Chip life prediction method and device, electronic equipment and medium

Abstract

The invention discloses a chip life prediction method and device, electronic equipment and a medium, and relates to the technical field of terminals. According to the specific technical scheme, the electronic equipment obtains electrical parameters of electrical signals of the output end of a to-be-detected chip through a feedback detection circuit in the to-be-detected chip; determining a resistance parameter of the chip to be tested according to the electrical parameter; and according to the resistance parameter, the residual use time of the chip to be tested is predicted.

Description

Technical Field

[0001] This application belongs to the field of terminal technology, specifically relating to a chip lifetime prediction method, device, electronic device, and medium. Background Technology

[0002] Currently, smart power amplifier (Smart PA) chips are widely used in various electronic devices because they can detect the load status in real time and optimize the load's performance based on the current-voltage (IV) feedback signal at the output terminal. However, the accuracy of the Smart PA chip in detecting the load status decreases as the remaining usage time of the chip diminishes, thus affecting its ability to optimize the load's performance.

[0003] However, since electronic devices cannot know the remaining usage time of the Smart PA chip during use, they cannot promptly remind users to replace the Smart PA chip. This may lead to poor load performance and thus affect the performance of the electronic device. Summary of the Invention

[0004] The purpose of this application is to provide a chip lifetime prediction method, apparatus, electronic device, and medium that can solve the problem of poor performance of electronic devices.

[0005] In a first aspect, embodiments of this application provide a chip lifetime prediction method, the method comprising: an electronic device acquiring electrical parameters of an electrical signal at the output terminal of the chip under test through a feedback detection circuit in the chip under test; determining the resistance parameters of the chip under test based on the electrical parameters; and predicting the remaining usage time of the chip under test based on the resistance parameters.

[0006] Secondly, embodiments of this application provide a chip lifetime prediction device, which includes an acquisition module and a processing module. The acquisition module is used to acquire electrical parameters of the electrical signal at the output terminal of the chip under test (DUT) through a feedback detection circuit in the DUT. The processing module is used to determine the resistance parameters of the DUT based on the electrical parameters acquired by the acquisition module, and predict the remaining usage time of the DUT based on the resistance parameters.

[0007] Thirdly, embodiments of this application provide an electronic device including a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions implementing the steps of the method as described in the first aspect when executed by the processor.

[0008] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method as described in the first aspect.

[0009] Fifthly, embodiments of this application provide a chip including a processor and a communication interface coupled to the processor, the processor being used to run programs or instructions to implement the method as described in the first aspect.

[0010] In a sixth aspect, embodiments of this application provide a computer program product stored in a storage medium, which is executed by at least one processor to implement the method as described in the first aspect.

[0011] In this embodiment, the electronic device can acquire the electrical parameters of the output signal of the chip under test (DUT) and determine the resistance parameter of the DUT based on these parameters. Since this resistance parameter is related to the remaining usage time of the DUT, the electronic device can accurately determine the remaining usage time of the DUT based on this resistance parameter. This allows the electronic device to promptly remind the user to replace the DUT, preventing damage to the DUT from affecting the performance of the electronic device. Furthermore, since the electronic device can acquire the aforementioned electrical parameters through the existing feedback detection circuit in the DUT without requiring additional components, the cost of the electronic device can be avoided. Thus, the performance of the electronic device can be optimized without increasing its cost. Attached Figure Description

[0012] Figure 1 This is a schematic diagram of the internal structure of a Smart PA chip in related technologies;

[0013] Figure 2 This is one of the flowcharts illustrating the chip lifetime prediction method provided in the embodiments of this application;

[0014] Figure 3 This is a second schematic flowchart of the chip lifetime prediction method provided in the embodiments of this application;

[0015] Figure 4 This is the third flowchart illustrating the chip lifetime prediction method provided in the embodiments of this application;

[0016] Figure 5 This is the fourth flowchart illustrating the chip lifetime prediction method provided in the embodiments of this application;

[0017] Figure 6 This is a schematic diagram of the chip lifetime prediction device provided in the embodiments of this application;

[0018] Figure 7This is one of the hardware structure diagrams of the electronic device provided in the embodiments of this application;

[0019] Figure 8 This is the second schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0021] The following will explain the technical terms used in the embodiments of this application.

[0022] 1. Smart PA chip

[0023] Figure 1 A schematic diagram of the internal structure of a Smart PA chip is shown. Figure 1 As shown, the I2S input interface of the Smart PA chip can be connected to an external digital audio source. The I2S signal (e.g., an audio signal) from the external digital audio source can be transmitted to the speaker protection algorithm module of the Smart PA chip through the I2S input interface. This module can output the I2S signal to the audio power amplifier, and the output of the audio power amplifier (which can be considered the output of the Smart PA chip) is then transmitted to the speaker. Simultaneously, the speaker protection algorithm module can transmit the speaker's IV feedback signal (e.g., the signal that flows back to the aforementioned output after the audio signal has passed through the speaker) to the speaker protection algorithm module via the ADC module and current processing module. The speaker protection algorithm module then uses the IV feedback signal to perform speaker temperature protection, load matching adjustment, and other functions.

[0024] 2. Other terms

[0025] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0026] The terms "at least one," "at least one of," etc., used in the specification and claims of this application refer to any one, any two, or a combination of two or more of the included items. For example, at least one of a, b, and c can mean: "a," "b," "c," "a and b," "a and c," "b and c," and "a, b, and c," where a, b, and c can be single or multiple. Similarly, "at least two" refers to two or more items, and its meaning is similar to that of "at least one."

[0027] The chip lifetime prediction method, apparatus, electronic device, and medium provided in this application will be described in detail below with reference to the accompanying drawings and through specific embodiments and application scenarios.

[0028] Smart PA chips, with their output IV feedback function, can detect load status in real time to optimize performance and are widely used in various electronic devices. The performance stability of their core component, the power amplifier (PA), directly determines the overall lifespan of the chip. During the use of a Smart PA chip, the accuracy of its load status detection decreases as the remaining usage time of the Smart PA chip diminishes, thus affecting its ability to optimize load performance.

[0029] However, since electronic devices cannot know the remaining usage time of the Smart PA chip during use, they cannot promptly remind users to replace the Smart PA chip. This may lead to poor load performance and thus affect the performance of the electronic device.

[0030] To address the aforementioned technical problems, this application provides a chip lifetime prediction method. Figure 2 A schematic flowchart of the chip lifetime prediction method provided in an embodiment of this application is shown. Figure 2 As shown, the chip lifetime prediction method provided in this application embodiment may include the following steps 101 to 103.

[0031] Step 101: The electronic device obtains the electrical parameters of the electrical signal at the output terminal of the chip under test through the feedback detection circuit in the chip under test.

[0032] In some embodiments of this application, the chip under test (DUT) may include, but is not limited to, a smart power amplifier (PA) chip, a central processing unit (CPU) chip, etc. The feedback detection circuit may include, but is not limited to, the current-voltage (IV) feedback current built into the DUT, wherein the IV feedback current is a dedicated detection circuit inside the DUT used to acquire the instantaneous voltage and instantaneous current at the output terminal of the power transistor (PA) in real time.

[0033] It is understandable that the above electrical parameters can be obtained directly through the feedback detection circuit without the need to add other components to the electronic device.

[0034] In some embodiments of this application, the electrical signal at the output of the chip under test (DUT) can be an IV feedback signal. For example, when the DUT is a Smart PA chip, the IV feedback signal can be a signal output by the DUT to a load (e.g., a speaker) connected to it, and this signal can include, but is not limited to, an audio signal.

[0035] It is understandable that after the chip under test outputs an electrical signal to the aforementioned load, the electrical signal can flow through the load and back to the output terminal of the chip under test, so that the electronic device can obtain the electrical parameters of the electrical signal through the feedback detection circuit.

[0036] In some embodiments of this application, the number of the above-mentioned electrical parameters may be at least one. These electrical parameters may include: current parameters and voltage parameters. The current parameter represents the current value of the electrical signal, and the voltage parameter represents the voltage value of the electrical signal.

[0037] In some embodiments of this application, assuming that the chip under test is a Smart PA chip, when the electronic device outputs an electrical signal to the speaker through the chip under test, the electronic device can first turn on the feedback detection circuit and perform secondary noise reduction processing on the electrical signal (which may be an electrical signal directly output from the output terminal, or an electrical signal that has been output from the output terminal and flows through the speaker). Then, the processed audio signal is detected, and the electrical parameters obtained by the PA feedback detection in the chip under test are used to enable the electronic device to obtain the electrical parameters.

[0038] In some examples, when there are at least two electrical parameters, the electronic device can use a sliding window to detect the processed audio signal at least twice in a row, and obtain at least two electrical parameters through feedback detection from the PA in the chip under test.

[0039] Alternatively, the electronic device can first adopt 3 The criteria involve removing abnormal parameters (e.g., parameters with values ​​less than the characteristic baseline or greater than the failure resistance parameter) from the detected electrical parameters, and then using the PA in the chip under test to detect the remaining electrical parameters (i.e., the electrical parameters after removing the abnormal parameters). The failure resistance parameter value can be pre-set, agreed upon, or configured by other devices for the electronic equipment.

[0040] It should be noted that, regarding 3 For an explanation of the guidelines, please refer to the specific descriptions in related technologies; the embodiments in this application will not be repeated here.

[0041] In some embodiments of this application, combined with Figure 2 ,like Figure 3 As shown, step 101 can be implemented through steps 101a and 101b below.

[0042] Step 101a: The electronic device obtains the initial electrical parameters of the electrical signal through the feedback detection circuit in the chip under test.

[0043] In some examples, the initial electrical parameters mentioned above can be the electrical parameters fed back by the PA in the chip under test.

[0044] This is understandable, because the chip under test may be affected by many factors, so the electrical parameters fed back by the PA in the chip under test may not be accurate. In other words, the electrical parameters fed back by the PA may be uncalibrated electrical parameters.

[0045] Step 101b: The electronic device performs parameter calibration on the initial electrical parameters based on the temperature of the chip under test and the ambient temperature of the environment in which the chip under test is located, and obtains the electrical parameters.

[0046] In some examples, the electronic device can use the temperature of the chip under test, the ambient temperature of the environment in which the chip under test is located, and the initial electrical parameters to calculate the aforementioned electrical parameters by inputting them into a preset temperature drift calibration formula.

[0047] It should be noted that the explanation of the temperature drift calibration formula can be found in the specific descriptions in the relevant technologies, and will not be repeated here in the embodiments of this application.

[0048] Therefore, after acquiring the initial electrical parameters of the electrical signal, the electronic device can further calibrate these initial electrical parameters based on factors affecting the chip under test (i.e., the temperature of the chip under test and the ambient temperature of the environment in which the chip under test is located). This ensures that the electronic device can acquire accurate electrical parameters of the electrical signal, thereby ensuring that the electronic device can accurately determine the resistance parameters of the chip under test in subsequent steps, and accurately determine the remaining usage time of the chip under test based on these resistance parameters. This improves the accuracy of the electronic device in determining the remaining usage time of the chip under test.

[0049] Step 102: The electronic device determines the resistance parameters of the chip under test based on the electrical parameters.

[0050] In some embodiments of this application, the resistance parameters described above can be the resistance values ​​of the chip under test.

[0051] In some embodiments of this application, the aforementioned electrical parameters may include the aforementioned voltage and current parameters, thereby allowing the electronic device to substitute the voltage and current parameters into the first formula to calculate the aforementioned resistance parameters. The first formula is:

[0052]

[0053] in, For the above resistance parameters, For the above voltage parameters, This is the voltage offset. For the above current parameters, This represents the current offset.

[0054] Here, the aforementioned voltage offset and current offset It can be a preset offset, such as a voltage offset. It can be set to 0.01 volts V, current offset It can be set to 0.001 amperes (A), thus ensuring that the calculation error of the above resistance parameters is controlled within a certain range. Within 0.5%.

[0055] Step 103: The electronic device predicts the remaining usage time of the chip under test based on the resistance parameters.

[0056] In some embodiments of this application, the association between resistance parameters and usage time can be pre-set in the electronic device, so that the electronic device can determine the remaining usage time based on the usage time associated with the resistance parameters of the chip under test.

[0057] In other embodiments of this application, the electronic device can input the resistance parameters of the chip under test into a neural network model (e.g., the duration prediction model in the following embodiments), and the neural network model can determine the remaining usage time based on the resistance parameters. Combined with Figure 2 ,like Figure 4 As shown, step 103 above can be specifically implemented through step 103a below.

[0058] Step 103a: The electronic device uses the duration prediction model to predict the parameter change trend based on the resistance parameters and outputs the remaining usage time.

[0059] In some examples, the aforementioned duration prediction model may include, but is not limited to, an autoregressive moving average (ARMA) model and a multivariate autoregressive moving average (MARMA) model. This duration prediction model is trained based on resistance parameters and information related to those parameters (e.g., remaining usage time, chip temperature, and ambient temperature of the chip's environment).

[0060] In some examples, electronic devices can use duration prediction models to predict parameter change trends based on the aforementioned resistance parameters and resistance parameter change characteristic curves, and output the remaining usage time.

[0061] Thus, it can be seen that since electronic devices can predict the parameter change trend based on the above resistance parameters using a duration prediction model, and this duration prediction model is trained with a lot of information, it can accurately predict the parameter change trend based on the above resistance parameters. Therefore, the accuracy of the remaining usage time output by the prediction model can be ensured, thereby improving the accuracy of electronic devices in determining the remaining usage time of the chip under test.

[0062] In some examples, step 103a above can be specifically implemented through steps 103a1 and 103a2 as described below.

[0063] Step 103a1: The electronic device calculates the time required for the parameter value of the above resistance parameter to change to the failure resistance parameter value through the duration prediction model.

[0064] Optionally, the failure resistance parameter value can be the resistance parameter value of the chip under test when the chip fails. This failure resistance parameter value can be a positive integer, for example, 100Ω.

[0065] Optionally, the electronic device can use a duration prediction model to substitute the aforementioned resistance parameters into the formula for the resistance parameter change characteristic curve, thereby calculating the change time required for the resistance parameter value of the chip under test to change to the failure resistance parameter value. The formula for the resistance parameter change characteristic curve can be:

[0066]

[0067] in, Let be the resistance parameter at time t, and c be a preset parameter. The resistance parameters at time t-1 are... The resistance parameters at time t-2 are... Let be the resistance parameter at time tn, and n be the order of the model. Let be the duration of the interval between time t and time t-1. All of these are weight parameters.

[0068] In this model, the order n can be equal to the number of electrical parameters.

[0069] It is understandable that as the remaining usage time of the chip under test changes, the resistance parameter of the target chip will also change, and the change of the resistance parameter is related to the change of the remaining usage time of the chip under test. Therefore, the electronic device can use the duration prediction model to calculate the time required for the resistance parameter value to change to the failure resistance parameter value, and determine the remaining usage time based on the change duration.

[0070] Step 103a2: The electronic device determines the changed duration as the remaining usage time.

[0071] Thus, it can be seen that since electronic devices can use the duration prediction model to calculate the time required for the resistance parameter value of the chip under test to change to the failure resistance parameter value based on the resistance parameter value of the chip under test, in other words, electronic devices can accurately determine the remaining usage time based on the resistance change characteristics of the chip under test through the duration prediction model. Therefore, the accuracy of electronic devices in determining the remaining usage time of the chip under test can be improved.

[0072] In some examples, prior to step 103a above, the chip lifetime prediction method provided in this application embodiment may also include steps 201 and 202 as described below.

[0073] Step 201: The electronic device acquires N training sample sets.

[0074] In the implementation of this application, the above-mentioned training sample set includes sample usage time, sample resistance parameters of sample chips, sample temperature of sample chips, and sample ambient temperature of the environment in which the sample chips are located, where N is a positive integer.

[0075] Optionally, each of the above N training sample sets is collected at a single point in time.

[0076] Optionally, the electronic device can acquire usage data from multiple chips (e.g., sample chips and / or chips under test), with each usage data being collected at the same time point. The usage data may include usage duration (the usage duration being the time between the activation time point and the data acquisition time point), the chip's resistance parameters, the chip's temperature, and the ambient temperature of the environment in which the chip is located. The usage data is then used to determine N training sample sets.

[0077] For example, when a chip (e.g., a sample chip and / or a chip under test) is manufactured or a device containing the chip is activated for the first time, the device can collect the resistance parameters of the chip under normal operating conditions as a feature baseline value. This feature baseline value is used to determine abnormal parameters and record the activation time point. This activation time point is used to determine the usage duration of the sample and is stored in the storage module of the device. Then, during the use of the device, a feature change curve is generated by using the resistance parameters in the usage data collected above. The device can associate and store the feature change curve, the temperature of the chip, and the ambient temperature of the environment in which the chip is located to obtain N training sample sets.

[0078] The aforementioned characteristic change curves can be continuously plotted with usage time as the horizontal axis and resistance parameters as the vertical axis.

[0079] The electronic device can use a dual-mode architecture of Static Random Access Memory (SRAM) and Electrically Erasable Memory (EER) to store the above N training sample sets. SRAM enables nanosecond-level real-time read and write, while EER enables data persistence, avoiding data loss due to power failure, and also supports fast data query and backtracking.

[0080] It is understood that the aforementioned N training sample sets may include usage data of sample chips obtained in the laboratory stage and / or usage data of the chip under test obtained in the actual use stage. In this way, the basic database storing the N training sample sets can be updated by multiple different training sample sets, providing sufficient samples for subsequent model training to improve the accuracy of prediction. Thus, subsequent electronic devices can use this real-time calculation method to input the resistance parameters at the current moment into the trained model (i.e., the duration prediction model) to predict the remaining usage time of the chip under test.

[0081] Step 202: The electronic device trains the preset model based on N training sample sets to obtain the duration prediction model.

[0082] Optionally, the aforementioned preset model may include, but is not limited to, the autoregressive moving average model (ARMA) and the multivariate autoregressive moving average model (MARMA).

[0083] Optionally, the electronic device can input different training sample sets from N training sample sets into a preset model, use the preset model to predict the parameter change trend, determine the loss function based on the output prediction result, and use the loss function to iteratively optimize the model parameters through the gradient descent algorithm, and assign weights to each input variable (among which the chip's resistance parameter and temperature have the highest weights, determined through feature importance analysis) to train the preset model.

[0084] For example, suppose the preset model is an autoregressive moving average (ARMA) model, which is usually denoted as AMRA(p,q), and its expression is as follows:

[0085]

[0086] in, For the observation at time point t, This can be a constant term or an intercept term, representing the average level of the pre-defined model. For autoregressive (AR) parameters, Let be the observation at time point ti, where each express right The degree of influence, where p is the order of the autoregressive term. The moving average (MA) parameter, Let be the random error term at time point tj, where each express right The degree of influence, where q is the order of the moving average term.

[0087] When q is 0, the ARMA model is equivalent to the autoregressive model AR(q), and its general form is shown below:

[0088]

[0089] When p is 0, the ARMA model is equivalent to the autoregressive model AR(q), and its general form is shown below:

[0090]

[0091] In this way, the electronic device can use the sample resistance parameters from M training sample sets out of N training sample sets as the target variable (e.g., as mentioned above). Using the sample time points, sample temperatures, and sample ambient temperatures from the M training sample sets as input variables, a multivariate autoregressive moving average model (MARMA) is constructed to replace the traditional univariate ARMA model. This model is adapted to lifetime prediction scenarios under the combined influence of multiple parameters, and the formula for the characteristic curve of the resistance parameter change can be obtained. That is:

[0092]

[0093] in, Let be the resistance parameter at time t, and c be a preset parameter. The resistance parameters at time t-1 are... The resistance parameters at time t-2 are... Let be the resistance parameter at time tn, and n be the order of the model. Let be the duration of the interval between time t and time t-1. All of these are weight parameters.

[0094] In this way, the electronic device can determine p and q, for example, by jointly determining p and q using the Akaike information criterion and the Bayesian information criterion, and determine the values ​​of a, b, and c. Then, it substitutes the other training sample sets in the N training sample sets excluding the above M training sample sets into the formula of the resistance parameter change characteristic curve for calculation, and outputs the prediction result.

[0095] For example, assuming p is 2, then M is also equal to 2, a is 0.4, b is 0.3, and c is 0.3. The formula for the characteristic curve of the resistance parameter variation can then be:

[0096]

[0097] Understandable. This represents the resistance value at time t. and This represents the actual resistance value of the chip under test at a historical moment, reflecting the "time-series dependence of resistance value." The current resistance value is influenced by the historical resistance values ​​of the previous two time periods (corresponding to an autoregressive order of p=2; a larger p value results in more accurate predictions). A multivariate fusion term is incorporated with weights of 0.4 / 0.3 / 0.4, directly participating in the current resistance value. The calculations demonstrate the direct driving effect of time on resistance degradation.

[0098] At this point, the electronic device can substitute the other training sample sets from the N training sample sets excluding the aforementioned M training sample sets into the formula for the resistance parameter change characteristic curve to perform calculations and output the prediction results.

[0099] Thus, it can be seen that since the electronic device can acquire different training sample sets collected at different sample time points and train the preset model based on these different training sample sets, the preset model can learn the correlation between sample time points, sample resistance parameters, sample temperature, and sample ambient temperature. In this way, it can learn the changing trend of the chip's resistance parameters over time. That is to say, the duration prediction model has learned the changing trend of the chip's resistance parameters over time. Therefore, in subsequent steps, the electronic device can accurately predict the parameter change trend through the duration prediction model and output the accurate remaining usage time, thereby improving the accuracy of the electronic device in determining the remaining usage time of the chip under test.

[0100] In some examples, the chip lifetime prediction method provided in this application embodiment may further include the following steps 203 and 204.

[0101] Step 203: When the model accuracy corresponding to the duration prediction model is less than or equal to the accuracy threshold, the electronic device acquires T historical datasets.

[0102] It should be noted that the execution order of steps 203 and 103a is not limited in this embodiment of the application; in one example, the electronic device may execute step 203 first and then step 103a; in another example, the electronic device may execute step 103a first and then step 203.

[0103] In this embodiment of the application, the aforementioned historical dataset includes historical usage duration, historical resistance parameters of the chip under test, historical temperature of the chip under test, and historical ambient temperature of the environment in which the chip under test is located, where T is a positive integer.

[0104] It should be noted that for an explanation of the model accuracy corresponding to the prediction model for the duration of electronic devices, please refer to the specific description in the relevant technology, and the embodiments of this application will not be repeated here.

[0105] Optionally, the above precision threshold can be a positive integer, for example, the precision threshold can be 3%.

[0106] Optionally, each of the T historical datasets mentioned above was collected at the same point in time.

[0107] Optionally, the electronic device can obtain historical datasets from a dataset spanning a preset period of time prior to the current point in time. The preset period can be in units including, but not limited to, seconds, minutes, hours, days, weeks, and months. For example, the preset period could be two months, meaning the electronic device can obtain historical datasets from the datasets of the two months preceding the current point in time.

[0108] Step 204: The electronic device updates the duration prediction model based on T historical datasets.

[0109] Optionally, the electronic device can train the duration prediction model based on T historical datasets, thereby updating the duration prediction model.

[0110] It should be noted that, for the explanation of how electronic devices train a duration prediction model based on T historical datasets, please refer to the specific description of how electronic devices train a preset model based on N training sample sets in the above embodiments. This application will not repeat the description here.

[0111] Thus, it can be seen that since the electronic device can update the duration prediction model again based on T historical datasets when the model accuracy corresponding to the duration prediction model is less than or equal to the accuracy threshold, that is, when the model accuracy corresponding to the duration prediction model is low, the updated duration prediction model can accurately determine the remaining usage time of the chip under test. Therefore, the accuracy of the electronic device in determining the remaining usage time of the chip under test can be improved.

[0112] In some examples, after the electronic device inputs the resistance parameters into the duration prediction model, it can also adjust the degradation rate coefficient corresponding to the temperature based on the temperature of the chip under test and the ambient temperature of the environment in which the chip under test is located (for example, adjusting a and b in the formula of the resistance parameter change characteristic curve mentioned above), thereby improving the accuracy of the electronic device in determining the remaining usage time of the chip under test.

[0113] As described above, the embodiments of this application can directly obtain the electrical parameters of the electrical signals that the chip under test (DUT) needs to output through the existing circuitry (i.e., the feedback detection circuit) in the DUT. Based on these electrical parameters, the resistance parameters of the DUT can be determined, thus determining the relevant parameters of the DUT itself. This allows for accurate prediction of the remaining usage time of the DUT based on its own parameters, improving the accuracy of determining the remaining usage time. Furthermore, this application requires no new components and no additional electrical signals from the DUT, avoiding significant changes to the structure and system architecture of the DUT and preventing the DUT from performing additional operations. This ensures that the cost of the electronic device is not increased and that the power consumption of the electronic device is not increased.

[0114] This application provides a chip lifespan prediction method. An electronic device can obtain the electrical parameters of the electrical signal of the chip under test (DUT) through a feedback detection circuit in the DUT, and determine the resistance parameter of the DUT based on these electrical parameters. Therefore, the electronic device can predict the remaining usage time of the DUT based on the resistance parameter. Since the electronic device can obtain the electrical parameters of the electrical signal at the output terminal of the DUT and determine the resistance parameter based on these electrical parameters, and this resistance parameter is related to the remaining usage time of the DUT, the electronic device can determine the accurate remaining usage time of the DUT based on the resistance parameter. This allows the electronic device to promptly remind the user to replace the DUT, avoiding performance impact due to DUT damage. Furthermore, since the electronic device can obtain the aforementioned electrical parameters through the existing feedback detection circuit in the DUT without the need for additional components, the cost of the electronic device can be avoided. Thus, the performance of the electronic device can be optimized without increasing its cost.

[0115] Furthermore, since electronic devices can directly determine the remaining service life of the chip under test based on the existing components in the chip under test, there is no need to make significant modifications to the structure of the chip under test. In other words, the system can be built based on the existing IV feedback architecture, thus adapting to chips under test of different specifications. Therefore, it has strong versatility, reduces application costs, and facilitates large-scale promotion and application.

[0116] In some embodiments of this application, after step 103 above, the chip lifetime prediction method provided in the embodiments of this application may further include step 104 below.

[0117] Step 104: If the remaining usage time of the electronic device is less than or equal to the time threshold, output a prompt message.

[0118] In this embodiment of the application, the above-mentioned prompt information is used to indicate the remaining usage time.

[0119] In some examples, the units for the aforementioned duration threshold may include, but are not limited to, seconds, minutes, hours, days, weeks, months, etc. For example, the duration threshold could be 3 days.

[0120] In this embodiment, if the remaining usage time is less than or equal to the time threshold, the chip under test can be considered to be about to fail (or be damaged). Therefore, the electronic device can output a prompt message to remind the user to repair or replace the chip under test in a timely manner, thereby reducing the situation where the user cannot use the electronic device due to the failure to repair or replace the chip under test in a timely manner.

[0121] In some examples, electronic devices may output prompts in ways including but not limited to vibration alerts, notification messages, voice prompts, and screen flashing.

[0122] In some examples, the above prompt may also include repair advice, which describes at least one of the following: the chip under test is about to fail, the remaining usage time, the address of a nearby repair shop, and the contact information of a nearby repair shop.

[0123] For example, assuming the time limit is 3 days, when the remaining usage time reaches 3 days, the electronic device can pop up a notification message in the notification bar: "Your phone's speaker chip is about to be damaged (estimated to be usable for 3 days). It is recommended to go to an official repair store as soon as possible to replace it to avoid affecting usage. The address of the nearest repair store is No. CD, Street A, and the contact number of the repair store is 12345678."

[0124] Thus, since electronic devices can output a prompt message when the remaining usage time is less than or equal to the time threshold, i.e. when the chip under test is about to fail (or be damaged), the prompt message can promptly inform the user that the chip under test is about to fail (or be damaged). Therefore, it can reduce the situation where users cannot use electronic devices due to untimely repair or replacement of the chip under test, thereby improving the operational reliability of electronic devices.

[0125] The chip lifetime prediction method provided in the embodiments of this application will be described below with a complete solution.

[0126] like Figure 5 As shown, the chip lifetime prediction method provided in this application embodiment may include the following steps:

[0127] Step 1: Power on the electronic device / activate the chip.

[0128] Step 2, Initial Feature Acquisition: Obtain the baseline value of the solder joint resistance of the chip under test.

[0129] The aforementioned solder joints can be understood as the output terminals of the chip under test.

[0130] Specifically, the main control chip of the electronic device can control the monitoring module to collect the initial resistance parameter of the chip under test, assuming it is 50Ω, and store the initial resistance parameter as a characteristic baseline value (i.e., the solder joint resistance baseline value). Furthermore, the electronic device has a failure resistance parameter value pre-configured or set by the user or other devices.

[0131] Furthermore, a duration prediction model is configured in the electronic device to predict the remaining usage time of the chip under test.

[0132] Step 3: Store the baseline resistance value in the basic database.

[0133] Step 4: The monitoring module collects the solder joint resistance value in real time.

[0134] Specifically, each time the chip under test is turned on, the monitoring module automatically monitors the electrical signal (e.g., current-voltage (IV) feedback signal) at the output terminal (e.g., the solder joint mentioned above) of the chip under test. In this way, the electronic device can obtain the electrical parameters of the IV feedback signal, determine the resistance parameter (e.g., the resistance value mentioned above) of the chip under test based on the electrical parameters, and input the resistance parameter into the duration prediction model, so that the duration prediction model predicts the time required for the resistance parameter of the chip under test to change to the failure resistance parameter value (i.e., the remaining usage time of the chip under test), and outputs the remaining usage time.

[0135] Specifically, when the number of resistance parameters of the chip under test is at least two, the electronic device can also remove abnormal data (e.g., parameters that are less than the characteristic baseline value or greater than the failure resistance parameter value) from at least two resistance parameters based on the aforementioned characteristic baseline value and failure resistance parameter value.

[0136] It is understandable that this application does not require additional device activation, as the feedback detection circuit is already activated during normal playback. In terms of basic functions, it only requires the algorithm to calculate the resistance parameters of the chip under test and input them into the pre-trained duration prediction model, which has a very small impact on power consumption.

[0137] Step 5, Signal Processing Unit: Filtering, noise reduction, digital-to-analog conversion.

[0138] Specifically, electronic devices can use a signal processing unit to filter, reduce noise, and perform digital-to-analog conversion on the aforementioned resistance parameters.

[0139] Step 6: The main control chip generates characteristic curves.

[0140] Specifically, the electronic device can input the processed parameters into the duration prediction model, and generate a feature curve through the duration prediction model.

[0141] Step 7: The main control chip determines whether the solder joint resistance has reached the warning threshold.

[0142] Specifically, the main control chip can determine whether the warning threshold has been reached based on the parameters processed above (i.e., solder joint resistance). This warning threshold can be set by the user or pre-configured in the main control chip. It can be understood that if the warning threshold is reached, the remaining usage time of the chip under test is considered to be relatively short. Therefore, step 8 can be executed to determine the specific remaining usage time.

[0143] Specifically, if the solder joint resistance reaches the warning threshold, then proceed to step 8; if the solder joint resistance does not reach the warning threshold, then proceed to step 4.

[0144] Step 8: The algorithm predicts the remaining available time of the chip.

[0145] Specifically, the main control chip can use a duration prediction model to predict the parameter change trend based on the parameters processed above, and output the remaining usage time.

[0146] Step 9: Push early warning reminders and maintenance suggestions to users.

[0147] Specifically, when the remaining usage time reaches the set time threshold (e.g., 3 days), a notification message will pop up in the notification bar of the electronic device: "Your phone's speaker chip is about to be damaged (estimated to be usable for 3 days). It is recommended to go to an official repair store for replacement as soon as possible to avoid affecting usage," along with the address and contact information of a nearby repair store.

[0148] Step 10: Determine if the user needs repairs.

[0149] Specifically, if the user has not repaired the device, proceed to step 11; if the user has already repaired the device, proceed to step 12.

[0150] Step 11: Continuously monitor until the chip under test is fully realized.

[0151] Step 12: After replacing the chip under test, re-collect the baseline value of the solder joint resistance.

[0152] Specifically, after performing step 12, the electronic device can perform step 4 again.

[0153] It should be noted that for the details of steps 1 to 12 above, please refer to the specific description in the above embodiments, and the embodiments of this application will not be repeated here.

[0154] In summary, this application has the following main beneficial effects:

[0155] Early warning: By monitoring the gradual change in the resistance parameter of the chip under test, the fault can be predicted before the chip under test is completely damaged, giving users enough time to arrange repairs and avoiding the inconvenience caused by sudden functional failures.

[0156] High accuracy: It relies on the IV feedback function of the chip under test to collect the IV feedback signal, and combines filtering to optimize the accuracy of PA resistance calculation; it refines the MARMA model parameters, determines the optimal order through joint criteria, and scientifically allocates the weights of input variables. Compared with traditional physical models, simple statistical methods and single-variable ARMA models, it greatly improves the accuracy and adaptability of chip life prediction, and avoids equipment failure or resource waste caused by prediction deviation.

[0157] High compatibility: No major structural modifications to the chip under test are required. The system can be built based on the existing IV feedback architecture and can be adapted to chips under test of different specifications. It has strong versatility, reduces application costs, and facilitates large-scale promotion and application.

[0158] User-friendly: The reminders are clear and concise, and maintenance suggestions are provided to reduce the user's operating costs.

[0159] It should be noted that each of the above method embodiments, or various possible implementations of each method embodiment, can be executed individually or in combination of any two or more. The specific implementation can be determined according to actual usage requirements, and this application embodiment does not impose any restrictions on this.

[0160] The chip lifetime prediction method provided in this application can be executed by a chip lifetime prediction device. This application uses a chip lifetime prediction device executing the chip lifetime prediction method as an example to illustrate the chip lifetime prediction device provided in this application.

[0161] Figure 6 This is a schematic diagram of a chip lifetime prediction device provided in an embodiment of this application. Figure 6 As shown, the chip lifetime prediction device 500 includes an acquisition module 501 and a processing module 502.

[0162] The acquisition module 501 acquires the electrical parameters of the output signal of the chip under test (DUT) through a feedback detection circuit in the DUT. The processing module 502 determines the resistance parameters of the DUT based on the electrical parameters acquired by the acquisition module 501, and predicts the remaining usage time of the DUT based on the resistance parameters.

[0163] This application provides a chip lifetime prediction device. Since the chip lifetime prediction device can acquire the electrical parameters of the output signal of the chip under test (DUT) and determine the resistance parameter of the DUT based on these electrical parameters, and since this resistance parameter is related to the remaining usage time of the DUT, the chip lifetime prediction device can determine the accurate remaining usage time of the DUT based on this resistance parameter. This allows the chip lifetime prediction device to promptly remind the user to replace the DUT, preventing damage to the DUT from affecting the performance of the chip lifetime prediction device. Furthermore, since the chip lifetime prediction device can acquire the aforementioned electrical parameters through the existing feedback detection circuit in the DUT without requiring additional components, the cost of the chip lifetime prediction device can be avoided. Thus, the performance of the chip lifetime prediction device can be optimized without increasing its cost.

[0164] In some embodiments of this application, the processing module 502 is specifically used to predict the parameter change trend based on the resistance parameters using a duration prediction model, and output the remaining usage time.

[0165] Thus, it can be seen that since the chip life prediction device can predict the parameter change trend based on the resistance parameter through the duration prediction model, and the duration prediction model is trained with a lot of information, that is, the duration prediction model can accurately predict the parameter change trend based on the resistance parameter. Therefore, the accuracy of the remaining usage time output by the prediction model can be ensured, thereby improving the accuracy of the chip life prediction device in determining the remaining usage time of the chip under test.

[0166] In some embodiments of this application, the processing module 502 is specifically used to calculate the change time required for the resistance parameter value of the chip under test to change to the failure resistance parameter value based on the resistance parameter using a duration prediction model; and to determine the change time as the remaining usage time.

[0167] Thus, it can be seen that since the chip life prediction device can calculate the time required for the resistance parameter of the chip under test to change to the failure resistance parameter value based on the resistance parameter using the duration prediction model, the chip life prediction device can accurately determine the remaining usage time based on the resistance change characteristics of the chip under test. Therefore, the accuracy of the chip life prediction device in determining the remaining usage time of the chip under test can be improved.

[0168] In some embodiments of this application, the acquisition module 501 is further configured to acquire N training sample sets before the processing module 502 predicts the parameter change trend based on the resistance parameters using the duration prediction model. These training sample sets include sample usage duration, sample resistance parameters of the sample chip, sample temperature of the sample chip, and sample ambient temperature of the environment in which the sample chip is located. The processing module 502 is further configured to train a preset model based on the N training sample sets acquired by the acquisition module 501 to obtain a duration prediction model; where N is a positive integer.

[0169] Thus, it can be seen that since the chip lifetime prediction device can acquire different training sample sets collected at different sample time points, and train the preset model based on these different training sample sets, the preset model can learn the correlation between sample time points, sample resistance parameters, sample temperature, and sample ambient temperature, thereby learning the changing trend of the chip's resistance parameters over time. In other words, the duration prediction model has learned the changing trend of the chip's resistance parameters over time. Therefore, in subsequent steps, the chip lifetime prediction device can accurately predict the parameter change trend through the duration prediction model and output an accurate remaining usage time, thereby improving the accuracy of the chip lifetime prediction device in determining the remaining usage time of the chip under test.

[0170] In some embodiments of this application, the acquisition module 501 is further configured to, after predicting the parameter change trend based on the resistance parameters using the duration prediction model and outputting the remaining usage time, acquire T historical datasets if the model accuracy corresponding to the duration prediction model is less than or equal to an accuracy threshold. These historical datasets include historical usage time, historical resistance parameters of the chip under test, historical temperature of the chip under test, and historical ambient temperature of the environment in which the chip under test is located. The processing module 502 is further configured to update the duration prediction model based on the T historical datasets acquired by the acquisition module 501; where T is a positive integer.

[0171] Thus, it can be seen that since the chip lifetime prediction device can update the lifetime prediction model again based on T historical datasets when the model accuracy corresponding to the lifetime prediction model is less than or equal to the accuracy threshold, that is, when the model accuracy corresponding to the lifetime prediction model is low, the updated lifetime prediction model can accurately determine the remaining usage time of the chip under test. Therefore, the accuracy of the chip lifetime prediction device in determining the remaining usage time of the chip under test can be improved.

[0172] In some embodiments of this application, the chip life prediction device 500 provided in this application further includes: a prompting module, used to output prompting information when the remaining usage time is less than or equal to a duration threshold after the processing module 502 predicts the remaining usage time of the chip under test based on the resistance parameters; wherein the prompting information is used to indicate the remaining usage time.

[0173] Thus, since the chip life prediction device can also output a prompt message when the remaining usage time is less than or equal to the time threshold, that is, when the chip under test is about to fail (or be damaged), the user can be promptly notified of the impending failure (or damage) of the chip under test. Therefore, the situation where the user cannot use the chip life prediction device due to untimely repair or replacement of the chip under test can be reduced, thereby improving the operational reliability of the chip life prediction device.

[0174] In some embodiments of this application, the acquisition module 501 is specifically used to acquire the initial electrical parameters of the electrical signal; and to perform parameter calibration on the initial electrical parameters according to the temperature of the chip under test and the ambient temperature of the environment in which the chip under test is located, so as to obtain the electrical parameters.

[0175] Therefore, after acquiring the initial electrical parameters of the electrical signal, the chip lifetime prediction device can further calibrate these initial electrical parameters based on factors affecting the chip under test (i.e., the temperature of the chip under test and the ambient temperature of the environment in which the chip under test is located). This ensures that the chip lifetime prediction device can acquire accurate electrical parameters of the electrical signal, thereby ensuring that the chip lifetime prediction device can accurately determine the resistance parameters in subsequent steps and accurately determine the remaining usage time of the chip under test based on these resistance parameters. In this way, the accuracy of the chip lifetime prediction device in determining the remaining usage time of the chip under test can be improved.

[0176] The chip lifetime prediction device in this application embodiment can be an electronic device or a component within an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices besides a terminal. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. It can also be a server, network attached storage (NAS), personal computer (PC), television (TV), ATM, or self-service machine, etc. This application embodiment does not specifically limit the device.

[0177] The chip lifetime prediction device in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.

[0178] The chip lifetime prediction device provided in this application embodiment can achieve... Figures 2 to 5 The various processes implemented in the method implementation examples will not be described again here to avoid repetition.

[0179] In some embodiments of this application, such as Figure 7As shown, this application embodiment also provides an electronic device 600, including a processor 601 and a memory 602. The memory 602 stores a program or instructions that can run on the processor 601. When the program or instructions are executed by the processor 601, they implement the various steps of the above-described chip lifetime prediction method embodiment and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0180] It should be noted that the electronic devices in the embodiments of this application include the aforementioned mobile electronic devices and non-mobile electronic devices.

[0181] Figure 8 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of this application.

[0182] The electronic device 700 includes, but is not limited to, components such as: radio frequency unit 701, network module 702, audio output unit 703, input unit 704, sensor 705, display unit 706, user input unit 707, interface unit 708, memory 709, and processor 710.

[0183] Those skilled in the art will understand that the electronic device 700 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 710 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 8 The electronic device structure shown does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0184] The processor 710 is used to obtain the electrical parameters of the electrical signal at the output terminal of the chip under test through the feedback detection circuit in the chip under test; and determine the resistance parameters of the chip under test based on the electrical parameters; and predict the remaining usage time of the chip under test based on the resistance parameters.

[0185] This application provides an electronic device that can acquire the electrical parameters of the output signal of a chip under test (DUT) and determine the resistance parameters of the DUT based on these parameters. Since the resistance parameters are related to the remaining usage time of the DUT, the electronic device can accurately determine the remaining usage time of the DUT based on these resistance parameters. This allows the electronic device to promptly remind the user to replace the DUT, preventing damage to the DUT from affecting the performance of the electronic device. Furthermore, since the electronic device can acquire the aforementioned electrical parameters through the existing feedback detection circuit in the DUT without requiring additional components, the cost of the electronic device can be avoided. Thus, the performance of the electronic device can be optimized without increasing its cost.

[0186] In some embodiments of this application, the processor 710 is specifically used to predict the parameter change trend based on the resistance parameters using a duration prediction model, and output the remaining usage time.

[0187] Thus, it can be seen that since electronic devices can predict the trend of parameter changes based on resistance parameters through a duration prediction model, and this duration prediction model is trained with a lot of information, that is, the duration prediction model can accurately predict the trend of parameter changes based on resistance parameters. Therefore, the accuracy of the remaining usage time output by the prediction model can be ensured, thereby improving the accuracy of electronic devices in determining the remaining usage time of the chip under test.

[0188] In some embodiments of this application, the processor 710 is specifically used to calculate, based on the resistance parameters, the time required for the resistance parameter value of the chip under test to change to the failure resistance parameter value using a time prediction model; and to determine the time of change as the remaining usage time.

[0189] Thus, it can be seen that since electronic devices can use duration prediction models to calculate the time required for the resistance parameter value of the chip under test to change to the failure resistance parameter value based on the resistance parameter, electronic devices can accurately determine the remaining usage time based on the resistance change characteristics of the chip under test through duration prediction models. Therefore, the accuracy of electronic devices in determining the remaining usage time of the chip under test can be improved.

[0190] In some embodiments of this application, the processor 710 is further configured to acquire N training sample sets before predicting the parameter change trend based on the resistance parameters using the duration prediction model. The training sample sets include sample usage duration, sample resistance parameters of the sample chip, sample temperature of the sample chip, and sample ambient temperature of the environment in which the sample chip is located. The processor 710 is also configured to train a preset model based on the N training sample sets to obtain a duration prediction model. N is a positive integer.

[0191] Thus, it can be seen that since the electronic device can acquire different training sample sets collected at different sample time points and train the preset model based on these different training sample sets, the preset model can learn the correlation between sample time points, sample resistance parameters, sample temperature, and sample ambient temperature. In this way, it can learn the changing trend of the chip's resistance parameters over time. That is to say, the duration prediction model has learned the changing trend of the chip's resistance parameters over time. Therefore, in subsequent steps, the electronic device can accurately predict the parameter change trend through the duration prediction model and output the accurate remaining usage time, thereby improving the accuracy of the electronic device in determining the remaining usage time of the chip under test.

[0192] In some embodiments of this application, the processor 710 is further configured to, after predicting the parameter change trend based on the resistance parameters using the duration prediction model and outputting the remaining usage time, acquire T historical datasets, wherein the historical datasets include historical usage time, historical resistance parameters of the chip under test, historical temperature of the chip under test, and historical ambient temperature of the environment in which the chip under test is located, and update the duration prediction model based on the T historical datasets; wherein T is a positive integer.

[0193] Thus, it can be seen that since the electronic device can update the duration prediction model again based on T historical datasets when the model accuracy corresponding to the duration prediction model is less than or equal to the accuracy threshold, that is, when the model accuracy corresponding to the duration prediction model is low, the updated duration prediction model can accurately determine the remaining usage time of the chip under test. Therefore, the accuracy of the electronic device in determining the remaining usage time of the chip under test can be improved.

[0194] In some embodiments of this application, the processor 710 is further configured to output a prompt message when the remaining usage time is less than or equal to a duration threshold after predicting the remaining usage time of the chip under test based on the resistance parameters; wherein the prompt message is used to indicate the remaining usage time.

[0195] Thus, since electronic devices can output a prompt message when the remaining usage time is less than or equal to the time threshold, i.e. when the chip under test is about to fail (or be damaged), the prompt message can promptly inform the user that the chip under test is about to fail (or be damaged). Therefore, it can reduce the situation where users cannot use electronic devices due to untimely repair or replacement of the chip under test, thereby improving the operational reliability of electronic devices.

[0196] In some embodiments of this application, the processor 710 is specifically used to acquire the initial electrical parameters of the electrical signal; and to perform parameter calibration on the initial electrical parameters according to the temperature of the chip under test and the ambient temperature of the environment in which the chip under test is located, so as to obtain the electrical parameters.

[0197] Therefore, after acquiring the initial electrical parameters of the electrical signal, the electronic device can further calibrate these initial electrical parameters based on factors affecting the chip under test (i.e., the temperature of the chip under test and the ambient temperature of the environment in which the chip under test is located). This ensures that the electronic device can acquire accurate electrical parameters of the electrical signal, thereby ensuring that the electronic device can accurately determine the resistance parameters in subsequent steps and accurately determine the remaining usage time of the chip under test based on the resistance parameters. This improves the accuracy of the electronic device in determining the remaining usage time of the chip under test.

[0198] It should be understood that, in this embodiment, the input unit 704 may include a graphics processing unit (GPU) 7041 and a microphone 7042. The GPU 7041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 706 may include a display panel 7061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 707 includes at least one of a touch panel 7071 and other input devices 7072. The touch panel 7071 is also called a touch screen. The touch panel 7071 may include a touch detection device and a touch controller. Other input devices 7072 may include, but are not limited to, a physical keyboard, function keys (such as volume control buttons, power buttons, etc.), a trackball, a mouse, and a joystick, which will not be described in detail here.

[0199] The memory 709 can be used to store software programs and various data. The memory 709 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 709 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 709 in the embodiments of this application includes, but is not limited to, these and any other suitable types of memory.

[0200] Processor 710 may include one or more processing units; optionally, processor 710 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 710.

[0201] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described chip lifetime prediction method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0202] The processor mentioned above is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0203] This application also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described chip lifetime prediction method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0204] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0205] This application provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the chip lifetime prediction method embodiment described above, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0206] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0207] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0208] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for predicting chip lifetime, characterized in that, include: The electrical parameters of the electrical signal at the output terminal of the chip under test are obtained through the feedback detection circuit in the chip under test. Based on the electrical parameters, determine the resistance parameters of the chip under test; Based on the resistance parameters, the remaining usage time of the chip under test is predicted.

2. The method according to claim 1, characterized in that, The step of predicting the remaining usage time of the chip under test based on the resistance parameters includes: The remaining usage time is output by predicting the parameter change trend based on the resistance parameters using a duration prediction model.

3. The method according to claim 2, characterized in that, The prediction of parameter change trends based on the resistance parameters using the duration prediction model includes: The duration prediction model is used to calculate the time required for the resistance parameter value to change to the failure resistance parameter value. The duration of the change is determined as the remaining usage duration.

4. The method according to claim 2, characterized in that, Before the duration prediction model is used to predict the parameter change trend based on the resistance parameters, the method further includes: Obtain N training sample sets, which include sample usage time, sample resistance parameters of sample chips, sample temperature of sample chips, and sample ambient temperature of the environment in which the sample chips are located. The preset model is trained based on the N training sample sets to obtain the duration prediction model; Where N is a positive integer.

5. The method according to claim 2, characterized in that, The method further includes: If the model accuracy corresponding to the duration prediction model is less than or equal to the accuracy threshold, obtain T historical datasets. The historical datasets include the historical usage duration, the historical resistance parameters of the chip under test, the historical temperature of the chip under test, and the historical ambient temperature of the environment in which the chip under test is located. The duration prediction model is updated based on the T historical datasets. Where T is a positive integer.

6. The method according to claim 1, characterized in that, After predicting the remaining usage time of the chip under test based on the resistance parameters, the method further includes: If the remaining usage time is less than or equal to the time threshold, a prompt message will be output; The prompt message is used to indicate the remaining usage time.

7. The method according to claim 1, characterized in that, The electrical parameters for obtaining the electrical signal at the output terminal of the chip under test include: Obtain the initial electrical parameters of the electrical signal; The initial electrical parameters are calibrated based on the temperature of the chip under test and the ambient temperature of the environment in which the chip under test is located, to obtain the electrical parameters.

8. A chip lifetime prediction device, characterized in that, include: The acquisition module acquires the electrical parameters of the electrical signal at the output terminal of the chip under test through the feedback detection circuit in the chip under test; The processing module determines the resistance parameters of the chip under test based on the electrical parameters obtained by the acquisition module; and predicts the remaining usage time of the chip under test based on the resistance parameters.

9. An electronic device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the method as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 7.

Images