Information processing method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention discloses an information processing method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring first time sequence data sets corresponding to a plurality of first terminal devices respectively; acquiring a second time sequence data set of a second terminal device; for each first terminal device in the plurality of first terminal devices, the following steps are executed: the similarity between the first time sequence data and the second time sequence data corresponding to each index is calculated, and the target similarity corresponding to each index is obtained; constructing a covariable set according to the target similarity corresponding to each index; inputting a plurality of covariable sets corresponding to the plurality of first terminals into a Cox model; and calculating an influence coefficient of the target similarity corresponding to each index on the operation life of the terminal equipment through a Cox model according to the multiple covariable sets, so as to predict the operation life of the first terminal equipment according to the influence coefficient. According to the embodiment of the invention, fault prediction can be accurately carried out on the equipment.

Description

Technical Field

[0001] The present application belongs to the field of data processing technology, and in particular, relates to an information processing method, device, equipment, storage medium and program product. Background Art

[0002] With the rise of smart homes, intelligence has begun to enter the hotel field. More and more consumers want to enjoy an intelligent accommodation experience in hotels, and in order to attract a new generation of consumers, hotels have also added intelligent elements to guest rooms. The so-called "smart hotel" refers to relying on new technologies such as cloud computing, the Internet of Things and mobile information, using smart terminal devices as carriers, and realizing personalized, humanized services and efficient management of hotels through digitalization, intelligence and networking of operations, management and services.

[0003] As a carrier of intelligence, the normal use of smart terminal devices is crucial to the user experience. Therefore, it is necessary to analyze the faults of smart terminal devices so as to maintain or replace them before problems occur, thus improving the user experience.

[0004] Current fault analysis generally infers the current health status of terminal equipment based on sensor data through the remaining useful life (RUL) model. However, the degradation process of equipment is often nonlinear and affected by multiple factors, including environmental conditions, operating loads, maintenance history, etc. The interaction between these factors increases the complexity of model establishment and may lead to deviations in prediction results, resulting in inaccurate prediction results. Summary of the invention

[0005] The embodiments of the present application provide an information processing method, apparatus, device, computer storage medium, and computer program product, which can accurately predict faults of equipment.

[0006] In a first aspect, an embodiment of the present application provides an information processing method, including:

[0007] Acquire a first time series data set corresponding to each of the plurality of first terminal devices, the first time series data set including first time series data corresponding to each of the plurality of indicators of the first terminal device in the first time period, the first time series data including a plurality of first moments in the first time period and indicator data of the first terminal at the first moment;

[0008] Acquire a second time series data set of the second terminal device, the second time series data set including second time series data corresponding to each of multiple indicators of the second terminal device in a second time period, wherein the second terminal device is a faulty device, the second time period is a time period in the life cycle of the second terminal device corresponding to the first time period, and the second time series data includes multiple second moments in the second time period and indicator data of the second terminal at the second moment;

[0009] For each of the multiple first terminal devices, the following steps are respectively performed: respectively calculating the similarity between the first time series data and the second time series data corresponding to each indicator to obtain the target similarity corresponding to each indicator; constructing a covariate set with the target similarity corresponding to each indicator;

[0010] Inputting a plurality of covariate sets corresponding to the plurality of first terminals into a proportional hazards regression Cox model;

[0011] The Cox model is used to calculate the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal device according to multiple covariate sets, so as to predict the operating life of the first terminal device according to the influence coefficient.

[0012] In an optional implementation, the similarity between the first time series data and the second time series data corresponding to each indicator is calculated respectively to obtain the target similarity corresponding to each indicator, including performing the following steps for the first time series data and the second time series data corresponding to each indicator respectively to obtain the target similarity corresponding to each indicator:

[0013] According to a preset segmentation rule, the first time period is divided into a plurality of first sub-time periods;

[0014] Extracting first time series sub-data corresponding to each of the plurality of first sub-periods from the first time series data;

[0015] Calculate the first average value of the indicator data in each first sub-period according to the first time series sub-data corresponding to each of the plurality of first sub-periods to obtain a first indicator data sequence;

[0016] According to a preset segmentation rule, the second time period is divided into a plurality of second sub-time periods;

[0017] Extracting second time series sub-data corresponding to each of the plurality of second sub-periods from the second time series data;

[0018] Calculate the second average value of the indicator data in each second sub-period according to the second time series sub-data corresponding to each of the plurality of second sub-periods to obtain a second indicator data sequence;

[0019] The dynamic time warping (DTW) similarity between the first indicator data sequence and the second indicator data sequence is calculated as the target similarity corresponding to the indicator.

[0020] In an optional implementation, calculating the dynamic time warping (DTW) similarity between the first indicator data sequence and the second indicator data sequence includes:

[0021] For each first average value in the first indicator data series, respectively calculate the cumulative distance between the first average value and each second average value;

[0022] Arrange the cumulative distances between each first average value and each second average value in a predetermined order to create a matrix grid;

[0023] Determine a target path from a preset grid start point to a preset grid end point in the matrix grid, the target path being the shortest path from a preset grid start point to a preset grid end point in the matrix grid;

[0024] The ratio of the number of cumulative distances in the matrix grid to the number of cumulative distances in the shortest path is calculated to obtain the DTW similarity between the first indicator data sequence and the second indicator data sequence.

[0025] In an optional implementation, the Cox model is used to calculate the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal device according to multiple covariate sets, including:

[0026] Substitute the covariate set into the logarithmic partial likelihood function formula preset in the Cox model to obtain the target logarithmic partial likelihood function formula, which is used to express the corresponding relationship between the logarithmic partial likelihood function and the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal equipment;

[0027] Based on the target logarithmic partial likelihood function formula, the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal equipment is calculated when the logarithmic partial likelihood function is the maximum partial likelihood function.

[0028] In an optional implementation, the multiple indicators include basic information of the terminal device and operating data of the terminal device.

[0029] In a second aspect, the present application provides an information processing device, including:

[0030] An acquisition module, configured to acquire first time series data sets corresponding to each of a plurality of first terminal devices, wherein the first time series data sets include first time series data corresponding to each of a plurality of indicators of the first terminal device in a first time period, and the first time series data include a plurality of first moments in the first time period and indicator data of the first terminal at the first moment;

[0031] The acquisition module is further used to acquire a second time series data set of the second terminal device, the second time series data set including second time series data corresponding to each of multiple indicators of the second terminal device in a second time period, wherein the second terminal device is a faulty device, the second time period is a time period in the life cycle of the second terminal device corresponding to the first time period, and the second time series data includes multiple second moments in the second time period and indicator data of the second terminal at the second moment;

[0032] An execution module is used to execute the following steps for each first terminal device among the multiple first terminal devices: respectively calculate the similarity between the first time series data and the second time series data corresponding to each indicator to obtain the target similarity corresponding to each indicator; construct a covariate set with the target similarity corresponding to each indicator;

[0033] An input module, used for inputting a plurality of covariate sets corresponding to a plurality of first terminals into a proportional hazard regression Cox model;

[0034] The calculation module is used to calculate the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal device according to multiple covariate sets through the Cox model, so as to predict the operating life of the first terminal device according to the influence coefficient.

[0035] In an optional implementation, the execution module is used to respectively calculate the similarity between the first time series data and the second time series data corresponding to each indicator to obtain the target similarity corresponding to each indicator, including:

[0036] The execution module is used to execute the following steps respectively for the first time series data and the second time series data corresponding to each indicator to obtain the target similarity corresponding to each indicator:

[0037] According to a preset segmentation rule, the first time period is divided into a plurality of first sub-time periods;

[0038] Extracting first time series sub-data corresponding to each of the plurality of first sub-periods from the first time series data;

[0039] Calculate the first average value of the indicator data in each first sub-period according to the first time series sub-data corresponding to each of the plurality of first sub-periods to obtain a first indicator data sequence;

[0040] According to a preset segmentation rule, the second time period is divided into a plurality of second sub-time periods;

[0041] Extracting second time series sub-data corresponding to each of the plurality of second sub-periods from the second time series data;

[0042] Calculate the second average value of the indicator data in each second sub-period according to the second time series sub-data corresponding to each of the plurality of second sub-periods to obtain a second indicator data sequence;

[0043] The dynamic time warping (DTW) similarity between the first indicator data sequence and the second indicator data sequence is calculated as the target similarity corresponding to the indicator.

[0044] In a third aspect, an embodiment of the present application provides an electronic device, the device comprising: a processor and a memory storing computer program instructions;

[0045] When the processor executes the computer program instructions, it implements the information processing method as described in any optional implementation manner of the first aspect of the present application.

[0046] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, an information processing method as in any optional implementation manner of the first aspect of the present application is implemented.

[0047] In a fifth aspect, an embodiment of the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes an information processing method as described in any optional implementation of the first aspect of the present application.

[0048] The information processing method, apparatus, device, computer storage medium and computer program product of the embodiment of the present application can obtain the first time series data set corresponding to each of the multiple first terminal devices, and the first time series data set includes the first time series data corresponding to each of the multiple indicators of the first terminal device in the first time period. The first time series data includes multiple first moments in the first time period and the indicator data of the first terminal device at the first moment. The embodiment of the present application can also obtain the second time series data set of the second terminal device, and the second time series data set includes the second time series data corresponding to each of the multiple indicators of the second terminal device in the second time period. Among them, the second terminal device is a faulty device, the second time period is a time period corresponding to the first time period in the life cycle of the second terminal device, and the second time series data includes multiple second moments in the second time period and the indicator data of the second terminal device at the second moment. In this way, the data of multiple indicators in the corresponding time period can be obtained for the equipment that has not failed and the faulty equipment, so that the influence of multiple factors on the fault can be comprehensively considered. Then, for each of the multiple first terminal devices, the similarity between the first time series data corresponding to each indicator and the second time series data is calculated respectively, and the target similarity corresponding to each indicator is obtained; the target similarity corresponding to each indicator is constructed into a covariate set. The target similarity corresponding to each indicator can reflect the similarity of the failure mode of the non-faulty equipment and the faulty equipment. Then, multiple covariate sets corresponding to multiple first terminals are input into the proportional risk regression Cox model. The Cox model is used to calculate the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal equipment according to multiple covariate sets, so as to predict the operating life of the first terminal equipment according to the influence coefficient. In this way, multi-factor analysis can be implemented through the Cox model to determine the influence of the similarity between each indicator of the non-faulty equipment and the faulty equipment on the failure mode of the non-faulty equipment. In this way, the operating life of the first terminal equipment can be accurately predicted, thereby improving the accuracy of fault analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0050] Figure 1 It is a flowchart of an information processing method provided by an embodiment of the present application;

[0051] Figure 2 is a structural diagram of an information processing device provided by another embodiment of the present application;

[0052] Figure 3 It is a structural schematic diagram of an electronic device provided in yet another embodiment of the present application. DETAILED DESCRIPTION

[0053] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0054] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants 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, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0055] As described in the background technology, the degradation process of equipment is often nonlinear and is affected by multiple factors, including environmental conditions, operating loads, maintenance history, etc. The interaction between these factors increases the complexity of model establishment and may lead to deviations in prediction results, resulting in inaccurate prediction results.

[0056] In view of this, the inventor, after in-depth thinking, cleverly proposed an information processing method, device, equipment, computer storage medium and computer program product.

[0057] The following is an introduction to the information processing method provided by the embodiment of the present application through specific embodiments and their application scenarios in conjunction with the accompanying drawings. The information processing method provided by the embodiment of the present application, the device that executes the sending may be an information processing device, or a partial module in the information processing device for executing the information processing method. In the embodiment of the present application, the information processing method provided by the embodiment of the present application is described in detail by taking the information processing device executing the information processing method as an example.

[0058] The following is combined with Figure 1 The information processing method provided in the embodiments of the present application is described in detail.

[0059] Figure 1 FIG. 1 is a flow chart showing an information processing method provided by an embodiment of the present application. Figure 1 As shown, the information processing method may include the following steps S110 to S150.

[0060] S110, obtaining a first time series data set corresponding to each of the multiple first terminal devices, the first time series data set including first time series data corresponding to each of the multiple indicators of the first terminal device in the first time period, the first time series data including multiple first moments in the first time period and indicator data of the first terminal device at the first moment.

[0061] In step S110, the first terminal device may be a device that has not failed. The first time period may be any time period before the current moment. Exemplarily, the first time period may be any time period from the moment the first terminal device is put into use to the current moment. For example, it may be from the moment the first terminal device is put into use to the current moment, or it may be half a year, a month, or a week before the current moment, etc. The multiple indicators may include indicators related to the life of the terminal device, such as maintenance records, upgrade records, working hours, operating load, ambient temperature, etc. Those skilled in the art may select as needed, and are not limited here.

[0062] S120, obtaining a second time series data set of the second terminal device, the second time series data set including second time series data corresponding to multiple indicators of the second terminal device in a second time period, wherein the second terminal device is a faulty device, the second time period is a time period in the life cycle of the second terminal device corresponding to the first time period, and the second time series data includes multiple second moments in the second time period and indicator data of the second terminal device at the second moment.

[0063] In step S120, the second terminal device may be the same device as the first terminal device. Specifically, the second terminal device may be a terminal device of the same device type, manufacturer, and model as the first terminal device. In one example, multiple first terminal devices and the second terminal device may be terminal devices belonging to the same organization, for example, they may be terminal devices belonging to the same smart hotel. The life cycle may represent a time period starting from the moment the terminal device is put into use and ending at the moment when the failure occurs. The second period is a period in the life cycle of the second terminal device corresponding to the first period, and may represent the distance between the second period and the starting point of the life cycle of the second terminal device, which is consistent with the distance between the first period and the starting point of the life cycle of the first terminal device. For example, if the first period is the second month of the first terminal device being put into use, then the second period is the second month of the second terminal device being put into use. In one example, the second period is equal in length to the first period.

[0064] S130, for each first terminal device among the multiple first terminal devices, respectively perform the following steps: respectively calculate the similarity between the first time series data and the second time series data corresponding to each indicator to obtain the target similarity corresponding to each indicator; construct a covariate set with the target similarity corresponding to each indicator.

[0065] S140, inputting a plurality of covariate sets corresponding to a plurality of first terminals into a proportional hazard regression Cox model.

[0066] In one example, the Cox model can be managed by the organization to which the first terminal device and the second terminal device belong. The Cox model can obtain and store the status information of all terminal devices of the organization during their life cycle as an observation set. The status information may include indicator data of various indicators of the terminal device at any time, and whether the terminal device is in a fault state.

[0067] S150, calculating the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal device according to multiple covariate sets through the Cox model, so as to predict the operating life of the first terminal device according to the influence coefficient.

[0068] The information processing method of the embodiment of the present application can obtain the first time series data set corresponding to each of the multiple first terminal devices, and the first time series data set includes the first time series data corresponding to each of the multiple indicators of the first terminal device in the first time period. The first time series data includes multiple first moments in the first time period and the indicator data of the first terminal device at the first moment. The embodiment of the present application can also obtain the second time series data set of the second terminal device, and the second time series data set includes the second time series data corresponding to each of the multiple indicators of the second terminal device in the second time period. Among them, the second terminal device is a faulty device, the second time period is a period corresponding to the first time period in the life cycle of the second terminal device, and the second time series data includes multiple second moments in the second time period and the indicator data of the second terminal device at the second moment. In this way, the data of multiple indicators in the corresponding time period can be obtained for the equipment that has not failed and the faulty equipment, so that the influence of multiple factors on the fault can be comprehensively considered. Then, for each of the multiple first terminal devices, the similarity between the first time series data corresponding to each indicator and the second time series data is calculated respectively, and the target similarity corresponding to each indicator is obtained; the target similarity corresponding to each indicator is used to construct a covariate set. The target similarity corresponding to each indicator can reflect the similarity of the failure mode of the equipment that has not failed and the faulty equipment. Next, multiple covariate sets corresponding to multiple first terminals are input into the proportional risk regression Cox model. The Cox model is used to calculate the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal device based on multiple covariate sets, so as to predict the operating life of the first terminal device based on the influence coefficient. In this way, multi-factor analysis can be implemented through the Cox model to determine the influence of the similarity between each indicator of the non-faulty device and the faulty device on the failure mode of the non-faulty device. In this way, the operating life of the first terminal device can be accurately predicted, thereby improving the accuracy of the fault analysis.

[0069] In one embodiment, the similarity between the first time series data and the second time series data corresponding to each indicator is calculated respectively to obtain the target similarity corresponding to each indicator. Specifically, the following steps may be performed for the first time series data and the second time series data corresponding to each indicator to obtain the target similarity corresponding to each indicator:

[0070] According to a preset segmentation rule, the first time period is divided into a plurality of first sub-time periods.

[0071] The first time series sub-data corresponding to each of the plurality of first sub-periods are extracted from the first time series data.

[0072] According to the first time series sub-data corresponding to each of the plurality of first sub-periods, a first average value of the indicator data in each first sub-period is calculated to obtain a first indicator data sequence.

[0073] According to a preset segmentation rule, the second time period is divided into a plurality of second sub-time periods.

[0074] Second time series sub-data corresponding to each of the plurality of second sub-periods are extracted from the second time series data.

[0075] According to the second time series sub-data corresponding to each of the plurality of second sub-periods, a second average value of the indicator data in each second sub-period is calculated to obtain a second indicator data sequence.

[0076] The dynamic time warping (DTW) similarity between the first indicator data sequence and the second indicator data sequence is calculated as the target similarity corresponding to the indicator.

[0077] In one example, the preset segmentation rule may include evenly dividing a period of time into multiple time periods according to preset durations.

[0078] According to the above-mentioned implementation, the first time series data and the second time series data can be segmented according to the time range, and the average value of the segmented first time series data and the second time series data can be calculated. In this way, the continuous instantaneous indicator data within a period of time can be converted into the average value of the indicator data of multiple time periods, and then the similarity is calculated. In addition, the above-mentioned implementation adopts DTW similarity as the target similarity corresponding to the indicator. DTW similarity can dynamically align the first average value and the second average value in the first indicator data sequence and the second indicator data sequence based on the actual indicators of the terminal device during operation. In this way, the calculated target similarity is associated with the actual operating conditions of the first terminal device and the second terminal device, which is conducive to further improving the accuracy of fault prediction.

[0079] In one embodiment, calculating the dynamic time warping (DTW) similarity between the first indicator data sequence and the second indicator data sequence may specifically include:

[0080] For each first average value in the first indicator data series, the cumulative distance between the first average value and each second average value is calculated respectively.

[0081] The cumulative distances between each first average value and each second average value are arranged in a preset order to create a matrix grid.

[0082] A target path from a preset grid start point to a preset grid end point is determined from the matrix grid, the target path being the shortest path from a preset grid start point to a preset grid end point in the matrix grid.

[0083] The ratio of the number of cumulative distances in the matrix grid to the number of cumulative distances in the shortest path is calculated to obtain the DTW similarity between the first indicator data sequence and the second indicator data sequence.

[0084] For ease of understanding, the above implementation is described below by taking the calculation of target similarity corresponding to the operating load index as an example.

[0085] Exemplarily, the first time period can be divided into m time periods of equal length, where m is a positive integer. Accordingly, the operation load time series data of the first terminal device in the first time period can be divided into m sections of operation load time series data. For each section of operation load time series data, the operation load mean value in the time period is calculated. The operation load mean values ​​of each time period are arranged in chronological order to obtain a first operation load sequence C=c1,c2,…,c j ,…,c m .

[0086] Exemplarily, the second time period can be divided into n time periods of equal length, where n is a positive integer. Accordingly, the operation load time series data of the second terminal device in the second time period can be divided into n sections of operation load time series data. For each section of operation load time series data, the operation load mean value in the time period is calculated. The operation load mean values ​​of each time period are arranged in chronological order to obtain the second operation load sequence Q = q1, q2, ... q i ,…,q n .

[0087] Since each smart terminal device has different usage frequencies and habits, for example, the terminal device and the second terminal device run for one hour at 9 and 10 o'clock respectively, this will cause a delay in the time series of the operating load data, resulting in the preprocessed operating load mean values ​​between users in a certain time period not being well matched in the time series. The time series needs to be aligned first. Specifically, the horizontal axis represents the Q sequence and the vertical axis represents the C sequence, and an n*m matrix grid with cumulative distance as the element can be constructed. Among them, the matrix element (i, j) represents q i and c j The cumulative distance between two points is recorded as AccumulatedCost(q i ,c j ). Next, we can find a path that passes through several grid points in the matrix grid. The matrix elements that the path passes through are the points where the two sequences are aligned for calculation. The statistical time range is monotonic and continuous, so each time the matrix element (i, j) has only three directions of movement: right (i+1, j), upward (i, j+1), and diagonally right and upward (i+1, j+

[0088] 1). Define the cumulative distance, start matching sequences Q and C from point (0, 0), and when you reach a point, the distances calculated from all previous points are accumulated. When you reach the end point (n, m), this cumulative distance is the cumulative distance of sequences Q and C.

[0089] The calculation formula of the cumulative distance can be shown as Formula 1.

[0090] Formula 1:

[0091] AccumulatedCost(q i ,c j )

[0092] =d(q i ,c j )

[0093] +Min{AccumulatedCost(q i-1 ,c j ),AccumulatedCost(q i ,c j-1 ),AccumulatedCost(q i-1 ,c j-1 )}

[0094] In formula 1, d(q i ,c j ) can represent q i and c j The Euclidean distance between two points. After calculating each element in the matrix grid according to Formula 1, you can start backtracking from the upper right corner of the matrix grid, starting from the target element in the upper right corner, and select the element with the smallest cumulative distance from the neighboring elements to the left, below, and below the left of the element; use the element with the smallest cumulative distance as the new target element, and return to select the element with the smallest cumulative distance from the neighboring elements to the left, below, and below the left of the element, until the lower left corner of the backtracking value matrix grid, all target elements form the shortest path. Use the total number of matrix grid elements divided by the number of elements in the shortest path to obtain the target similarity corresponding to the operating load of the first terminal device and the second terminal device.

[0095] In one embodiment, the Cox model is used to calculate the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal device according to multiple covariate sets, which may specifically include:

[0096] The covariate set is substituted into the log partial likelihood function formula preset in the Cox model to obtain the target log partial likelihood function formula. The target log partial likelihood function formula is used to express the corresponding relationship between the log partial likelihood function and the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal equipment.

[0097] Based on the target logarithmic partial likelihood function formula, the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal equipment is calculated when the logarithmic partial likelihood function is the maximum partial likelihood function.

[0098] The basic form of the Cox model is:

[0099] h(t|X)=h0(t)exp(X T β)

[0100] where h(t|X) is given by the covariate X = [X1, X2, X3…, X p ] T Under the condition of , the failure rate at time t, h0(t) is the baseline hazard function, which is not affected by the covariate X, β = [β1, β2, β3..., β p ] is the coefficient variable corresponding to the covariate, and the effect size corresponding to each variable can be understood as the degree of influence of the result. Among them, 1 to p can represent p indicators numbered 1 to p, X1, X2, X3..., X p It can represent the target similarity corresponding to each of the p indicators numbered from 1 to p, β1, β2, β3..., β p The influence coefficients of the target similarities corresponding to the p indicators numbered from 1 to p on the operating life of the terminal equipment can be respectively represented.

[0101] Since h0(t) is unknown, Cox proposed a partial likelihood function that depends only on covariates and the observed event sequence, and has nothing to do with the unobserved baseline risk function. n is the time that n observed devices have not failed, δ i is the indicator function, when T i is the actual observed failure time, δ i =1, otherwise δ i =0, the partial likelihood function L(β) is defined as:

[0102]

[0103] For ease of calculation, the logarithmic partial likelihood function l(β) is usually maximized, which is defined as follows:

[0104]

[0105] In this expression:

[0106] Represents the linear prediction value of the i-th device based on the covariate.

[0107] The risk contribution of all devices where an incident occurred is added up.

[0108] At each event time point T iThe exponential sum of the risk proportions of all devices still at risk is intended to normalize the risk at each event, thereby eliminating the effect of the underlying risk function h0(t).

[0109] In order to find the maximum β value that makes l(β), a numerical optimization algorithm, such as the gradient ascent method, can be used to find the partial derivative of the partial likelihood function with respect to β and set it to 0 for solution. For the Cox model, this gradient can be expressed as:

[0110]

[0111] By maximizing the log-partial likelihood function l(β), we can get the estimated value of parameter β Then the influence of covariates on survival time is evaluated and applied to equipment failure prediction analysis.

[0112] By maximizing the logarithmic partial likelihood function, it is helpful to simplify the processing process within the model and exclude the baseline risk function from the calculation process, which is helpful to improve the accuracy and efficiency of fault prediction analysis.

[0113] In one embodiment, the multiple indicators may include basic information of the terminal device and operation data of the terminal device.

[0114] In one example, the basic information may include but is not limited to maintenance records and / or upgrade records. The operation data may include but is not limited to one or more of working time, load, and ambient temperature.

[0115] Fault prediction based on the above indicators is conducive to multi-dimensional analysis of factors affecting faults, thereby improving the accuracy of fault prediction.

[0116] Based on the same inventive concept as the information processing method, an embodiment of the present application further provides an information processing device, wherein the detection application stores multiple groups of detection data corresponding to multiple cryptographic algorithms.

[0117] like Figure 2 As shown, the information processing device 200 may include an acquisition module 201 , an execution module 202 , an input module 203 and a calculation module 204 .

[0118] Acquisition module 201 is used to acquire first time series data sets corresponding to multiple first terminal devices respectively. The first time series data sets include first time series data corresponding to multiple indicators of the first terminal device in the first time period. The first time series data include multiple first moments in the first time period and indicator data of the first terminal at the first moment.

[0119] The acquisition module 201 is also used to acquire a second time series data set of the second terminal device, the second time series data set includes second time series data corresponding to multiple indicators of the second terminal device in a second time period, wherein the second terminal device is a faulty device, the second time period is a time period in the life cycle of the second terminal device corresponding to the first time period, and the second time series data includes multiple second moments in the second time period and indicator data of the second terminal at the second moment.

[0120] The execution module 202 is used to execute the following steps for each first terminal device among multiple first terminal devices: respectively calculate the similarity between the first time series data and the second time series data corresponding to each indicator to obtain the target similarity corresponding to each indicator; and construct a covariate set with the target similarity corresponding to each indicator.

[0121] The input module 203 is used to input a plurality of covariate sets corresponding to a plurality of first terminals into the proportional hazard regression Cox model.

[0122] The calculation module 204 is used to calculate the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal device according to multiple covariate sets through the Cox model, so as to predict the operating life of the first terminal device according to the influence coefficient.

[0123] The information processing device of the embodiment of the present application can obtain the first time series data set corresponding to each of the multiple first terminal devices, and the first time series data set includes the first time series data corresponding to each of the multiple indicators of the first terminal device in the first time period. The first time series data includes multiple first moments in the first time period and the indicator data of the first terminal device at the first moment. The embodiment of the present application can also obtain the second time series data set of the second terminal device, and the second time series data set includes the second time series data corresponding to each of the multiple indicators of the second terminal device in the second time period. Among them, the second terminal device is a faulty device, the second time period is a time period corresponding to the first time period in the life cycle of the second terminal device, and the second time series data includes multiple second moments in the second time period and the indicator data of the second terminal device at the second moment. In this way, the data of multiple indicators in the corresponding time period can be obtained for the equipment that has not failed and the faulty equipment, so that the influence of multiple factors on the fault can be comprehensively considered. Then, for each of the multiple first terminal devices, the similarity between the first time series data corresponding to each indicator and the second time series data is calculated respectively, and the target similarity corresponding to each indicator is obtained; the target similarity corresponding to each indicator is used to construct a covariate set. The target similarity corresponding to each indicator can reflect the similarity of the failure mode of the equipment that has not failed and the faulty equipment. Next, multiple covariate sets corresponding to multiple first terminals are input into the proportional risk regression Cox model. The Cox model is used to calculate the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal device based on multiple covariate sets, so as to predict the operating life of the first terminal device based on the influence coefficient. In this way, multi-factor analysis can be implemented through the Cox model to determine the influence of the similarity between each indicator of the non-faulty device and the faulty device on the failure mode of the non-faulty device. In this way, the operating life of the first terminal device can be accurately predicted, thereby improving the accuracy of the fault analysis.

[0124] In one embodiment, the execution module is used to respectively calculate the similarity between the first time series data and the second time series data corresponding to each indicator to obtain the target similarity corresponding to each indicator, which may specifically include:

[0125] The execution module is used to process the first time series data and the second time series data corresponding to each indicator through the following sub-modules to obtain the target similarity corresponding to each indicator:

[0126] The sub-segmentation module is used to divide the first time period into multiple first sub-time periods according to a preset segmentation rule.

[0127] The extraction submodule is used to extract the first time series sub-data corresponding to each of the plurality of first sub-periods from the first time series data.

[0128] The calculation submodule is used to calculate the first average value of the indicator data in each first sub-period according to the first time series sub-data corresponding to each of the multiple first sub-periods, so as to obtain a first indicator data sequence.

[0129] The segmentation submodule is further used to divide the second time period into a plurality of second sub-time periods according to a preset segmentation rule.

[0130] The extraction submodule is further used to extract second time series sub-data corresponding to each of the plurality of second sub-periods from the second time series data.

[0131] The calculation submodule is further used to calculate the second average value of the indicator data in each second sub-period according to the second time series sub-data corresponding to each of the plurality of second sub-periods, so as to obtain a second indicator data sequence.

[0132] The calculation submodule is also used to calculate the dynamic time warping DTW similarity between the first indicator data sequence and the second indicator data sequence as the target similarity corresponding to the indicator.

[0133] In one embodiment, the calculation submodule may be specifically used for:

[0134] For each first average value in the first indicator data series, the cumulative distance between the first average value and each second average value is calculated respectively.

[0135] The cumulative distances between each first average value and each second average value are arranged in a preset order to create a matrix grid.

[0136] A target path from a preset grid start point to a preset grid end point is determined from the matrix grid, the target path being the shortest path from a preset grid start point to a preset grid end point in the matrix grid.

[0137] The ratio of the number of cumulative distances in the matrix grid to the number of cumulative distances in the shortest path is calculated to obtain the DTW similarity between the first indicator data sequence and the second indicator data sequence.

[0138] In one embodiment, the calculation module is used to calculate the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal device according to multiple covariate sets through the Cox model, which may specifically include:

[0139] The substitution submodule is used to substitute the covariate set into the logarithmic partial likelihood function formula preset in the Cox model to obtain the target logarithmic partial likelihood function formula. The target logarithmic partial likelihood function formula is used to express the corresponding relationship between the logarithmic partial likelihood function and the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal equipment.

[0140] The calculation submodule is used to calculate the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal device when the logarithmic partial likelihood function is a maximizing partial likelihood function based on the target logarithmic partial likelihood function formula.

[0141] In one embodiment, the multiple indicators may include basic information of the terminal device and operation data of the terminal device.

[0142] The information processing device provided in the embodiment of the present application can realize Figure 1 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0143] Figure 3 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0144] The electronic device may include a processor 301 and a memory 302 storing computer program instructions.

[0145] Specifically, the processor 301 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0146] The memory 302 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 302 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 302 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 302 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 302 is a non-volatile solid-state memory.

[0147] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0148] The processor 301 implements any one of the information processing or information processing methods in the above embodiments by reading and executing computer program instructions stored in the memory 302 .

[0149] As an example, the electronic device may further include a communication interface 303 and a bus 310. Figure 3 As shown, the processor 301, the memory 302, and the communication interface 303 are connected via a bus 310 and communicate with each other.

[0150] The communication interface 303 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0151] Bus 310 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 410 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0152] The electronic device can execute the information processing method in the embodiment of the present application, thereby realizing the combination Figure 1 and Figure 2 Described information processing method and device.

[0153] In addition, in combination with the information processing method in the above embodiments, the embodiments of the present application may provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the information processing methods in the above embodiments is implemented.

[0154] The present application embodiment also provides a computer program product, including a computer program, and the computer program is processed to implement any one of the information processing methods in the above embodiments when it is executed. It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figure. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiment, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0155] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0156] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0157] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0158] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application.

Claims

1. An information processing method, characterized in that: include: Acquire a first time series data set corresponding to each of the plurality of first terminal devices, wherein the first time series data set includes first time series data corresponding to each of the plurality of indicators of the first terminal device in the first time period, and the first time series data includes a plurality of first moments in the first time period and indicator data of the first terminal at the first moment; Acquire a second time series data set of a second terminal device, the second time series data set including second time series data corresponding to each of multiple indicators of the second terminal device in a second time period, wherein the second terminal device is a faulty device, the second time period is a time period in the life cycle of the second terminal device corresponding to the first time period, and the second time series data includes multiple second moments in the second time period and indicator data of the second terminal at the second moment; For each of the plurality of first terminal devices, the following steps are respectively performed: respectively calculating the similarity between the first time series data and the second time series data corresponding to each indicator to obtain the target similarity corresponding to each indicator; constructing a covariate set with the target similarities corresponding to each indicator; Inputting a plurality of covariate sets corresponding to the plurality of first terminals into a proportional hazards regression Cox model; The Cox model is used to calculate the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal device according to the multiple covariate sets, so as to predict the operating life of the first terminal device according to the influence coefficient.

2. The method according to claim 1, characterized in that The similarity between the first time series data and the second time series data corresponding to each indicator is calculated respectively to obtain the target similarity corresponding to each indicator, including performing the following steps respectively for the first time series data and the second time series data corresponding to each indicator to obtain the target similarity corresponding to each indicator: According to a preset segmentation rule, the first time period is divided into a plurality of first sub-time periods; Extracting first time series sub-data corresponding to each of the plurality of first sub-periods from the first time series data; Calculate the first average value of the indicator data in each first sub-period according to the first time series sub-data corresponding to each of the plurality of first sub-periods to obtain a first indicator data sequence; Divide the second time period into a plurality of second sub-time periods according to a preset division rule; Extracting second time series sub-data corresponding to each of the plurality of second sub-periods from the second time series data; Calculate the second average value of the indicator data in each second sub-period according to the second time series sub-data corresponding to each of the plurality of second sub-periods to obtain a second indicator data sequence; The dynamic time warping (DTW) similarity between the first indicator data sequence and the second indicator data sequence is calculated as the target similarity corresponding to the indicator.

3. The method according to claim 2, characterized in that The calculating of the dynamic time normalization (DTW) similarity between the first indicator data sequence and the second indicator data sequence includes: For each first average value in the first indicator data series, respectively calculate the cumulative distance between the first average value and each second average value; Arrange the cumulative distances between each first average value and each second average value in a predetermined order to create a matrix grid; Determine a target path from a preset grid start point to a preset grid end point in the matrix grid, wherein the target path is the shortest path from a preset grid start point to a preset grid end point in the matrix grid; The ratio of the number of cumulative distances in the matrix grid to the number of cumulative distances in the shortest path is calculated to obtain the DTW similarity between the first indicator data sequence and the second indicator data sequence.

4. The method according to claim 1, characterized in that: The calculating, by the Cox model according to the plurality of covariate sets, the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal device includes: Substituting the multiple covariate sets into the logarithmic partial likelihood function formula preset in the Cox model to obtain a target logarithmic partial likelihood function formula, wherein the target logarithmic partial likelihood function formula is used to express the corresponding relationship between the logarithmic partial likelihood function and the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal device; Based on the target logarithmic partial likelihood function formula, the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal device is calculated when the logarithmic partial likelihood function is the maximizing partial likelihood function.

5. The method according to any one of claims 1 to 4, characterized in that The multiple indicators include basic information of the terminal device and operating data of the terminal device.

6. An information processing device, characterized in that: include: An acquisition module, configured to acquire first time series data sets corresponding to each of a plurality of first terminal devices, wherein the first time series data sets include first time series data corresponding to each of a plurality of indicators of the first terminal device in a first time period, and the first time series data include a plurality of first moments in the first time period and indicator data of the first terminal at the first moment; The acquisition module is further used to acquire a second time series data set of a second terminal device, the second time series data set including second time series data corresponding to each of multiple indicators of the second terminal device in a second time period, wherein the second terminal device is a faulty device, the second time period is a time period in the life cycle of the second terminal device corresponding to the first time period, and the second time series data includes multiple second moments in the second time period and indicator data of the second terminal at the second moment; An execution module is used to execute the following steps for each first terminal device among the plurality of first terminal devices: respectively calculate the similarity between the first time series data and the second time series data corresponding to each indicator to obtain the target similarity corresponding to each indicator; construct a covariate set with the target similarity corresponding to each indicator; An input module, used for inputting a plurality of covariate sets corresponding to the plurality of first terminals into a proportional hazard regression Cox model; A calculation module is used to calculate the influence coefficient of the target similarity corresponding to each indicator on the operating life of the terminal device according to the multiple covariate sets through the Cox model, so as to predict the operating life of the first terminal device according to the influence coefficient.

7. The device according to claim 6, characterized in that The execution module is used to respectively calculate the similarity between the first time series data and the second time series data corresponding to each indicator to obtain the target similarity corresponding to each indicator, including: The execution module is used to execute the following steps respectively for the first time series data and the second time series data corresponding to each indicator to obtain the target similarity corresponding to each indicator: According to a preset segmentation rule, the first time period is divided into a plurality of first sub-time periods; Extracting first time series sub-data corresponding to each of the plurality of first sub-periods from the first time series data; Calculate the first average value of the indicator data in each first sub-period according to the first time series sub-data corresponding to each of the plurality of first sub-periods to obtain a first indicator data sequence; Divide the second time period into a plurality of second sub-time periods according to a preset division rule; Extracting second time series sub-data corresponding to each of the plurality of second sub-periods from the second time series data; Calculate the second average value of the indicator data in each second sub-period according to the second time series sub-data corresponding to each of the plurality of second sub-periods to obtain a second indicator data sequence; The dynamic time warping (DTW) similarity between the first indicator data sequence and the second indicator data sequence is calculated as the target similarity corresponding to the indicator.

8. An information processing device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the information processing method according to any one of claims 1 to 5 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the information processing method according to any one of claims 1 to 5 is implemented.

10. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device is enabled to execute the information processing method as described in any one of claims 1 to 5.

Images