Fault parameter prediction method and device and storage medium

Abstract

The invention relates to a fault parameter prediction method and device and a storage medium. The method comprises the following steps: acquiring historical fault parameters and first influence parameters of a plurality of different first devices; wherein the historical fault parameter is at least used for describing the probability of screen fragmentation of the first equipment; determining a second influence parameter according to the first influence parameter and the historical fault parameter; the second influence parameter comprises a key influence parameter causing screen fragmentation of the first equipment; constructing a fault prediction model based on the second influence parameter and the historical fault parameter of the first equipment; and obtaining a second influence parameter of the second equipment, and predicting a fault parameter of the second equipment by using the fault prediction model and the second influence parameter of the second equipment. The accuracy of the fault prediction model can be improved, the accuracy of predicting the screen fragmentation probability is further improved, the credibility of the prediction result is improved, and risk identification is more effectively carried out.

Description

Technical Field

[0001] The present disclosure relates to the technical field of electronic equipment, and in particular to a fault parameter prediction method, device and storage medium. Background Art

[0002] In the related art, the product fault feedback ratio (FFR) of electronic device screen breakage is used to measure the probability of screen breakage of electronic devices. When predicting the probability of screen breakage of electronic devices, historical data of electronic devices can be referred to. Relying on business experience, the key influencing factors that cause electronic device screen breakage are identified from historical data, and weights are assigned to each key influencing factor, and the probability of screen cover breakage is estimated through a simple formula. However, after experimental verification, the prediction results obtained by this prediction method have a very low accuracy and low credibility. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the present disclosure provides a fault parameter prediction method, device and storage medium.

[0004] According to a first aspect of an embodiment of the present disclosure, a fault parameter prediction method is provided, comprising:

[0005] Acquire historical fault parameters and first impact parameters of a plurality of different first devices; wherein the historical fault parameters are at least used to describe the probability of screen breakage of the first device;

[0006] Determining a second influencing parameter according to the first influencing parameter and the historical fault parameter; the second influencing parameter includes: a key influencing parameter causing the screen of the first device to be shattered;

[0007] Building a fault prediction model based on the second influencing parameter of the first device and the historical fault parameter;

[0008] A second influencing parameter of the second device is acquired, and a fault parameter of the second device is predicted using the fault prediction model and the second influencing parameter of the second device.

[0009] In some embodiments, determining the second influencing parameter according to the first influencing parameter and the historical fault parameter includes:

[0010] A correlation analysis is performed on the first influencing parameter and the historical fault parameter, and based on the correlation analysis result, the second influencing parameter is determined from a plurality of the first influencing parameters.

[0011] In some embodiments, the performing correlation analysis on the first influencing parameter and the historical fault parameter includes:

[0012] Based on the first influencing parameters and the historical fault parameters of the plurality of first devices, determining first information between each of the first influencing parameters and the historical fault parameters; the first information is used to describe the correlation between a change trend of the first influencing parameter and a change trend of the historical fault parameter;

[0013] Based on the first influencing parameters and the historical fault parameters of the first devices, determining second information between the first influencing parameters and the historical fault parameters; the second information is used to describe the amount of information of the historical fault parameters contained in the first influencing parameters;

[0014] Based on the first information and the second information, determining whether the plurality of first influencing parameters meet a preset modeling condition;

[0015] When the modeling condition is met, a correlation analysis is performed on the first influencing parameter and the historical fault parameter.

[0016] In some embodiments, the method further comprises:

[0017] If the modeling condition is not met, the plurality of first influencing parameters of the first device are reacquired.

[0018] In some embodiments, the determining, based on the first influencing parameters and the historical fault parameters of the plurality of first devices, the first information between each of the first influencing parameters and the historical fault parameters includes:

[0019] determining first sorting information of the plurality of first devices based on the same first influencing parameter of the plurality of first devices;

[0020] Determining second sorting information of the plurality of first devices based on historical fault parameters of the plurality of first devices;

[0021] According to the correlation between the first sorting information corresponding to each of the first influencing parameters among a plurality of the first influencing parameters and the second sorting information, the first information between each of the first influencing parameters and the historical fault information is determined respectively.

[0022] In some embodiments, determining second information between the plurality of first influencing parameters and the historical fault parameters based on the plurality of first influencing parameters and the historical fault parameters of the first devices includes:

[0023] Performing regression analysis on the first influencing parameters and the historical fault parameters of the plurality of first devices to obtain a regression model;

[0024] Based on the R-squared value corresponding to the regression model, the second information between the plurality of first influencing parameters and the historical fault parameters is determined.

[0025] In some embodiments, constructing a fault prediction model based on the second influencing parameter and the historical fault parameter of the first device includes:

[0026] constructing an initial prediction model based on the second influencing parameter and the historical fault parameter of a first target device; the first target device is any one of the plurality of first devices;

[0027] Using the second influencing parameters of the plurality of second target devices and the initial prediction model, respectively obtain the predicted fault parameters of the plurality of second target devices; wherein the second target device is any device among the plurality of first devices except the first target device;

[0028] Determining the accuracy of the initial prediction model based on a plurality of predicted failure parameters of the second target device and historical failure parameters of the second target device;

[0029] When the accuracy reaches a preset accuracy, the initial prediction model is determined as the fault prediction model.

[0030] In some embodiments, the second influencing parameters include: first-category parameters and second-category parameters; wherein the first-category parameters are used to describe the screen structure of the electronic device; and the second-category parameters are used to describe the single body strength of the screen of the electronic device;

[0031] The constructing a fault prediction model based on the second influencing parameter of the first device and the historical fault parameter includes:

[0032] A first prediction model is constructed based on the first-category parameters, the second-category parameters and the historical fault parameters of the first devices; the first prediction model is used to predict fault parameters of the second device in the design stage.

[0033] In some embodiments, the method further comprises:

[0034] If the fault parameter of the second device in the design stage is greater than a preset fault threshold, the first type parameters and the second type parameters of the second device are adjusted.

[0035] In some embodiments, the second influencing parameter includes: a first type parameter, a second type parameter and a third type parameter; wherein the third type parameter is used to describe the overall reliability of the electronic device;

[0036] The constructing a fault prediction model based on the second influencing parameter of the first device and the historical fault parameter includes:

[0037] A second prediction model is constructed based on the first-category parameters, the second-category parameters, the third-category parameters and the historical fault parameters of the first devices; the second prediction model is used to predict fault parameters of the second device in the production test stage.

[0038] In some embodiments, the method further comprises:

[0039] If the fault parameter of the second device in the production test phase is greater than a preset fault threshold, the third type of parameter of the second device is adjusted.

[0040] According to a second aspect of an embodiment of the present disclosure, a fault parameter prediction device is provided, comprising:

[0041] A first acquisition module is configured to acquire historical fault parameters and first influencing parameters of a plurality of different first devices; wherein the historical fault parameters are at least used to describe the probability of screen breakage of the first device;

[0042] A first determination module is configured to determine a second influencing parameter according to the first influencing parameter and the historical fault parameter; the second influencing parameter includes: a key influencing parameter causing the screen of the first device to be broken;

[0043] A construction module configured to construct a fault prediction model based on the second influencing parameter and the historical fault parameter of the first device;

[0044] The prediction module is configured to obtain a second influencing parameter of the second device, and predict a fault parameter of the second device by using the fault prediction model and the second influencing parameter of the second device.

[0045] In some embodiments, the first determining module is configured to:

[0046] A correlation analysis is performed on the first influencing parameter and the historical fault parameter, and based on the correlation analysis result, the second influencing parameter is determined from a plurality of the first influencing parameters.

[0047] In some embodiments, the first determining module is configured to:

[0048] Based on the first influencing parameters and the historical fault parameters of the plurality of first devices, determining first information between each of the first influencing parameters and the historical fault parameters; the first information is used to describe the correlation between a change trend of the first influencing parameter and a change trend of the historical fault parameter;

[0049] Based on the first influencing parameters and the historical fault parameters of the first devices, determining second information between the first influencing parameters and the historical fault parameters; the second information is used to describe the amount of information of the historical fault parameters contained in the first influencing parameters;

[0050] Based on the first information and the second information, determining whether the plurality of first influencing parameters meet a preset modeling condition;

[0051] When the modeling condition is met, a correlation analysis is performed on the first influencing parameter and the historical fault parameter.

[0052] In some embodiments, the apparatus further comprises:

[0053] The second acquisition module is configured to re-acquire the plurality of first influencing parameters of the first device if the modeling condition is not met.

[0054] In some embodiments, the first determining module is configured to:

[0055] determining first sorting information of the plurality of first devices based on the same first influencing parameter of the plurality of first devices;

[0056] Determining second sorting information of the plurality of first devices based on historical fault parameters of the plurality of first devices;

[0057] According to the correlation between the first sorting information corresponding to each of the first influencing parameters and the second sorting information, the first information between each of the first influencing parameters and the historical fault information is determined respectively.

[0058] In some embodiments, the first determining module is configured to:

[0059] Performing regression analysis on the first influencing parameters and the historical fault parameters of the plurality of first devices to obtain a regression model;

[0060] Based on the R-squared value corresponding to the regression model, the second information between the plurality of first influencing parameters and the historical fault parameters is determined.

[0061] In some embodiments, the building block is configured as follows:

[0062] constructing an initial prediction model based on the second influencing parameter and the historical fault parameter of a first target device; the first target device is any one of the plurality of first devices;

[0063] Using the second influencing parameters of the plurality of second target devices and the initial prediction model, respectively obtain the predicted fault parameters of the plurality of second target devices; wherein the second target device is any device among the plurality of first devices except the first target device;

[0064] Determining the accuracy of the initial prediction model based on a plurality of predicted failure parameters of the second target device and historical failure parameters of the second target device;

[0065] When the accuracy reaches a preset accuracy, the initial prediction model is determined as the fault prediction model.

[0066] In some embodiments, the second influencing parameters include: first-category parameters and second-category parameters; wherein the first-category parameters are used to describe the screen structure of the electronic device; and the second-category parameters are used to describe the single body strength of the screen of the electronic device;

[0067] The building blocks are configured as follows:

[0068] A first prediction model is constructed based on the first-category parameters, the second-category parameters and the historical fault parameters of the first devices; the first prediction model is used to predict fault parameters of the second device in the design stage.

[0069] In some embodiments, the apparatus further comprises:

[0070] The first adjustment module is configured to adjust the first type parameters and the second type parameters of the second device if the fault parameter of the second device in the design stage is greater than a preset fault threshold.

[0071] In some embodiments, the second influencing parameter includes: a first type parameter, a second type parameter and a third type parameter; wherein the third type parameter is used to describe the overall reliability of the electronic device;

[0072] The building blocks are configured as follows:

[0073] A second prediction model is constructed based on the first-category parameters, the second-category parameters, the third-category parameters and the historical fault parameters of the first devices; the second prediction model is used to predict fault parameters of the second device in the production test stage.

[0074] In some embodiments, the apparatus further comprises:

[0075] The second adjustment module is configured to adjust the third type of parameters of the second device if the fault parameter of the second device in the production test phase is greater than a preset fault threshold.

[0076] According to a third aspect of an embodiment of the present disclosure, a fault parameter prediction device is provided, comprising:

[0077] processor;

[0078] a memory configured to store processor-executable instructions;

[0079] Wherein, the processor is configured to: implement the steps in any one of the fault parameter prediction methods in the first aspect when executed.

[0080] According to a fourth aspect of an embodiment of the present disclosure, a non-temporary computer-readable storage medium is provided. When instructions in the storage medium are executed by a processor of a fault parameter prediction device, the device is enabled to perform the steps in any one of the fault parameter prediction methods in the first aspect above.

[0081] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:

[0082] In the disclosed embodiment, the second influencing parameter is determined based on the first influencing parameter and the historical fault parameter, and a fault prediction model is constructed based on the second influencing parameter and the historical fault parameter, and the fault prediction model can be used to predict the fault parameter of the second device. In this way, the fault prediction model is constructed based on the second influencing parameter determined by the first influencing parameter and the historical fault parameter, which can improve the accuracy of the fault prediction model, thereby improving the accuracy of the predicted screen breakage probability, increasing the credibility of the prediction result, and more effectively identifying risks.

[0083] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0085] Figure 1 is a schematic diagram of a fault parameter prediction method according to an exemplary embodiment. Figure 1 ;

[0086] Figure 2 is a schematic diagram showing the thermal bending depth of a cover plate according to an exemplary embodiment;

[0087] Figure 3 is a schematic diagram showing the size of the middle frame corner exceeding the edge of the cover plate according to an exemplary embodiment;

[0088] Figure 4 is a schematic diagram showing the dimensions of the middle frame extending beyond the edge of the cover plate in the left and right / up and down directions according to an exemplary embodiment;

[0089] Figure 5 is a schematic diagram of a fault parameter prediction method according to an exemplary embodiment. Figure 2 ;

[0090] Figure 6 is a block diagram of a fault parameter prediction device according to an exemplary embodiment;

[0091] Figure 7 is a block diagram of a fault parameter prediction device 800 according to an exemplary embodiment;

[0092] Figure 8 The figure is a hardware structure block diagram of a fault parameter prediction device according to an exemplary embodiment. DETAILED DESCRIPTION

[0093] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0094] The present disclosure provides a method for predicting fault parameters. Figure 1 is a schematic diagram of a fault parameter prediction method according to an exemplary embodiment. Figure 1 ,like Figure 1 The method is applied to electronic equipment and mainly includes the following steps:

[0095] In step 101, historical fault parameters and first influencing parameters of a plurality of different first devices are obtained; wherein the historical fault parameters are at least used to describe the probability of screen breakage of the first device;

[0096] In step 102, a second influencing parameter is determined according to the first influencing parameter and the historical fault parameter; the second influencing parameter includes: a key influencing parameter causing the screen of the first device to be broken;

[0097] In step 103, a fault prediction model is constructed based on the second influencing parameter and the historical fault parameter of the first device;

[0098] In step 104, a second influencing parameter of the second device is obtained, and a fault parameter of the second device is predicted using the fault prediction model and the second influencing parameter of the second device.

[0099] It should be noted that the fault parameter prediction method proposed in the present disclosure can be applied to electronic devices as well as servers. Here, electronic devices may include: terminal devices, for example, mobile terminals or fixed terminals. Among them, mobile terminals may include: mobile phones, tablet computers, laptop computers and other devices. Fixed terminals may include: desktop computers, smart TVs, etc. As a type of computer, a server can provide computing or application services for other clients (such as computers, smart phones, ATMs and other terminal devices, and even large devices such as train systems) in the network.

[0100] The fault parameter prediction method in the embodiment of the present disclosure may be configured in a fault parameter prediction device, and the fault parameter prediction device may be set in a server, or may also be set in an electronic device, which is not limited in the embodiment of the present disclosure.

[0101] It should be noted that the execution subject of the embodiment of the present disclosure may be, for example, a central processing unit (CPU) in a server or electronic device in terms of hardware, or may be, for example, a related background service in a server or electronic device in terms of software, without limitation.

[0102] In some embodiments, the first device may be a historical electronic device, and different first devices may be first devices of different models, wherein first devices of different models may include: first devices with different appearances, first devices with different covers, and first devices with different weights, etc. The historical failure parameter may be used to describe the probability of a screen being broken on the first device, the historical failure parameter may also be used to describe the probability of a black screen on the first device, and the historical failure parameter may also be used to describe the probability of a freeze on the first device.

[0103] The first influencing parameters may include: design parameters, screen cover parameters and whole machine reliability parameters, etc. Among them, the design parameters may include: the whole machine weight of the electronic device, the cover material and thickness of the electronic device, the thermal bending depth of the cover (the thermal bending depth of the straight screen cover is 0) and the size of the middle frame shape exceeding the edge of the cover, etc. It should be noted that when the electronic device to which the fault parameter prediction method is applied is a curved screen, the thermal bending depth of the cover may be included in the design parameters; when the electronic device to which the fault parameter prediction method is applied is a straight screen, the thermal bending depth of the cover may be excluded from the design parameters. Figure 2 is a schematic diagram of the thermal bending depth of a cover plate according to an exemplary embodiment. Figure 2 As shown, the thermal bending depth of the cover plate 201 is J.

[0104] The dimensions of the middle frame shape exceeding the edge of the cover plate may include: the dimensions of the middle frame corners exceeding the edge of the cover plate and the dimensions of the middle frame left and right / top and bottom exceeding the edge of the cover plate. Here, the structure of the middle frame shape exceeding the edge of the cover plate can be used to protect the cover plate and prevent the cover plate from being worn. Figure 3 is a schematic diagram showing the size of the middle frame corner exceeding the edge of the cover plate according to an exemplary embodiment. Figure 3 As shown, the middle frame 301 is fixedly connected to the cover plate 201 , and the dimension of the corner of the middle frame 301 beyond the edge of the cover plate 201 is W. Figure 4 is a schematic diagram showing the size of the middle frame extending beyond the edge of the cover plate in the left and right / up and down directions according to an exemplary embodiment. Figure 4 As shown, the left and right dimensions of the middle frame 301 that extend beyond the edge of the cover plate 201 are X, and the top and bottom dimensions of the middle frame 301 that extend beyond the edge of the cover plate 201 are Y.

[0105] The screen cover parameters may include: the central static pressure test (ROR) and four-point bending test (4PB) test values ​​that characterize the strength of the single unit; the whole machine reliability parameters may include: the whole machine directional drop test and roller drop test, etc.

[0106] In some embodiments, the second influencing parameter may be determined based on the first influencing parameter and the historical fault parameter. For example, the parameter value difference of the same first influencing parameter of any two first devices may be determined, and the parameter value difference of the historical fault parameters of the two first devices may be determined. If the parameter value difference of the first influencing parameter is close to the parameter value difference of the historical fault parameter, the first influencing parameter may be determined as the second influencing parameter.

[0107] For another example, the parameter value change rate of the same first influencing parameter of any two first devices can be determined, and the parameter value change rate of the historical fault parameters of the two first devices can be determined. When the parameter value change rate of the first influencing parameter is close to the parameter value change rate of the historical fault parameter, the first influencing parameter can be determined as the second influencing parameter.

[0108] In some embodiments, when the historical failure parameters are used to describe the probability of a screen shattering on the first device, the second influencing parameters may include key influencing parameters causing the screen shattering of the first device; when the historical failure parameters are used to describe the probability of a black screen on the first device, the second influencing parameters may include key influencing parameters causing the black screen on the first device; when the historical failure parameters are used to describe the probability of a freeze on the first device, the second influencing parameters may include key influencing parameters causing the freeze on the first device.

[0109] In some embodiments, when the second influencing parameter is determined, a fault prediction model can be constructed based on the second influencing parameter and the historical fault parameter of the first device. The fault prediction model and the acquired second influencing parameter of the second device can be used to predict the fault parameter of the second device. Here, the second device can be an electronic device that is different from any of the first devices. The second device can be a different model from any of the first devices.

[0110] In the disclosed embodiment, the second influencing parameter is determined based on the first influencing parameter and the historical fault parameter, and a fault prediction model is constructed based on the second influencing parameter and the historical fault parameter, and the fault prediction model can be used to predict the fault parameter of the second device. In this way, the fault prediction model is constructed based on the second influencing parameter determined by the first influencing parameter and the historical fault parameter, which can improve the accuracy of the fault prediction model, thereby improving the accuracy of the predicted screen breakage probability, increasing the credibility of the prediction result, and more effectively identifying risks.

[0111] In some embodiments, determining the second influencing parameter according to the first influencing parameter and the historical fault parameter includes:

[0112] A correlation analysis is performed on the first influencing parameter and the historical fault parameter, and based on the correlation analysis result, the second influencing parameter is determined from a plurality of the first influencing parameters.

[0113] In some embodiments, the correlation analysis may be performed by ranking the first influencing parameter and the historical fault parameter. In other embodiments, the correlation analysis may be performed by building a model based on the first influencing parameter and the historical fault parameter. In other embodiments, the correlation analysis may be performed by calculating the correlation coefficient between the first influencing parameter and the historical fault parameter.

[0114] Taking the multiple different first devices as multiple different models of first devices, and performing correlation analysis by calculating the correlation coefficient between the first influencing parameter and the historical fault parameter as an example, the historical fault parameters and the first influencing parameters of the multiple different models of first devices can be obtained, and the correlation coefficient between the first influencing parameter and the historical fault parameter can be calculated. From the multiple first influencing parameters, the first influencing parameter whose correlation coefficient meets the preset correlation coefficient can be determined as the second influencing parameter with a high correlation with the historical fault parameter.

[0115] In some embodiments, a first influencing parameter having a high correlation with the historical fault parameter (for example, a correlation coefficient reaches 0.5) or a significant correlation with the historical fault parameter (for example, a P value less than 0.05) can be screened out from the first influencing parameters and determined as the second influencing parameter.

[0116] In the disclosed embodiment, a correlation analysis is performed on the first influencing parameter and the historical fault parameter, and the second influencing parameter is determined from the first influencing parameter using the result of the correlation analysis. In this way, the fault prediction model is constructed using the second influencing parameter determined by the correlation analysis result, which can improve the accuracy of the fault prediction model and further improve the accuracy of the predicted screen breakage probability.

[0117] In some embodiments, the performing correlation analysis on the first influencing parameter and the historical fault parameter includes:

[0118] Based on the first influencing parameters and the historical fault parameters of the plurality of first devices, determining first information between each of the first influencing parameters and the historical fault parameters; the first information is used to describe the correlation between a change trend of the first influencing parameter and a change trend of the historical fault parameter;

[0119] Based on the first influencing parameters and the historical fault parameters of the first devices, determining second information between the first influencing parameters and the historical fault parameters; the second information is used to describe the amount of information of the historical fault parameters contained in the first influencing parameters;

[0120] Based on the first information and the second information, determining whether the plurality of first influencing parameters meet a preset modeling condition;

[0121] When the modeling condition is met, a correlation analysis is performed on the first influencing parameter and the historical fault parameter.

[0122] Here, before performing a correlation analysis on the first influencing parameter and the historical fault parameter, it can be determined whether the first influencing parameter and the historical fault parameter meet preset modeling conditions. If it is determined that the modeling conditions are met, a correlation analysis is performed on the first influencing parameter and the historical fault parameter.

[0123] In some embodiments, first information between each first influencing parameter and the historical fault parameter may be determined based on the first influencing parameters and the historical fault parameters of the plurality of first devices, and second information between the plurality of first influencing parameters and the historical fault parameters may be determined.

[0124] The first information may be used to describe the correlation between the change trend of the first influencing parameter and the change trend of the historical fault parameter; it should be noted that the first information can reflect the closeness of the connection between each first influencing parameter and the historical fault parameter.

[0125] For example, when the first information indicates that the correlation between the change trend of the first influencing parameter and the change trend of the historical fault parameter is high, when the first influencing parameter increases, the historical fault parameter also increases accordingly.

[0126] For another example, when the first information indicates that the correlation between the change trend of the first influencing parameter and the change trend of the historical fault parameter is low, when the first influencing parameter increases, the historical fault parameter remains unchanged or even decreases.

[0127] The second information can be used to describe the amount of information of the historical fault parameters jointly contained in the multiple first influencing parameters; it should be noted that the second information can reflect the degree of fit of the model constructed based on the multiple first influencing parameters and the historical fault parameters to the data.

[0128] For example, when the second information indicates that the plurality of first influencing parameters together contain a large amount of information about the historical fault parameters, the model constructed based on the plurality of first influencing parameters and the historical fault parameters has a high degree of fit to the data.

[0129] For another example, when the second information indicates that the amount of information of the historical fault parameters contained in the plurality of first influencing parameters is small, the degree of fit of the model constructed based on the plurality of first influencing parameters and the historical fault parameters to the data is low.

[0130] In some embodiments, the determined first information may be used as a result of correlation analysis to determine the second influencing parameter from the plurality of first influencing parameters.

[0131] In some embodiments, a table can be directly established based on the first influencing parameters and the historical fault parameters, and a calculation tool can be used to determine the first information between each first influencing parameter and the historical fault parameter. The calculation tool may include Excel software, and the first information may be a rank correlation coefficient; for example, the first information is a Spearman rank correlation coefficient, a Kendall rank correlation coefficient, etc.

[0132] In some embodiments, a regression model can be directly established using statistical software, and the second information between multiple first influencing parameters and historical fault parameters can be determined based on the output value of the model. The statistical software may include: R software, Python software, etc. The regression model may be a linear regression model, for example, the linear regression model may be a gamma regression model. The second information may be an R-squared value, which may be used to evaluate the amount of information contained in the multiple first influencing parameters including the historical fault parameters, and may also be understood as the R-squared value which may be used to indicate the degree of fit of the model to the data; the second information may also be the mean absolute percentage error, and the squared absolute percentage error may be used to evaluate the fitting effect of the model.

[0133] In some embodiments, when the correlation described by the first information satisfies a preset correlation and the amount of information described by the second information satisfies a preset amount of information, it can be determined that multiple first influencing parameters satisfy preset modeling conditions, and when it is determined that the modeling conditions are satisfied, a correlation analysis is performed on the first influencing parameters and the historical fault parameters.

[0134] It should be noted that the method of determining the first information and the second information, the calculation tools and statistical software used can be adaptively adjusted according to actual needs, and the preset correlation and the preset amount of information can also be adaptively adjusted according to actual needs.

[0135] In the embodiment of the present disclosure, by giving priority to determining whether the modeling conditions are met, the reliability of the data used for modeling can be guaranteed, and thus the reliability of the model can be guaranteed; and the problem of low model accuracy that occurs when modeling is performed by using the first influencing parameters and historical fault parameters that do not meet the modeling conditions without prior determination of whether the modeling conditions are met, and unnecessary cost consumption can be avoided.

[0136] In some embodiments, the method further comprises:

[0137] If the modeling condition is not met, the plurality of first influencing parameters of the first device are reacquired.

[0138] In some embodiments, when the relevance described by the first information is less than the preset relevance, and the amount of information described by the second information is less than the preset amount of information, it can be determined that the plurality of first influencing parameters do not meet the preset modeling conditions. In other embodiments, when the relevance described by the first information is less than the preset relevance, or the amount of information described by the second information is less than the preset amount of information, it can be determined that the plurality of first influencing parameters do not meet the preset modeling conditions.

[0139] When it is determined that multiple first influence parameters do not meet the preset modeling conditions, the multiple first influence parameters of the first device can be re-acquired based on the first information and the second information; the multiple first influence parameters of the first device can be re-acquired based on business experience; and the multiple first influence parameters of the first device can be re-acquired by combining the first information, the second information and business experience.

[0140] In the case of reacquiring multiple first influencing parameters of the first device, it is determined whether the reacquired multiple first influencing parameters meet the preset modeling conditions. In the case of determining that the reacquired multiple first influencing parameters do not meet the preset modeling conditions, the multiple first influencing parameters of the first device can be acquired again until it is determined that the multiple first influencing parameters meet the preset modeling conditions, that is, a correlation analysis is performed on the first influencing parameters that meet the preset modeling conditions and the historical fault parameters.

[0141] In the embodiment of the present disclosure, by reacquiring multiple first influencing parameters of the first device when the modeling conditions are not met, the modeling data, i.e., the first influencing parameters, can be adaptively adjusted in a timely manner. When the model is constructed based on the first influencing parameters that meet the preset modeling conditions, the reliability of the model can be guaranteed.

[0142] In some embodiments, the determining, based on the first influencing parameters and the historical fault parameters of the plurality of first devices, the first information between each of the first influencing parameters and the historical fault parameters includes:

[0143] determining first sorting information of the plurality of first devices based on the same first influencing parameter of the plurality of first devices;

[0144] Determining second sorting information of the plurality of first devices based on historical fault parameters of the plurality of first devices;

[0145] According to the correlation between the first sorting information corresponding to each of the first influencing parameters and the second sorting information, the first information between each of the first influencing parameters and the historical fault information is determined respectively.

[0146] Here, the ranking information may be the ranking information of the first device. For example, the ranking information may be: the sequence number of the first device in the ranking obtained by ranking the same first influencing parameter of multiple first devices. For another example, the ranking information may be: the sequence number of the first device in the ranking obtained by ranking the historical fault parameters of the first device.

[0147] In some embodiments, the same first influencing parameter of multiple first devices can be sorted from small to large to determine first sorting information of the multiple first devices; and the historical fault parameters of the multiple first devices can be sorted from small to large to determine second sorting information of the multiple first devices.

[0148] In other embodiments, the same first influencing parameter of multiple first devices may be sorted from large to small to determine first sorting information of the multiple first devices; and the historical fault parameters of the multiple first devices may be sorted from large to small to determine second sorting information of the multiple first devices.

[0149] Here, the sorting method can be adaptively adjusted according to actual needs. It should be noted that the method of sorting the same first influencing parameter of multiple first devices is consistent with the method of sorting the historical fault parameters of multiple first devices.

[0150] In some embodiments, the first information between each first influencing parameter and the historical fault information may be determined respectively according to the correlation between the first sorting information corresponding to each first influencing parameter among the plurality of first influencing parameters and the second sorting information.

[0151] In the disclosed embodiment, the first information between each first influencing parameter and the historical fault information is determined by sorting, so that the correlation between each first influencing parameter and the historical fault parameter can be determined conveniently and quickly based on each first influencing parameter and the historical fault parameter.

[0152] In some embodiments, the determining, based on the first influencing parameters and the historical fault parameters of the plurality of first devices, second information between the plurality of first influencing parameters and the historical fault parameters comprises:

[0153] Performing regression analysis on the first influencing parameters and the historical fault parameters of the plurality of first devices to obtain a regression model;

[0154] Based on the R-squared value corresponding to the regression model, the second information between the plurality of first influencing parameters and the historical fault parameters is determined.

[0155] Here, the regression model may be a linear regression model, for example, the linear regression model may be a gamma regression model. The second information may be an R-squared value, which may be used to evaluate the amount of information contained in the historical fault parameters by the plurality of first influencing parameters.

[0156] In some embodiments, statistical software can be directly used to perform regression analysis on the first influencing parameters and historical fault parameters of the plurality of first devices to obtain a regression model, and based on the R-square value output by the regression model, the second information between the plurality of first influencing parameters and the historical fault parameters can be determined. The statistical software may include: R software, Python software, etc.

[0157] In the disclosed embodiment, by establishing a regression model, the second information between the plurality of first influencing parameters and the historical fault parameters can be determined more conveniently and intuitively based on the R-square value corresponding to the regression model.

[0158] In some embodiments, constructing a fault prediction model based on the second influencing parameter and the historical fault parameter of the first device includes:

[0159] constructing an initial prediction model based on the second influencing parameter and the historical fault parameter of a first target device; the first target device is any one of the plurality of first devices;

[0160] Using the second influencing parameters of the plurality of second target devices and the initial prediction model, respectively obtain the predicted fault parameters of the plurality of second target devices; wherein the second target device is any device among the plurality of first devices except the first target device;

[0161] Determining the accuracy of the initial prediction model based on a plurality of predicted failure parameters of the second target device and historical failure parameters of the second target device;

[0162] When the accuracy reaches a preset accuracy, the initial prediction model is determined as the fault prediction model.

[0163] In some embodiments, the first target device may be any device among the plurality of first devices, and the second target device may be any device among the plurality of first devices except the first target device. In other embodiments, the first target device may also be any device among the plurality of first devices, and the second target device may be any device among the plurality of first devices except the plurality of first target devices. In other embodiments, the second target device may be any device among the plurality of first devices, and the first target device may include all devices among the plurality of first devices except the second target device.

[0164] In some embodiments, the machine learning library in Python software (e.g., statsmodels) can be used to implement the design of the initial prediction model based on the second influencing parameter and the historical fault parameter of the first target device. Here, the form of the model may include: linear model, generalized linear model, tree model, etc. During the implementation process, a suitable model can be selected according to the performance effect of the model (e.g., the accuracy of the model). When a suitable model is designed, the machine learning library in Python software (e.g., statsmodels) can be used to solve the undetermined parameters in the model to implement the construction of the initial prediction model.

[0165] When the accuracy of all first devices including the first target device and the second target device reaches the preset accuracy, the fault prediction model can be used to predict the fault parameters of the second device. At the same time, the fault parameter information of the second device after it is put on the market can be tracked to continuously verify and optimize the fault prediction model.

[0166] In some embodiments, a leave-one-out validation method can be adopted to use the parameters of the first device to verify the performance of the model. The leave-one-out validation can be: for a data set with N samples, only one sample is left as a validation set each time, and N-1 samples are left as a training set, until N steps or the required number of operations are reached. Here, for each second target device, the other first target devices except it are used as training sets to establish an initial prediction model, and the second influencing parameters and historical fault parameters of the second target model are input into the initial prediction model to obtain the predicted fault parameters of the second target model, and then the accuracy of the initial prediction model is determined.

[0167] In some embodiments, the accuracy rate may be determined by: determining the difference between the predicted fault parameter and the historical fault parameter based on the predicted fault parameter and the historical fault parameter, and determining the ratio between the absolute value of the difference and the historical fault parameter based on the absolute value of the difference and the historical fault parameter; and determining the accuracy rate of the initial prediction model based on the ratio. Here, the calculation formula for the accuracy rate may be: accuracy rate = 1 - | predicted fault parameter - historical fault parameter | / historical fault parameter. Among them, the historical fault parameter may be used to describe the probability of a screen shattering on the first device, and the predicted fault parameter may be used to describe the probability that a screen shattering may occur on the first device.

[0168] Here, the preset accuracy rate can be 80% or 75%. During use, the preset accuracy rate, the method for determining the preset accuracy rate, the method for verifying the model, and the method for establishing the model can be adaptively adjusted according to actual conditions.

[0169] In some embodiments, when the accuracy of the model does not reach the preset accuracy, other forms of models can be selected to reconstruct the initial prediction model based on the second influencing parameter and historical failure parameters of the first target device, until the accuracy of the model reaches the preset accuracy, the initial prediction model can be determined as a fault prediction model.

[0170] In the disclosed embodiment, the model is constructed and verified based on the parameters of the first device, so that the processes of model construction and verification can be guaranteed to have data support, thereby ensuring the accuracy of the model.

[0171] In some embodiments, the second influencing parameters include: first-category parameters and second-category parameters; wherein the first-category parameters are used to describe the screen structure of the electronic device; and the second-category parameters are used to describe the single body strength of the screen of the electronic device;

[0172] The constructing a fault prediction model based on the second influencing parameter of the first device and the historical fault parameter includes:

[0173] A first prediction model is constructed based on the first-category parameters, the second-category parameters and the historical fault parameters of the first devices; the first prediction model is used to predict fault parameters of the second device in the design stage.

[0174] Here, when the electronic device is in the design stage, the second influencing parameters of the electronic device may include first-category parameters and second-category parameters, wherein the first-category parameters may be used to describe the screen structure of the electronic device, and the second-category parameters may be used to describe the screen unit strength of the electronic device.

[0175] In some embodiments, for an electronic device in the design stage, a first prediction model can be constructed based on the first type of parameters, the second type of parameters and historical failure parameters of the first device, and the first prediction model can be used to predict the failure parameters of a second device in the design stage.

[0176] In the disclosed embodiment, by constructing a first prediction model, fault parameter prediction can be performed on a second device that is in the design stage, and fault parameter prediction can be accurately performed on second devices with different design parameters such as different screen structures and screen unit strengths, thereby facilitating identification of the risk of screen shattering in different devices.

[0177] In some embodiments, the method further comprises:

[0178] If the fault parameter of the second device in the design stage is greater than a preset fault threshold, the first type parameters and the second type parameters of the second device are adjusted.

[0179] In some embodiments, when it is determined that the fault parameter of the second device in the design stage is greater than a preset fault threshold, the first type of parameters and / or the second type of parameters of the second device may be adaptively adjusted based on the predicted fault parameter.

[0180] In the disclosed embodiment, the design parameters of the second device in the design stage are adjusted based on the fault parameters predicted by the first prediction model, so that the design parameters can be corrected in time and the improvement of the second device in the design stage can be promoted.

[0181] In some embodiments, the second influencing parameter includes: a first type parameter, a second type parameter and a third type parameter; wherein the third type parameter is used to describe the overall reliability of the electronic device;

[0182] The constructing a fault prediction model based on the second influencing parameter of the first device and the historical fault parameter includes:

[0183] A second prediction model is constructed based on the first-category parameters, the second-category parameters, the third-category parameters and the historical fault parameters of the first devices; the second prediction model is used to predict fault parameters of the second device in the production test stage.

[0184] Here, when the electronic device is in the production test stage, the second influencing parameters of the electronic device may include first-category parameters, second-category parameters, and third-category parameters. Among them, the first-category parameters can be used to describe the screen structure of the electronic device, the second-category parameters can be used to describe the screen unit strength of the electronic device, and the third-category parameters are used to describe the overall reliability of the electronic device.

[0185] In some embodiments, for electronic devices in the production test stage, a second prediction model can be constructed based on the first type parameters, second type parameters, third type parameters and historical failure parameters of the first device, and the second prediction model can be used to predict the failure parameters of the second device in the production test stage.

[0186] In the disclosed embodiment, by constructing a second prediction model, the fault parameters of the second device in the production test stage can be accurately predicted, which is beneficial for risk assessment and balancing the relationship between quality, competitiveness and cost.

[0187] In some embodiments, the method further comprises:

[0188] If the fault parameter of the second device in the production test phase is greater than a preset fault threshold, the third type of parameter of the second device is adjusted.

[0189] In some embodiments, when it is determined that the fault parameter of the second device in the production test phase is greater than a preset fault threshold, the third type of parameter of the second device may be adaptively adjusted based on the predicted fault parameter.

[0190] In the disclosed embodiment, the production test parameters of the second device in the production test stage are adjusted based on the fault parameters predicted by the second prediction model, so as to better formulate the production test parameters, control the cost of the second device, and ensure the quality and competitiveness of the second device.

[0191] Figure 5 is a schematic diagram of a fault parameter prediction method according to an exemplary embodiment. Figure 2 ,like Figure 5 As shown, the method mainly includes the following steps:

[0192] In step 501, historical data is collected and acquired.

[0193] Here, the historical data may include historical fault parameters and first influencing parameters of multiple different first devices. The sample size of the historical data may be more than 30 and needs to be greater than the number of first influencing parameters. It should be noted that if the sample size of the historical data is less than 10, the modeling conditions may not be met.

[0194] In step 502, feasibility analysis is performed.

[0195] Here, the feasibility analysis may include: determining the first information between each first influencing parameter and the historical fault parameter based on the first influencing parameters and historical fault parameters of multiple first devices; and determining the second information between multiple first influencing parameters and the historical fault parameters; wherein the first information is used to describe the correlation between the changing trend of the first influencing parameter and the changing trend of the historical fault parameter; and the second information is used to describe the amount of information of the historical fault parameter jointly contained in multiple first influencing parameters.

[0196] In some embodiments, a regression model may be directly established using statistical software, and the second information between the plurality of first influencing parameters and the historical fault parameters may be determined based on the output values ​​of the model.

[0197] For example, taking the regression model as a gamma regression model, the historical fault parameters may include historical activation values ​​and historical fault values. A gamma regression model is established using a statistical model, wherein the independent variables of the gamma regression model may include: historical activation values ​​and first influencing parameters, and the dependent variables of the gamma regression model may include: historical fault values ​​as dependent variables. The R-squared value output by the gamma regression model is obtained, and based on the R-squared value, the second information between the multiple first influencing parameters and the historical fault parameters can be determined.

[0198] In step 503, it is determined whether the historical data is feasible for modeling.

[0199] Here, the relevance described by the first information may be compared with a preset relevance, and the amount of information described by the second information may be compared with a preset amount of information to determine whether the historical data is feasible for modeling.

[0200] In some embodiments, when the relevance of the first information description is less than the preset relevance, and the amount of information described by the second information is less than the preset amount of information, it can be determined that the multiple first influencing parameters do not meet the preset modeling conditions. In other embodiments, when the relevance of the first information description is less than the preset relevance, or the amount of information described by the second information is less than the preset amount of information, it can be determined that the multiple first influencing parameters do not meet the preset modeling conditions.

[0201] When it is determined that the plurality of first influencing parameters do not satisfy the preset modeling condition, the plurality of first influencing parameters of the first device may be reacquired based on the first information and the second information.

[0202] In step 504, a correlation analysis is performed on the first influencing parameter and the historical fault parameter, and based on the correlation analysis result, a second influencing parameter is determined from the plurality of first influencing parameters.

[0203] In some embodiments, when the relevance of the first information description satisfies the preset relevance and the amount of information described by the second information satisfies the preset amount of information, it can be determined that the plurality of first influencing parameters satisfy the preset modeling conditions. When it is determined that the modeling conditions are satisfied, a correlation analysis is performed on the first influencing parameters and the historical fault parameters.

[0204] For example, taking the first information as the Spearman rank correlation coefficient, when the Spearman rank correlation coefficient between most of the first influencing parameters and the historical fault parameters reaches 0.5, and the Spearman rank correlation coefficient between some of the first influencing parameters and the historical fault parameters reaches 0.7, it can be determined that the correlation described by the first information meets the preset correlation. Among them, most of the first influencing parameters can be 50% of the first influencing parameters, and some of the first influencing parameters can be 20% of the first influencing parameters. In addition, the value range of the correlation coefficient is between 0 and 1. The closer the correlation coefficient is to 1, the higher the correlation between the first influencing parameter and the historical fault parameter.

[0205] For another example, taking the second information as an R-squared value, when the R-squared value reaches 0.5, it can be determined that the amount of information described by the second information meets the preset amount of information. The value range of the R-squared value is between 0 and 1, and the larger the value of the R-squared value, the more information the multiple first influencing parameters jointly contain about the historical fault parameters.

[0206] It should be noted that the number of most of the first influencing parameters and some of the first influencing parameters in the above embodiments is variable; the value that the R-squared value needs to reach is also variable.

[0207] Based on the result of the correlation analysis, the first influencing parameter having a high correlation with the historical fault parameter is determined as the second influencing parameter.

[0208] In step 505, model prototyping is performed.

[0209] Here, the design of the initial prediction model can be implemented based on the second influencing parameter and the historical fault parameter of the first target device. The form of the model may include: linear model, generalized linear model, tree model, etc. In the implementation process, a suitable model can be selected according to the performance effect of the model (for example, the accuracy of the model).

[0210] In step 506, a model solving algorithm is designed.

[0211] Here, when a suitable model is designed, the undetermined parameters in the model can be solved to realize the construction of the initial prediction model.

[0212] In step 507, the model is validated.

[0213] Here, verification methods including leave-one-out verification can be adopted to determine the accuracy of the model and realize model verification.

[0214] In step 508, it is determined whether the performance effect of the model meets expectations.

[0215] Here, the performance effect of the model may include the accuracy of the model, and whether the performance effect of the model meets expectations can be judged based on whether the accuracy of the model reaches a preset accuracy.

[0216] In some embodiments, when the accuracy of the model does not reach the preset accuracy, other forms of models can be selected to reconstruct the initial prediction model based on the second influencing parameter and historical failure parameters of the first target device, until the accuracy of the model reaches the preset accuracy, the initial prediction model can be determined as a fault prediction model.

[0217] In step 509, the model is engineered.

[0218] In some embodiments, when the accuracy of all first devices including the first target device and the second target device reaches the preset accuracy, the initial prediction model is determined as the fault prediction model to complete the model engineering development. In this way, the fault prediction model can be used to predict the fault parameters of the second device, and at the same time, the fault parameter information of the second device after it is put on the market can be tracked to continuously verify and optimize the fault prediction model.

[0219] In step 510, the product is produced into a model product.

[0220] Here, the input interface of the model can be designed, and the predicted results can be presented through the interface.

[0221] The process of the above-mentioned fault parameter prediction method may include three stages. The first stage may be the pre-modeling analysis stage, including steps 501 to 504; the second stage may be the modeling and algorithm design stage, including steps 505 to 508; the third stage may be the productization implementation stage, including steps 509-510.

[0222] In the disclosed embodiment, historical data including historical fault parameters and first influencing parameters of multiple different first devices are used as references, and a feasibility analysis is performed by conducting in-depth learning of the historical data, evaluating the correlation between the changing trend of the first influencing parameter and the changing trend of the historical fault parameter, and the amount of information of the historical fault parameter contained in multiple first influencing parameters. Then, when the historical data has the feasibility of modeling, a correlation analysis is performed on the first influencing parameter and the historical fault parameter, and the second influencing parameter is determined from the multiple first influencing parameters. A fault prediction model is constructed based on the second influencing parameter and the historical fault parameter, and the model is verified. In this way, the fault parameters of the second device can be predicted based on the fault prediction model, which can improve the accuracy of the fault prediction model, thereby improving the accuracy of the predicted screen shattering probability, increasing the credibility of the prediction results, and more effectively identifying risks.

[0223] Figure 6 FIG. 1 is a block diagram of a fault parameter prediction device according to an exemplary embodiment. Figure 6 As shown, the fault parameter prediction device 600 mainly includes:

[0224] A first acquisition module 601 is configured to acquire historical fault parameters and first influencing parameters of a plurality of different first devices; wherein the historical fault parameters are at least used to describe the probability of screen breakage of the first device;

[0225] A first determining module 602 is configured to determine a second influencing parameter according to the first influencing parameter and the historical fault parameter; the second influencing parameter includes: a key influencing parameter causing the screen of the first device to be broken;

[0226] A construction module 603 is configured to construct a fault prediction model based on the second influencing parameter and the historical fault parameter of the first device;

[0227] The prediction module 604 is configured to obtain a second influencing parameter of the second device, and predict a fault parameter of the second device by using the fault prediction model and the second influencing parameter of the second device.

[0228] In some embodiments, the first determining module 602 is configured to:

[0229] A correlation analysis is performed on the first influencing parameter and the historical fault parameter, and based on the correlation analysis result, the second influencing parameter is determined from a plurality of the first influencing parameters.

[0230] In some embodiments, the first determining module 602 is configured to:

[0231] Based on the first influencing parameters and the historical fault parameters of the plurality of first devices, determining first information between each of the first influencing parameters and the historical fault parameters; the first information is used to describe the correlation between a change trend of the first influencing parameter and a change trend of the historical fault parameter;

[0232] Based on the first influencing parameters and the historical fault parameters of the first devices, determining second information between the first influencing parameters and the historical fault parameters; the second information is used to describe the amount of information of the historical fault parameters contained in the first influencing parameters;

[0233] Based on the first information and the second information, determining whether the plurality of first influencing parameters meet a preset modeling condition;

[0234] When the modeling condition is met, a correlation analysis is performed on the first influencing parameter and the historical fault parameter.

[0235] In some embodiments, the apparatus further comprises:

[0236] The second acquisition module is configured to re-acquire the plurality of first influencing parameters of the first device if the modeling condition is not met.

[0237] In some embodiments, the first determining module 602 is configured to:

[0238] determining first sorting information of the plurality of first devices based on the same first influencing parameter of the plurality of first devices;

[0239] Determining second sorting information of the plurality of first devices based on historical fault parameters of the plurality of first devices;

[0240] According to the correlation between the first sorting information corresponding to each of the first influencing parameters and the second sorting information, the first information between each of the first influencing parameters and the historical fault information is determined respectively.

[0241] In some embodiments, the first determining module 602 is configured to:

[0242] Performing regression analysis on the first influencing parameters and the historical fault parameters of the plurality of first devices to obtain a regression model;

[0243] Based on the R-squared value corresponding to the regression model, the second information between the plurality of first influencing parameters and the historical fault parameters is determined.

[0244] In some embodiments, the construction module 603 is configured to:

[0245] constructing an initial prediction model based on the second influencing parameter and the historical fault parameter of a first target device; the first target device is any one of the plurality of first devices;

[0246] Using the second influencing parameters of the plurality of second target devices and the initial prediction model, respectively obtain the predicted fault parameters of the plurality of second target devices; wherein the second target device is any device among the plurality of first devices except the first target device;

[0247] Determining the accuracy of the initial prediction model based on a plurality of predicted failure parameters of the second target device and historical failure parameters of the second target device;

[0248] When the accuracy reaches a preset accuracy, the initial prediction model is determined as the fault prediction model.

[0249] In some embodiments, the second influencing parameters include: first-category parameters and second-category parameters; wherein the first-category parameters are used to describe the screen structure of the electronic device; and the second-category parameters are used to describe the single body strength of the screen of the electronic device;

[0250] The construction module 603 is configured as follows:

[0251] A first prediction model is constructed based on the first-category parameters, the second-category parameters and the historical fault parameters of the first devices; the first prediction model is used to predict fault parameters of the second device in the design stage.

[0252] In some embodiments, the apparatus further comprises:

[0253] The first adjustment module is configured to adjust the first type parameters and the second type parameters of the second device if the fault parameter of the second device in the design stage is greater than a preset fault threshold.

[0254] In some embodiments, the second influencing parameter includes: a first type parameter, a second type parameter and a third type parameter; wherein the third type parameter is used to describe the overall reliability of the electronic device;

[0255] The construction module 603 is configured as follows:

[0256] A second prediction model is constructed based on the first-category parameters, the second-category parameters, the third-category parameters and the historical fault parameters of the first devices; the second prediction model is used to predict fault parameters of the second device in the production test stage.

[0257] In some embodiments, the apparatus further comprises:

[0258] The second adjustment module is configured to adjust the third type of parameters of the second device if the fault parameter of the second device in the production test phase is greater than a preset fault threshold.

[0259] Figure 7 is a block diagram of a fault parameter prediction device 800 according to an exemplary embodiment. For example, the device 800 may be a mobile phone, a mobile computer, etc.

[0260] Reference Figure 7 , the device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0261] The processing component 802 generally controls the overall operation of the device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0262] The memory 804 is configured to store various types of data to support operations on the device 800. Examples of such data include instructions for any application or method operating on the device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0263] The power supply component 806 provides power to the various components of the device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 800.

[0264] The multimedia component 808 includes a screen that provides an output interface between the device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0265] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the device 800 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0266] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0267] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the device 800. For example, the sensor assembly 814 can detect the open / closed state of the device 800, the relative positioning of components, such as the display and keypad of the device 800, the sensor assembly 814 can also detect the position change of the device 800 or a component of the device 800, the presence or absence of user contact with the device 800, the orientation or acceleration / deceleration of the device 800 and the temperature change of the device 800. The sensor assembly 814 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 can also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 can also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor or a temperature sensor.

[0268] The communication component 816 is configured to facilitate wired or wireless communication between the device 800 and other devices. The device 800 can access a wireless network based on a communication standard, such as Wi-Fi, 4G or 5G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0269] In an exemplary embodiment, the apparatus 800 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0270] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the instructions can be executed by the processor 820 of the device 800 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0271] A non-transitory computer-readable storage medium, when instructions in the storage medium are executed by a processor of a fault parameter prediction device, enables the fault parameter prediction device to perform a fault parameter prediction method, the method comprising:

[0272] Acquire historical fault parameters and first impact parameters of a plurality of different first devices; wherein the historical fault parameters are at least used to describe the probability of screen breakage of the first device;

[0273] Performing a correlation analysis on the first influencing parameter and the historical fault parameter, and determining a second influencing parameter from a plurality of the first influencing parameters based on the correlation analysis result; the second influencing parameter includes: a key influencing parameter causing the screen of the first device to be shattered;

[0274] Building a fault prediction model based on the second influencing parameter of the first device and the historical fault parameter;

[0275] A second influencing parameter of the second device is acquired, and a fault parameter of the second device is predicted using the fault prediction model and the second influencing parameter of the second device.

[0276] Figure 8 1 is a hardware structure block diagram of a fault parameter prediction device according to an exemplary embodiment. For example, the electronic device 1900 may be provided as a server. Figure 8 The electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform a fault parameter prediction method, including:

[0277] Acquire historical fault parameters and first impact parameters of a plurality of different first devices; wherein the historical fault parameters are at least used to describe the probability of screen breakage of the first device;

[0278] Performing a correlation analysis on the first influencing parameter and the historical fault parameter, and determining a second influencing parameter from a plurality of the first influencing parameters based on the correlation analysis result; the second influencing parameter includes: a key influencing parameter causing the screen of the first device to be shattered;

[0279] Building a fault prediction model based on the second influencing parameter of the first device and the historical fault parameter;

[0280] A second influencing parameter of the second device is acquired, and a fault parameter of the second device is predicted using the fault prediction model and the second influencing parameter of the second device.

[0281] The electronic device 1900 may also include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output (I / O) interface 1958. The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™ or the like.

[0282] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present disclosure. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in the various embodiments of the present disclosure, the size of the serial number of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure. The serial numbers of the embodiments of the present disclosure are for description only and do not represent the advantages and disadvantages of the embodiments.

[0283] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0284] In the several embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0285] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0286] In addition, all functional units in the embodiments of the present disclosure may be integrated into one processing unit, or each unit may be separately configured as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0287] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0288] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A fault parameter prediction method, applied to electronic equipment, It is characterized in that The method comprises: Acquire historical fault parameters and first impact parameters of a plurality of different first devices; wherein the historical fault parameters are at least used to describe the probability of screen breakage of the first device; Determining a second influencing parameter according to the first influencing parameter and the historical fault parameter; the second influencing parameter includes: a key influencing parameter causing the screen of the first device to be shattered; Building a fault prediction model based on the second influencing parameter of the first device and the historical fault parameter; A second influencing parameter of the second device is acquired, and a fault parameter of the second device is predicted using the fault prediction model and the second influencing parameter of the second device.

2. The method according to claim 1, It is characterized in that The determining of the second influencing parameter according to the first influencing parameter and the historical fault parameter includes: A correlation analysis is performed on the first influencing parameter and the historical fault parameter, and based on the correlation analysis result, the second influencing parameter is determined from a plurality of the first influencing parameters.

3. The method according to claim 2, It is characterized in that The performing correlation analysis on the first influencing parameter and the historical fault parameter includes: Based on the first influencing parameters and the historical fault parameters of the plurality of first devices, determining first information between each of the first influencing parameters and the historical fault parameters; the first information is used to describe the correlation between a change trend of the first influencing parameter and a change trend of the historical fault parameter; Based on the first influencing parameters and the historical fault parameters of the first devices, determining second information between the first influencing parameters and the historical fault parameters; the second information is used to describe the amount of information of the historical fault parameters contained in the first influencing parameters; Based on the first information and the second information, determining whether the plurality of first influencing parameters meet a preset modeling condition; When the modeling condition is met, a correlation analysis is performed on the first influencing parameter and the historical fault parameter.

4. The method according to claim 3, It is characterized in that The method further comprises: If the modeling condition is not met, the plurality of first influencing parameters of the first device are reacquired.

5. The method according to claim 3, It is characterized in that The determining, based on the first influencing parameters and the historical fault parameters of the plurality of first devices, first information between each of the first influencing parameters and the historical fault parameters includes: determining first sorting information of the plurality of first devices based on the same first influencing parameter of the plurality of first devices; Determining second sorting information of the plurality of first devices based on historical fault parameters of the plurality of first devices; According to the correlation between the first sorting information corresponding to each of the first influencing parameters and the second sorting information, the first information between each of the first influencing parameters and the historical fault information is determined respectively.

6. The method according to claim 3, It is characterized in that The determining, based on the first influencing parameters and the historical fault parameters of the plurality of first devices, second information between the plurality of first influencing parameters and the historical fault parameters comprises: Performing regression analysis on the first influencing parameters and the historical fault parameters of the plurality of first devices to obtain a regression model; Based on the R-squared value corresponding to the regression model, the second information between the plurality of first influencing parameters and the historical fault parameters is determined.

7. The method according to claim 1, It is characterized in that The constructing a fault prediction model based on the second influencing parameter of the first device and the historical fault parameter includes: constructing an initial prediction model based on the second influencing parameter and the historical fault parameter of a first target device; the first target device is any one of the plurality of first devices; Using the second influencing parameters of the plurality of second target devices and the initial prediction model, respectively obtain the predicted fault parameters of the plurality of second target devices; wherein the second target device is any device among the plurality of first devices except the first target device; Determining the accuracy of the initial prediction model based on a plurality of predicted failure parameters of the second target device and historical failure parameters of the second target device; When the accuracy reaches a preset accuracy, the initial prediction model is determined as the fault prediction model.

8. The method according to claim 1, It is characterized in that The second influencing parameters include: first-category parameters and second-category parameters; wherein the first-category parameters are used to describe the screen structure of the electronic device; and the second-category parameters are used to describe the single body strength of the screen of the electronic device; The constructing a fault prediction model based on the second influencing parameter of the first device and the historical fault parameter includes: A first prediction model is constructed based on the first-category parameters, the second-category parameters and the historical fault parameters of the first devices; the first prediction model is used to predict fault parameters of the second device in the design stage.

9. The method according to claim 8, It is characterized in that The method further comprises: If the fault parameter of the second device in the design stage is greater than a preset fault threshold, the first type parameters and the second type parameters of the second device are adjusted.

10. The method according to claim 1, It is characterized in that The second influencing parameters include: first-category parameters, second-category parameters and third-category parameters; wherein the third-category parameters are used to describe the overall reliability of the electronic device; The constructing a fault prediction model based on the second influencing parameter of the first device and the historical fault parameter includes: A second prediction model is constructed based on the first-category parameters, the second-category parameters, the third-category parameters and the historical fault parameters of the first devices; the second prediction model is used to predict fault parameters of the second device in the production test stage.

11. The method according to claim 10, It is characterized in that The method further comprises: If the fault parameter of the second device in the production test phase is greater than a preset fault threshold, the third type of parameter of the second device is adjusted.

12. A fault parameter prediction device, applied to electronic equipment, It is characterized in that The device comprises: A first acquisition module is configured to acquire historical fault parameters and first influencing parameters of a plurality of different first devices; wherein the historical fault parameters are at least used to describe the probability of screen breakage of the first device; A first determination module is configured to determine a second influencing parameter according to the first influencing parameter and the historical fault parameter; the second influencing parameter includes: a key influencing parameter causing the screen of the first device to be broken; A construction module, configured to construct a fault prediction model based on the second influencing parameter and the historical fault parameter of the first device; The prediction module is configured to obtain a second influencing parameter of the second device, and predict a fault parameter of the second device by using the fault prediction model and the second influencing parameter of the second device.

13. A fault parameter prediction device, It is characterized in that include: processor; a memory for storing processor-executable instructions; The processor is configured to: implement the steps in any one of the fault parameter prediction methods of claims 1 to 11 when executed.

14. A non-transitory computer-readable storage medium, It is characterized in that When the instructions in the storage medium are executed by the processor of the fault parameter prediction device, the device is enabled to execute the steps in any one of the fault parameter prediction methods of claims 1 to 11.

Images