example, disks or DVD / CD-ROMs, volatile or non-volatile media, such as RAM (e.g., SDRAM, DDR, RDRAM, SRAM, etc.), ROM, etc.

[0076] In various embodiments, the methods and processes described herein may be implemented in software, hardware, or a combination thereof. Furthermore, the order of the methods may be changed, and various elements may be added, reordered, combined, omitted, or otherwise modified. All examples described herein are presented in a non-limiting manner. It will be apparent to those skilled in the art having the benefit of this disclosure that various modifications and variations are possible. Implementations according to the embodiments have been described in the context of specific embodiments. These embodiments are intended to be illustrative rather than limiting. Many variations, modifications, additions, and improvements are possible. Thus, multiple instances of the components described herein may be provided as a single instance. The boundaries between various components, operations, and data stores are somewhat arbitrary, and specific operations are described in the context of specific illustrative configurations. Other allocations of functionality are contemplated and may fall within the scope of the following claims. Structures and functions presented as discrete components in the example configurations may be implemented as combined structures or components. These and other variations, modifications, additions, and improvements may fall within the scope of the embodiments defined in the following claims.

[0077] In the foregoing description, many specific details, examples, and scenarios are set forth in order to provide a more thorough understanding of the present disclosure. However, it should be understood that embodiments of the present disclosure can be practiced without these specific details. Furthermore, such examples and scenarios are provided for illustration and are not intended to limit the present disclosure in any way. With the included description, one of ordinary skill in the art should be able to implement the appropriate functionality without undue experimentation.

[0078] References in the specification to "an embodiment" or the like indicate that the described embodiment may include a particular feature, structure, or characteristic, but not every embodiment may include the particular feature, structure, or characteristic. Such phrases do not necessarily refer to the same embodiment. In addition, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, it is considered within the knowledge of those skilled in the art to affect these features, structures, or characteristics in conjunction with other embodiments, whether or not explicitly indicated.

[0079] Embodiments according to the present disclosure may be implemented in hardware, firmware, software, or any combination thereof. Embodiments may also be implemented as instructions stored using one or more machine-readable media, which may be read and executed by one or more processors. A machine-readable medium may include any mechanism for storing or transmitting information in a form readable by a machine (e.g., a computing device or a "virtual machine" running on one or more computing devices). For example, a machine-readable medium may include any suitable form of volatile or non-volatile memory.

[0080] Furthermore, the various operations, processes, and methods disclosed herein may be embodied in a machine-readable medium and / or machine-accessible medium / storage device compatible with a data processing system (e.g., a computer system) and may be performed in any order (e.g., including using means for implementing the various operations). Accordingly, the description and drawings should be considered illustrative rather than restrictive. In some embodiments, the machine-readable medium may be in the form of a non-transitory machine-readable medium / storage device.

[0081] The modules, data structures, etc. defined herein are defined for ease of discussion and are not intended to imply that any specific implementation details are required. For example, any described modules and / or data structures may be combined or divided into sub-modules, sub-processes, or other units of computer code or data, as required by a particular design or implementation.

[0082] In the accompanying drawings, for ease of description, the specific arrangement or the order of schematic elements can be shown. However, the particular order or arrangement of these elements do not mean that specific processing order or sequence, or the separation of process, are needed in all embodiments. Usually, the schematic elements for representing instruction blocks or modules can be implemented using any suitable form of machine-readable instructions, and each such instruction can be implemented using any suitable programming language, library, application programming interface (API) and / or other software development tools or frameworks. Similarly, the schematic elements for representing data or information can be implemented using any suitable electronic arrangement or data structure. In addition, some connections, relations or associations between elements can be simplified or not shown in the accompanying drawings, to avoid blurring the disclosure.

[0083] This disclosure is to be considered illustrative rather than restrictive, and changes and modifications that come within the guiding principles of this disclosure are intended to be protected.

Claims

1. A method for generating a prediction model, comprising: operating the device under test while collecting data corresponding to at least one frequency-dependent parameter, at least one operating characteristic, and / or at least one environmental event, wherein the at least one frequency-dependent parameter varies as the at least one operating characteristic and / or the at least one environmental event varies; and The data is processed to generate a predictive model that is used to compensate for changes in at least one frequency-dependent parameter corresponding to the at least one operating characteristic and / or the at least one environmental event.

2. The method according to claim 1, wherein Processing the data includes correlating at least one frequency-related parameter with at least one corresponding operating characteristic and / or at least one corresponding environmental event to determine a frequency response of a frequency source associated with the device under test to a change in at least one of the at least one operating characteristic and / or the at least one environmental event.

3. The method according to any one of claims 1 and 2, further comprising: The predictive model is used to correct a frequency response of a frequency source associated with the device under test for changes in at least one of the at least one operating characteristic and / or the at least one environmental event.

4. The method according to claim 3, further comprising: The frequency of the frequency source is adjusted using a motion compensated correlation technique.

5. The method according to claim 4, wherein The motion compensation correlation technology includes a super correlation technology.

6. The method according to claim 3, wherein: Correcting the frequency response includes at least one of: adjusting for frequency variations of the frequency source during signal processing of signals received by the associated device under test; adjusting operating characteristics of the device under test; and / or adjusting environmental characteristics of the environment in which the device under test is operating.

7. The method according to any one of claims 1, 2, 4, 5 and 6, wherein: The predictive model includes at least one of a lookup table and / or a machine learning model.

8. The method according to claim 5, wherein The machine learning model includes a neural network that is trained using collected data corresponding to the at least one frequency-related parameter, the at least one operating characteristic, and / or the at least one environmental event.

9. The method according to any one of claims 1, 2, 4, 5, 6 and 8, wherein The at least one operational characteristic comprises at least one of: display activity of a display associated with the device under test, display brightness of a display associated with the device under test, modem activity of a modem associated with the device under test, CPU activity of a CPU associated with the device under test, crystal age of a crystal associated with the device under test, and / or battery voltage of a battery associated with the device under test, and wherein the at least one environmental event comprises at least one of: heating, cooling, vibration and / or dropping of the device under test.

10. An apparatus for generating a prediction model, comprising: at least one processor; at least one memory comprising at least one of a program and / or instructions that, when executed by the processor, causes the apparatus to perform operations comprising: operating the device under test while collecting data corresponding to at least one frequency-dependent parameter, at least one operating characteristic, and / or at least one environmental event, wherein the at least one frequency-dependent parameter changes as the at least one operating characteristic and / or the at least one environmental event changes; as well as The data is processed to generate a predictive model that is used to compensate for changes in at least one frequency-dependent parameter corresponding to the at least one operating characteristic and / or the at least one environmental event.

11. The device according to claim 10, wherein Processing the data includes correlating at least one frequency-related parameter with at least one corresponding operating characteristic and / or at least one corresponding environmental event to determine a frequency response of a frequency source associated with the device under test to a change in at least one of the at least one operating characteristic and / or the at least one environmental event.

12. The device according to any one of claims 10 and 11, wherein The device also performs: The predictive model is used to correct a frequency response of a frequency source associated with the device under test for changes in at least one of the at least one operating characteristic and / or the at least one environmental event.

13. The device according to claim 12, wherein The device also performs: The frequency of the frequency source is adjusted using a motion compensated correlation technique.

14. The device according to claim 13, wherein The motion compensation correlation technology includes a super correlation technology.

15. The device according to claim 12, wherein Correcting the frequency response includes at least one of: adjusting for frequency variations of the frequency source during signal processing of signals received by the associated device under test; adjusting operating characteristics of the device under test; and / or adjusting environmental characteristics of an environment in which the device under test is operating.

16. The device according to any one of claims 10, 11, 13, 14 and 15, wherein The predictive model includes at least one of a lookup table and / or a machine learning model.

17. The device according to claim 16, wherein The machine learning model includes a neural network that is trained using collected data corresponding to the at least one frequency-related parameter, the at least one operating characteristic, and / or at least one environmental event.

18. The device according to any one of claims 10, 11, 13, 14, 15 and 17, wherein The at least one operational characteristic comprises at least one of: display activity of a display associated with the device under test, display brightness of a display associated with the device under test, modem activity of a modem associated with the device under test, CPU activity of a CPU associated with the device under test, crystal age of a crystal associated with the device under test, and / or battery voltage of a battery associated with the device under test, and wherein the at least one environmental event comprises at least one of: heating, cooling, vibration and / or dropping of the device under test.

19. A computer-implemented method for training a neural network to generate a prediction model to compensate for frequency-dependent errors, comprising: collecting data corresponding to at least one operational characteristic of the radio signal receiving device in operation; creating a first training set comprising collected data corresponding to at least one operating characteristic of the radio signal receiving device; collecting data corresponding to at least one environmental event associated with the radio signal receiving device in operation; creating a second training set comprising collected data corresponding to the at least one environmental event associated with the radio signal receiving device; collecting data corresponding to at least one frequency-dependent parameter corresponding to at least one of the at least one operating characteristic and / or the at least one environmental event associated with the radio signal receiving device, wherein the at least one frequency-dependent parameter varies as the at least one operating characteristic and / or the at least one environmental event varies; creating a third training set comprising the collected data corresponding to the at least one frequency-related parameter; as well as The neural network is trained using the first training set, the second training set, and the third training set to generate a prediction model that is used to compensate for changes in at least one frequency-dependent parameter corresponding to the at least one operating characteristic and / or the at least one environmental event.

20. The method according to claim 19, further comprising: The prediction model is used to correct a frequency response of a frequency source associated with the radio signal receiving device to changes in at least one of the at least one operating characteristic and / or the at least one environmental event, wherein correcting the frequency response comprises at least one of: adjusting frequency changes of the frequency source during signal processing of a signal received by the radio signal receiving device; adjusting the operating characteristics of the radio signal receiving device; and / or adjusting environmental characteristics of the environment in which the radio signal receiving device is operating.

Images