Data processing method, device, storage medium and computer equipment

Abstract

The embodiments of the present application provide a data processing method, apparatus, storage medium and computer equipment, including: obtaining abnormal data, inputting the abnormal data into a trained feature representation estimator, and determining the feature representation of the abnormal data in a preset subspace; determining the degree of correlation between each trained classifier and the feature representation, and obtaining the degree of correlation corresponding to each trained classifier; screening out a target correlation degree with the largest correlation degree from multiple correlation degrees, and determining a trained target classifier corresponding to the target correlation degree; determining a target abnormality type corresponding to the trained target classifier based on a preset mapping relationship between the abnormality type and the trained classifier. Compared with the related art, in which the abnormality diagnosis method often assumes that the monitoring data has a homogeneous variable space, the abnormal data in different variable spaces are made measurable in this preset subspace through the trained feature representation estimator, thereby improving the accuracy of abnormality diagnosis.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a data processing method, apparatus, storage medium, and computer equipment. Background Art

[0002] With the rapid advancement and widespread application of artificial intelligence (AI) technology, AI models are gradually being adopted in application scenarios such as industrial production. Among them, abnormality diagnosis solutions based on AI models are gradually being adopted because they can determine whether abnormalities occur in the industrial production process in real time.

[0003] In related technologies, AI-based anomaly diagnosis solutions analyze collected data to determine whether anomalies have occurred during industrial production. The collected data is generally composed of different variables collected by multiple sensors. However, in actual industrial production, factors such as sensor quality degradation, system expansion, and changes in monitoring requirements can lead to the removal or addition of status sensors, causing the monitoring variable space to change over time. Abnormal data is heterogeneous, and existing anomaly diagnosis methods often assume that the monitoring data has a homogeneous variable space, resulting in poor anomaly diagnosis accuracy. Therefore, related technologies urgently need to propose a data processing method to solve these technical problems. Summary of the Invention

[0004] The main purpose of this application is to provide a data processing method, device, storage medium and computer equipment, which can avoid the problem of poor accuracy of abnormality diagnosis and improve the accuracy of abnormality diagnosis.

[0005] In a first aspect, an embodiment of the present application provides a data processing method, comprising:

[0006] Acquire abnormal data, input the abnormal data into a trained feature representation estimator, and determine a feature representation of the abnormal data in a preset subspace;

[0007] Determining the degree of association between each trained classifier and the feature representation, and obtaining the degree of association corresponding to each trained classifier;

[0008] Screening out a target correlation degree with the greatest correlation degree from the plurality of correlation degrees, and determining a trained target classifier corresponding to the target correlation degree;

[0009] Based on a preset mapping relationship between anomaly types and trained classifiers, a target anomaly type corresponding to the trained target classifier is determined.

[0010] In a second aspect, an embodiment of the present application provides a data processing device, including:

[0011] An input unit, configured to obtain abnormal data, input the abnormal data into a trained feature representation estimator, and determine a feature representation of the abnormal data in a preset subspace;

[0012] A first determining unit is configured to determine a correlation degree between each trained classifier and the feature representation, and obtain a correlation degree corresponding to each trained classifier;

[0013] a screening unit, configured to screen out a target correlation degree having the greatest correlation degree from the plurality of correlation degrees, and determine a trained target classifier corresponding to the target correlation degree;

[0014] The second determining unit is configured to determine a target abnormality type corresponding to the trained target classifier based on a preset mapping relationship between the abnormality type and the trained classifier.

[0015] In a third aspect, an embodiment of the present application provides a storage medium, wherein the computer-readable storage medium stores a plurality of instructions, which are suitable for loading by a processor to execute any of the above data processing methods.

[0016] In a fourth aspect, an embodiment of the present application provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above data processing methods when executing the computer program.

[0017] In an embodiment of the present application, abnormal data is obtained and input into a trained feature representation estimator to determine the feature representation of the abnormal data in a preset subspace; the degree of association between each trained classifier and the feature representation is determined to obtain the degree of association corresponding to each trained classifier; a target correlation degree with the largest correlation degree is screened out from a plurality of correlation degrees, and a trained target classifier corresponding to the target correlation degree is determined; based on a preset mapping relationship between the abnormality type and the trained classifier, a target abnormality type corresponding to the trained target classifier is determined. Compared with the related art, the abnormality diagnosis method often assumes that the monitoring data has a homogeneous variable space. In the embodiment of the present application, the feature representation of the abnormal data in a preset subspace is determined by a trained feature representation estimator, so that data in different variable spaces are measurable in this preset subspace, and then the abnormality type is determined according to the feature representation. This can avoid the problem of poor accuracy of abnormal diagnosis caused by assuming that the monitoring data has a homogeneous variable space, thereby improving the accuracy of abnormal diagnosis.

[0018] Other features and advantages of the present disclosure will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present disclosure. The purposes and other advantages of the present disclosure can be realized and obtained by the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 The abnormality diagnosis scheme of the AI ​​model in the related technology provided in the embodiment of this application assumes abnormal data with a homogeneous variable space.

[0021] Figure 2 Abnormal data from actual industrial processes provided by the embodiments of this application.

[0022] Figure 3 A schematic diagram of a data processing system according to an embodiment of the present invention.

[0023] Figure 4 A flowchart of a data processing method provided in an embodiment of the present application.

[0024] Figure 5 A schematic diagram of the structure of a data processing device provided in an embodiment of the present application.

[0025] Figure 6 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of this application.

[0027] It should be noted that some processes described in the specification, claims, and figures above include multiple steps that appear in a specific order. However, it should be understood that these steps may be executed in a different order than the order in which they appear herein or in parallel. The step numbers are used solely to distinguish between the different steps and do not themselves represent any order of execution. Furthermore, terms such as "first," "second," or "target" are used herein to distinguish similar objects and are not necessarily used to describe a specific order or precedence.

[0028] Before further explaining the embodiments of the present disclosure in detail, the nouns and terms involved in the embodiments of the present disclosure are explained. The nouns and terms involved in the embodiments of the present disclosure are subject to the following interpretations:

[0029] Artificial Intelligence (AI) is a key component of the intelligent sciences. It seeks to understand the essence of intelligence and produce new intelligent machines that can respond in a manner similar to human intelligence. AI is a broad discipline encompassing robotics, speech recognition, image recognition, natural language processing, expert systems, machine learning, and computer vision.

[0030] Target, see Figure 1 and Figure 2 , Figure 1 The abnormal data with homogeneous variable space assumed in the abnormal diagnosis scheme of the AI ​​model in the related technology provided in the embodiment of the present application is Figure 2 This is the abnormal data in the actual industrial process provided by the embodiment of this application. Figure 1 As shown, as time changes, it is assumed that at each time point, each acquisition sensor (for example, acquisition sensor 1 to acquisition sensor 5) can collect the corresponding variables, that is, each can obtain the observed variables, so that at the same time point, multiple variables collected (for example, variable 1 to variable 5) constitute abnormal data.

[0031] However, industrial processes may remove or add monitoring sensors due to factors such as system expansion or demand changes, causing the abnormal data variable space to evolve over time. Specific situations may include the following:

[0032] 1. When some measurement values ​​provided by the sensor are no longer needed, the sensor will be removed, the monitored variables will be reduced, and the dimension of the original variable space will be reduced.

[0033] 2. When process adjustments require expanding the production line, new monitoring sensors are added, monitoring variables increase, and the dimensionality of the original variable space increases. In this case, the anomaly diagnosis model needs to learn effective anomaly information in the evolving variable space to ensure the model's anomaly diagnosis performance.

[0034] like Figure 2 As shown in the figure, at time t-3, the data consists only of variables 1, 2, and 3. From time t-1 to time t, acquisition sensors 4 and 5 transition from an undefined state to an observed state, increasing the original variable space dimension (the data originally consisted of variables 1, 2, and 3, but now consists of variables 1, 2, 3, 4, and 5, changing the variable space dimension from 3 to 5). At the same time, the observed variable of acquisition sensor 3 is missing, turning the observed variable into a missing variable. Subsequently, from time t to time t+1, acquisition sensor 3 is removed and no longer records data, and its corresponding variable transitions from an observed state to an undefined state, reducing the variable space dimension.

[0035] It can be seen that the methods in the related art generally assume that abnormal data have a homogeneous variable space, and do not consider the heterogeneity of the corresponding abnormal data at different times.

[0036] In order to solve the above problems, the embodiment of the present application obtains abnormal data, inputs the abnormal data into the trained feature representation estimator, and determines the feature representation of the abnormal data in the preset subspace; determines the degree of association between each trained classifier and the feature representation, and obtains the degree of association corresponding to each trained classifier; screens out the target correlation degree with the largest correlation degree from multiple correlation degrees, and determines the trained target classifier corresponding to the target correlation degree; based on the preset mapping relationship between the abnormal type and the trained classifier, determines the target abnormal type corresponding to the trained target classifier. The abnormal data with heterogeneity is mapped to the preset subspace, giving the data in different variable spaces a common metric so that they can be compared and evaluated in the same subspace. The measurability makes abnormality detection more accurate. Abnormal diagnosis can be performed more accurately, improving the accuracy and reliability of abnormal diagnosis. For details, please continue to refer to the following specific embodiments.

[0037] See also Figure 3 , Figure 3 This is a schematic diagram of a data processing system provided in an embodiment of the present application, which includes a terminal 140, the Internet 130, a gateway 120, a computer device 110, etc.

[0038] Terminal 140 includes, but is not limited to, pre-configured sensors, cameras, or electronic devices such as mobile phones and tablets with information collection capabilities. Furthermore, it can be a single device or a collection of multiple devices. Terminal 140 can communicate with Internet 130 via wired or wireless means to exchange data. Sensors include, but are not limited to, pressure sensors, visual sensors, and voltage and current sensors, which are not specifically defined herein.

[0039] A computer device refers to a computer system that can provide certain services to a terminal 140. Compared to a standard terminal 140, a computer device 110 has higher requirements for stability, security, and performance. A computer device 110 can be a single high-performance computer in a network platform, a cluster of multiple high-performance computers, a portion of a single high-performance computer (e.g., a virtual machine), or a combination of portions of multiple high-performance computers (e.g., virtual machines).

[0040] Gateway 120, also known as a gateway or protocol converter, implements network interconnection at the transport layer and is a computer system or device that acts as a converter. It acts as a translator between two systems using different communication protocols, data formats, languages, or even completely different architectures. Gateways can also provide filtering and security functions. Messages sent from terminal 140 to computer device 110 are sent through gateway 120 to the corresponding computer device 110. Messages sent from computer device 110 to terminal 140 are also sent through gateway 120 to the corresponding terminal 140.

[0041] In industrial applications, the computer device 110 may also be directly connected to the terminal 140 without going through the gateway 120 to achieve real-time synchronization of data collected by the terminal 140 .

[0042] The data processing method according to the embodiment of the present disclosure may be implemented on the computer device 110 .

[0043] It should be noted that Figure 3 The scenario diagram of the data processing system shown is only an example. The data processing system and scenario described in the embodiment of the present application are intended to more clearly illustrate the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided by the embodiment of the present application. Ordinary technicians in this field can know that with the evolution of data processing technology and the emergence of new business scenarios, the technical solution provided by the embodiment of the present application is also applicable to similar technical problems.

[0044] In this embodiment, the description will be made from the perspective of a data processing device, which can be specifically integrated into a computer device having a storage unit and a microprocessor installed therein and having computing capabilities.

[0045] See also Figure 4 , Figure 4 This is a flow chart of a data processing method provided in an embodiment of the present application. The data processing method includes:

[0046] In step 201 , abnormal data is acquired and input into a trained feature representation estimator to determine a feature representation of the abnormal data in a preset subspace.

[0047] Abnormal data is composed of different variables collected by multiple sensors at the same time. The trained feature representation estimator is used to estimate the feature representation of abnormal data mapped to a preset subspace. The preset subspace is a low-dimensional data space that can extract the main features of the data and highlight the key information and patterns in the data. This helps to better understand the essential structure of the data. The subspace provides a new way to represent data, allowing data from different variable spaces to be compared and analyzed in this common subspace, and achieving measurement of data from different variable spaces within the preset subspace. Abnormal data refers to data in industrial processes where the value exceeds the normal range or data is missing due to a certain industrial machine or operation.

[0048] Specifically, the method for determining the characteristic representation of abnormal data in the preset subspace can be implemented according to the following formula:

[0049]

[0050] Among them, x * is abnormal data, q * is the abnormal data x * Feature representation in the preset subspace, L t is the trained feature representation estimator, Used to represent pseudo-inverse, That is the pseudo-inverse matrix of the trained feature representation estimator, Θ t represents the set of observed variables, For the set of variables Θ t The projection operator, That is the abnormal data x * The set of variables Θ observed in t The projection operator is , and t is the time.

[0051] Specifically, the projection operator It can be determined according to the following formula:

[0052]

[0053] Among them, j is a variable. The significance of this formula is that due to sensor abnormalities and other reasons, there will be missing values ​​at each time. Therefore, when at time t, if variable j is in the observed variable set Θ t , then in Retain variable j in , if variable j is not in the observed variable set Θ t , then in Keep 0 in , so as to obtain the projection operator

[0054] For example, there are three sensors that collect different variables, namely variable 1, variable 2 and variable 3. At a certain time t, if This means that at time t, only variables 1 and 2 were observed, and variable 3 was not observed. Therefore,

[0055] In this way, after obtaining the abnormal data, the projection operator of the abnormal data is calculated Recalculate the projection operator and the pseudo-inverse matrix of the trained feature representation estimator The inner product of * Feature representation q in the preset subspace * .

[0056] In step 202, the degree of association between each trained classifier and the feature representation is determined to obtain the degree of association corresponding to each trained classifier.

[0057] Specifically, different classifiers are trained for the types of abnormalities that may occur during the abnormality diagnosis process, so that one abnormality type corresponds to one trained classifier, thereby obtaining multiple trained classifiers.

[0058] For example, if there are C types of anomalies, then the classifier That is the classifier corresponding to the Cth abnormal type.

[0059] Specifically, the degree of association between each trained classifier and the feature representation can be determined according to the following formula:

[0060]

[0061] in, is the trained classifier corresponding to each abnormality type, r is the label of the abnormality type, and the feature representation q is calculated * The trained classifier corresponding to each anomaly type The inner product is used to characterize the projection or similarity measure of the sample in the direction determined by the classifier parameters.

[0062] For example, if the feature representation q * The trained classifier corresponding to each anomaly type If the directions of the trained classifiers in the dataset are consistent or similar in some sense, the inner product will be relatively large, that is, the degree of association will be greater; conversely, if the directions are significantly different, the inner product will be smaller, that is, the degree of association will be smaller. Based on this, the degree of association between each trained classifier and the feature representation is calculated to obtain the corresponding degree of association for each trained classifier.

[0063] In this way, different classifiers are trained for different anomaly types, ensuring that each anomaly type is handled by a corresponding classifier, improving the pertinence and professionalism of anomaly diagnosis. Association Degree Metrics: By calculating the degree of association (inner product) between the feature representation and each classifier, it is possible to quantify the projection or similarity of the sample in the direction determined by the classifier, providing a basis for accurately determining the anomaly type.

[0064] In step 203, a target correlation degree with the greatest correlation degree is screened out from the plurality of correlation degrees, and a trained target classifier corresponding to the target correlation degree is determined.

[0065] After determining the correlation degree corresponding to each trained classifier in step S202, a target correlation degree with the greatest correlation degree is screened out from the plurality of correlation degrees, and the trained target classifier corresponding to the target correlation degree is determined. The trained target classifier with the greatest correlation degree with the feature representation is queried by screening the target correlation degrees.

[0066] In step 204, based on a preset mapping relationship between anomaly types and trained classifiers, a target anomaly type corresponding to the trained target classifier is determined.

[0067] Among them, since different classifiers are trained for the types of abnormalities that may occur during the abnormality diagnosis process, a preset mapping relationship is established between the abnormality type and the trained classifier, that is, one abnormality type corresponds to one trained classifier. Based on this, after determining the trained target classifier in step 203, the target abnormality type corresponding to the trained target classifier can be determined based on the preset mapping relationship. Since the trained target classifier has the highest degree of correlation with the feature representation, the target abnormality type corresponding to the trained target classifier is the most likely abnormality type, thereby achieving the effect of determining the abnormality type based on the abnormal data.

[0068] Specifically, the process of determining the target anomaly type can refer to the following formula:

[0069]

[0070] Among them, argmax r To find out the degree of correlation The label value r with the maximum value is obtained. Since the label value r represents the abnormal type, the degree of association is found. The exception type that obtains the maximum value, which is also the target exception type.

[0071] As can be seen from the above, the embodiment of the present application obtains abnormal data, inputs the abnormal data into the trained feature representation estimator, determines the feature representation of the abnormal data in the preset subspace; determines the degree of correlation between each trained classifier and the feature representation, and obtains the degree of correlation corresponding to each trained classifier; selects the target correlation degree with the largest correlation degree from the multiple correlation degrees, and determines the trained target classifier corresponding to the target correlation degree; based on the preset mapping relationship between the abnormal type and the trained classifier, determines the target abnormal type corresponding to the trained target classifier. In this way, considering that the sensor may have an abnormality that leads to data loss, by introducing the projection operator It effectively handles missing values, ensuring reasonable data representation and analysis under different sensor states. It leverages a trained feature representation estimator to map abnormal data into a low-dimensional pre-set subspace, extracting key features, reducing data dimensionality and complexity, and highlighting key information and patterns. This helps better understand the data's essential structure and improves the accuracy and efficiency of subsequent abnormality diagnosis.

[0072] In some embodiments, before obtaining abnormal data, inputting the abnormal data into a trained feature representation estimator, and determining the feature representation of the abnormal data in a preset subspace, the method further includes:

[0073] (1) determining unused target abnormal sample data in the abnormal sample data set in time order, and obtaining previous control abnormal sample data that is before the target abnormal sample data in time order, wherein the abnormal sample data set includes a plurality of abnormal sample data in time order, and each abnormal sample data is marked with an abnormal type;

[0074] (2) adjusting the feature representation estimator to be trained based on the target variable included in the target abnormal sample data and the control variable of the control abnormal sample data to obtain the adjusted feature representation estimator to be trained, and constructing a target diagonal matrix;

[0075] (3) determining an initial feature representation of the target abnormal sample data based on the adjusted feature representation estimator to be trained, the target diagonal matrix, and the target abnormal sample data;

[0076] (4) determining the degree of correlation between the initial feature representation and each classifier to be trained, and determining a loss value based on the target abnormality type marked by the target abnormal sample data and the degree of correlation between each classifier to be trained;

[0077] (5) updating the initial feature representation based on the adjusted feature representation estimator to be trained, the target diagonal matrix, the target abnormal sample data, and the loss value to obtain a target feature representation corresponding to the target abnormal sample data;

[0078] (6) based on the adjusted feature representation estimator to be trained, the target feature representation, and the target diagonal matrix, iteratively updating the network parameters of the feature representation estimator to be trained until the number of training times reaches a preset number of training times, thereby obtaining an updated feature representation estimator to be trained;

[0079] (7) updating the network parameters of the classifier to be trained based on the target feature representation, the loss value, and the degree of correlation corresponding to each classifier to be trained;

[0080] (8) When there is unused abnormal sample data in the abnormal sample data set, return to the step of determining the unused target abnormal sample data in the abnormal sample data set according to the time sorting until there is no unused abnormal sample data in the abnormal sample data set, thereby obtaining a trained feature representation estimator and each trained classifier.

[0081] The embodiment of this application mainly introduces the training process of the feature representation estimator and the classifier. The task of anomaly diagnosis is to learn the anomaly diagnosis model and identify the corresponding anomaly type in an incremental update manner. Using the minimum empirical loss criterion, the following online optimization problem can be constructed. Specifically, given data at time t and exception type label y i , the goal is to learn an anomaly diagnosis model at time t Minimize the experience loss function. The specific formula is described as follows:

[0082]

[0083] Where i is any time from time 1 to time t, x i That is, the abnormal sample data corresponding to time i, That is the abnormal sample data x i The set of variables Θ observed in i The projection operator, The loss caused by the difference between the actual anomaly category and the predicted anomaly category is quantified. Since data at different times is heterogeneous, it is necessary to learn from heterogeneous data samples. Therefore, a subspace learning method is proposed to map heterogeneous data into a unified subspace and learn an anomaly diagnosis model in this unified subspace. Let f() be the subspace projection function, then the formula can be rewritten as:

[0084]

[0085] Specifically, in the actual training process, in order to reduce the time overhead of the incremental learning process, only the information of the last sample can be considered for updating, so the final form of the formula is:

[0086]

[0087] This formula is the design criterion for incremental anomaly diagnosis models based on feature space evolution using subspace learning. Different loss functions and subspace learning models can be selected based on different application requirements.

[0088] Specifically, the abnormality diagnosis model consists of two parts: the first part is the feature representation estimator, and the second part is the classifier. R is the set of real numbers, is a real number set consisting of S variables at time t, K is the dimension of the subspace, and the feature representation estimator to be trained needs to be trained to obtain a model that can be used to represent heterogeneous abnormal sample data. Projected into the subspace, so that the heterogeneous abnormal sample data in the subspace expression (ie, feature representation) q t ∈R K It can be measured directly, and considering the linear projection problem, the feature representation estimator can be learned at any time by optimizing the following formula:

[0089]

[0090] in, is the objective function in anomaly diagnosis based on subspace learning, and its value depends on the feature representation estimator L t and feature representation q t This objective function is usually used to measure the performance of the model under given data. By optimizing this objective function, L t and q t The value of , enables the model to better fit the data and improve the accuracy of abnormal diagnosis. OSL is the abbreviation of Online Subspace Learning, ‖.‖2 is the 2-norm operation, ‖.‖ F is the F-norm operation, λ1 and λ2 are control parameters greater than zero, and T represents the transpose of the calculation matrix.

[0091] Regarding the classifier, since the classification area is mainly used to learn the classifier in the shared subspace for the classification of sample abnormal types, consider learning multiple linear classifiers. C is the number of exception types, That is, the classifier of the Cth abnormal type, whose dimension is also K. Therefore, at any time t, a classifier can be learned by optimizing the following formula:

[0092]

[0093] in, is the objective function of the classifier, OCL is the abbreviation of Online Classifier Learning, y t is the characteristic representation q t The label corresponding to the abnormal sample data, that is, the anomaly type marked, r t is the highest-ranked irrelevant label, that is, the highest-ranked anomaly type other than the anomaly type noted. l() represents the loss function of the learning classifier. There are many choices for loss functions, such as slope loss, logistic loss, hinge loss, etc. The marginal loss in the embodiment of this application is only one of the choices. This loss requires not only a positive confidence score, but also a confidence score of at least 1 for the model prediction.

[0094] During incremental training, the overall loss function of the feature representation estimator and classifier training process You can refer to the following format:

[0095]

[0096] Specifically, when When it is minimized, the trained feature representation estimator L can be solved. t , the best feature representation q of abnormal sample data t And the trained classifier W t . Reconstruct the formula to minimize This is equivalent to optimizing the following formula:

[0097]

[0098] in, It is a diagonal matrix with the number of rows and columns being the number of variables. When variable i is observed, that is, when the variable set constituting the abnormal sample data includes variable i, then [Θ] i,i =1, that is, the value of the i-th row and column in the diagonal matrix is ​​1, otherwise it is 0.

[0099] Based on this, in the training process of the feature representation estimator and the classifier, it is necessary to obtain an abnormal sample data set, which includes multiple abnormal sample data sorted by time, and each abnormal sample data is marked with an abnormal type, specifically in the form of: t ,y t, where t∈[1,T], that is, the abnormal sample data is a plurality of abnormal sample data sorted by time from time 1 to time T.

[0100] Multiple abnormal sample data are sorted in time to incrementally train the feature representation estimator and classifier. Unused target abnormal sample data in the abnormal sample dataset is identified in time order, i.e., the abnormal sample data currently needed to train the feature representation estimator and classifier. To adapt to the data structure of the new data, the feature representation estimator to be trained needs to be adjusted. This adjustment requires comparing the target variable of the target abnormal sample data with the control variable of the previous control abnormal sample data that is sorted in time before the target abnormal sample data.

[0101] For example, if the target abnormal sample data is x3, then the control abnormal sample data is x2. The target variables of x3 are variables 1, 2, and 3, while the control variables of x2 are variables 2 and 4. Since the data structures of x3 and x2 are different, the feature representation estimator to be trained needs to be adjusted to obtain the adjusted feature representation estimator to be trained.

[0102] When the fixed L t and W t When the network parameters are updated, the feature representation q t When Relative to the feature representation q t The partial derivative of , we get the following formula:

[0103]

[0104] Among them, when l t When it is 0, the optimization formula is selected That is the first preset optimization formula, when l t When >0, the optimization formula is selected That is, the second preset optimization formula, where I in λ1I is a unit matrix with K rows and K columns.

[0105] Specifically, according to the above partial derivatives, the feature representation q can be obtained t The update rule is:

[0106]

[0107] Among them, *∈{Ⅰ,Ⅱ}, that is, the feature representation q t The update rule is based on the loss value e t The relationship between η and zero is determined by selecting different optimization formulas. t is a pre-set learning rate.

[0108] Specifically, the variable structure of abnormal sample data can be obtained through the projection operator To express it, we can use Converted into a diagonal matrix, the target diagonal matrix is ​​obtained. Using the adjusted feature representation estimator to be trained, the target diagonal matrix and the target abnormal sample data, the initial feature representation of the target abnormal sample data is determined. Initial characterization To initialize the actual feature representation at time t, in order to speed up the model convergence process, the embodiment of the present application selects a hot start method to determine the initial feature representation, but the initial feature representation can also be randomly initialized, which is not limited here.

[0109] Among them, when determining the target abnormal sample data x t The corresponding target feature representation q t When the target feature representation q is determined t The update rule is composed of the loss value l t To determine, therefore in determining the target feature representation q t Before, we need to determine the loss value l t , thereby adjusting the feature representation estimator to be trained The target diagonal matrix Θ t , the target abnormal sample data x t And the loss value l t , update the initial feature representation Get the target feature representation q corresponding to the target abnormal sample data t .

[0110] Specifically, after obtaining the target feature representation q corresponding to the target abnormal sample data t Finally, the network parameters of the feature representation estimator to be trained are iteratively updated based on the adjusted feature representation estimator to be trained, the target feature representation, and the target diagonal matrix until the preset number of training cycles is reached. This continuously adjusts the estimator's parameters to better extract data features and improve model performance. The network parameters of the classifier to be trained are then updated based on the target feature representation, the loss value, and the corresponding correlation level of each classifier to be trained. This classifier update also enables it to more accurately classify different anomaly types.

[0111] If unused abnormal sample data exists in the abnormal sample dataset, the process returns to the step of sorting by time and identifying unused target abnormal sample data in the abnormal sample dataset, and this process continues until no unused abnormal sample data exists in the abnormal sample dataset. This cycle ensures that all data is used for training, continuously optimizing the model. Ultimately, a trained feature representation estimator and each trained classifier are obtained. These trained models can be used to predict and diagnose the anomaly type of new abnormal data.

[0112] In some embodiments, each row of the feature characterization estimator to be trained represents a variable, and adjusting the feature characterization estimator to be trained based on the target variable included in the target abnormal sample data and the control variable of the control abnormal sample data to obtain the adjusted feature characterization estimator to be trained includes:

[0113] (2.1) determining the intersection of the target variables included in the target abnormal sample data and the control variables of the control abnormal sample data to obtain a set of identical variables;

[0114] (2.2) determining a new variable in the target variable that is not in the same variable set;

[0115] (2.3) determining missing variables in the control variables that are not in the same variable set;

[0116] (2.4) Deleting the rows corresponding to the missing variables in the feature representation estimator to be trained, and performing new row processing in the feature representation estimator to be trained according to the new variables to obtain an adjusted feature representation estimator to be trained.

[0117] The specific adjustment method for adjusting the feature representation estimator to be trained can refer to the following formula:

[0118]

[0119] Where Π represents the projection operator, That is, the feature representation estimator to be trained after the feature representation estimator to be trained is trained with the control abnormal sample data. t-1 Projected onto the target variable S t and control variable S t-1 The intersection of and the subspace determined by dimension K; To represent the projection of the zero vector onto the subspace determined by the difference between and and the dimension K. In this way, when dealing with the situation where the number of sensors changes, the old feature representation estimator can be adjusted and updated according to the new set of observation variables.

[0120] Specifically, the same variable set is St ∩S t-1 , the new variable is S t \S t-1 , the missing variable is the control variable S t-1 are not in the same variable set S t ∩S t-1 Since each row of the feature representation estimator to be trained represents a variable, this formula deletes the L corresponding to the missing variable t-1 At the same time, The addition of initialized the corresponding This strategy enables the feature characterization estimator of the embodiment of the present application to adapt to changes in the sensor.

[0121] In some embodiments, constructing a target diagonal matrix includes:

[0122] (2.5) determining the sum of the variables in the same variable set, the newly added variables, and the missing variables to obtain the total number of variables;

[0123] (2.6) constructing an initial diagonal matrix according to the total number, wherein the values ​​of the corresponding positions of the rows and columns with the same values ​​in the initial diagonal matrix are 1;

[0124] (2.7) Change the values ​​in the rows corresponding to the missing variables in the initial diagonal matrix from one to zero to obtain the target diagonal matrix.

[0125] Among them, since the purpose of the diagonal matrix is ​​to project the operator Converted into matrix form, The number of rows and columns are both the number of variables. When variable i is observed, that is, when the variable set that constitutes the abnormal sample data includes variable i, then [Θ] i,i =1, that is, the value of the i-th row and column in the diagonal matrix is ​​1, otherwise it is 0. Therefore, the sum of the variables in the same variable set, the newly added variables, and the missing variables is determined to obtain the total number of variables; an initial diagonal matrix is ​​constructed based on the total number, and the values ​​of the corresponding positions of the rows and columns with the same values ​​in the initial diagonal matrix are 1; the values ​​in the rows corresponding to the missing variables in the initial diagonal matrix are changed from 1 to 0 to obtain the target diagonal matrix.

[0126] For example, in an industrial process, there are three variables, namely variable A, variable B and variable C. At a certain time point t-1, the observed variable set is S t-1 ={A,B}. At time point t, the set of observed variables becomes S t ={A,C}. Diagonal matrix Θ t-1 and Θ tThey are all 3×3 matrices (because there are three variables).

[0127] For Θ t-1 , since we observe variables A and B, so [Θ] 1,1 =1,[Θ] 2,2 =1, and other positions are 0.

[0128] For Θ t , we observe variables A and C, so [Θ] 1,1 =1,[Θ] 3,3 =1, and other positions are 0.

[0129] For the target diagonal matrix at the time point, since in S t Variable B is missing in , so the value of B row and B column corresponding to variable B in the initial diagonal matrix is ​​changed from 1 to 0, and the target diagonal matrix is ​​obtained as

[0130] In some embodiments, determining the loss value based on the target abnormality type labeled with the target abnormal sample data and the degree of correlation of each of the classifiers to be trained includes:

[0131] (4.1) determining a first classifier to be trained corresponding to a target abnormality type marked by the target abnormal sample data;

[0132] (4.2) selecting a second classifier to be trained with the greatest correlation from the other classifiers to be trained, wherein the other classifier to be trained is a classifier other than the first classifier to be trained in each classifier to be trained;

[0133] (4.3) obtaining a first correlation degree of the first classifier to be trained and a second correlation degree of the second classifier to be trained;

[0134] (4.4) determining a difference from the first correlation degree to obtain a first determination result;

[0135] (4.5) determining a sum of the first determination result and the second correlation degree to obtain a second determination result;

[0136] (4.6) When the second determination result is greater than zero, determining the second determination result as a loss value;

[0137] (4.7) When the second determination result is less than zero, zero is determined as the loss value.

[0138] Among them, the loss value for the classifier is Therefore, it is necessary to train the first classifier corresponding to the target abnormal type marked by the target abnormal sample data. For example, if the target abnormal type marked by the target abnormal sample data is a, then the first classifier to be trained is It converts to Since the target feature representation q of the target abnormal sample data is not known at this time t , so the initial feature representation of the target abnormal sample data is calculated The degree of correlation with each classifier other than the first classifier (other classifiers to be trained), and then select the classifier with the largest degree of correlation as the second classifier to be trained, that is, If the exception type corresponding to the second classifier is b, then It converts to The first degree of correlation is The second degree of correlation is The first determination result is The second determination result is

[0139] Specifically, if the second determination result is greater than zero, there is a loss value, and the second determination result is determined as the loss value; if the second determination result is equal to zero, there is no loss value, and the loss value is determined to be zero. This process determines the loss value by comparing the correlation between the classifier corresponding to the target anomaly type and other classifiers and the feature representation, which is used for subsequent updating of the parameters of the feature representation estimator and classifier to improve the model's ability to accurately judge the anomaly type.

[0140] In some embodiments, updating the network parameters of the classifier to be trained based on the target feature representation, the loss value, and the correlation degree corresponding to each classifier to be trained includes:

[0141] (7.1) When the loss value is not zero, calculating the product of a preset learning rate and the target feature representation to obtain an updated parameter;

[0142] (7.2) determining a sum of the first classifier to be trained and the updated parameter to obtain a third determination result;

[0143] (7.3) Updating the network parameters of the first classifier to be trained to the third determination result;

[0144] (7.4) determining a difference between the second classifier to be trained and the updated parameter to obtain a fourth determination result;

[0145] (7.5) Update the network parameters of the second classifier to be trained to the fourth determination result.

[0146] Among them, at a fixed q tand L t When W is updated t , that is, calculation To W t The partial derivative of , we can get the following W t Update rules:

[0147]

[0148] Among them, when the loss value is not zero, it means that there is a certain error in the classification result of the classifier on the current target abnormal sample data, and the parameters of the classifier need to be adjusted. The preset learning rate is η t , the target feature is represented as t , then the updated parameter is η t q t The learning rate controls the step size of the parameter update. If the loss value is not zero, the first classifier to be trained corresponding to the target anomaly type The update method is This is the third determination result. This means that the first classifier is updated in the direction of making it more relevant to the target feature representation to reduce the loss. The update method is This is the fourth determination result, which is an update in the direction of making the second classifier irrelevant to the target feature representation, because the current loss value shows that the second classifier performs too well on the current sample relative to the first classifier, and needs to be adjusted to reduce its correlation with the feature representation.

[0149] In some embodiments, updating the initial feature representation based on the adjusted feature representation estimator to be trained, the target diagonal matrix, the target abnormal sample data, and the loss value to obtain a target feature representation corresponding to the target abnormal sample data includes:

[0150] (5.1) determining whether the loss value is zero to determine a target optimization formula from a preset optimization formula;

[0151] (5.2) Substituting the adjusted feature representation estimator to be trained, the target diagonal matrix, and the target abnormal sample data into the target optimization formula to determine the optimization parameters;

[0152] (5.3) Determine the difference between the initial feature representation and the optimized parameter to obtain the target feature representation corresponding to the target abnormal sample data.

[0153] Among them, due to the characteristic representation q t The update rule is:

[0154]

[0155] and for still And through the loss value l t Determine, so we need to determine the loss value l t Is it zero? If the loss value is l t If is zero, for If the loss value l t If it is not zero, for because and Different optimization formulas are used, so the target optimization formula is determined from the preset optimization formula by determining whether the loss value is zero. Target diagonal matrix Θ t And the target abnormal sample data x t Substitute the target optimization formula to determine the optimization parameters Determine initial characterization With the optimization parameters The difference (which also involves the optimization parameters With the learning rate η t The product of the target abnormal sample data is obtained to obtain the target feature representation q t .

[0156] In some embodiments, based on the adjusted feature representation estimator to be trained, the target feature representation, and the target diagonal matrix, iteratively updating the network parameters of the feature representation estimator to be trained until the number of training times reaches a preset number of training times, thereby obtaining the updated feature representation estimator to be trained, comprising:

[0157] (6.1) determining adjustment parameters based on the adjusted feature representation estimator to be trained, the target feature representation, and the target diagonal matrix;

[0158] (6.2) determining a difference between the adjusted feature representation estimator to be trained and the adjustment parameter, and updating the difference as a network parameter of the adjusted feature representation estimator to be trained;

[0159] (6.3) Increase the number of iterations by one;

[0160] (6.4) When the number of iterations does not reach the preset number of training times, return to the step of determining the adjustment parameters based on the adjusted feature representation estimator to be trained, the target feature representation, and the target diagonal matrix until the number of iterations reaches the preset number of training times, thereby obtaining the updated feature representation estimator to be trained.

[0161] Among them, when q is fixed t With W t , when updating the feature representation estimator, calculate To L t The partial derivative of L t The update rule is:

[0162]

[0163] Among them, m is the number of iterations, m≤M, and M is the set maximum number of iterations. The feature representation estimator to be trained after adjustment The first one to be updated during iteration By Substituting this formula, we can get the first iteration Similarly, in the second iteration, As Thus, iteratively obtain After M iterations, the updated feature representation estimator to be trained is finally obtained, which is trained using the target abnormal sample data.

[0164] Specifically, That is to adjust the parameters, and adjust the feature representation estimator to be trained Target feature representation q t And the target diagonal matrix Θ t Substitute this formula and combine it with the preset learning rate η t , we can get the adjustment parameters. The difference between the adjusted parameters is used to update the network parameters of the feature representation estimator to be trained after the difference is adjusted, that is, The number of iterations is changed from zero to one. If M is set to 20, since 1<20, the step of determining the adjustment parameters based on the adjusted feature representation estimator to be trained, the target feature representation and the target diagonal matrix is ​​returned to the process until the number of iterations reaches the preset training number (M), and the updated feature representation estimator to be trained L is obtained. t .

[0165] The following will explain from the perspective of argument whether it is possible to extract the abnormal data sample x containing missing variables from the t The projection operator Learn accurate feature representation q t , and whether the incremental update strategy for the classifier is effective.

[0166] The first assumption is: Assume that any abnormal sample are uniformly bounded, that is,

[0167] The second assumption is: Assume that the feature representation estimator L t , feature representation q t and classifier W t are uniformly bounded, that is, and is the feature representation estimator L t The uniform boundedness conditions of Characterize q t The uniform boundedness conditions of is the classifier W t The uniform boundedness condition of .

[0168] If the learned subspace feature representation is accurate enough, it can be obtained by q even in the presence of missing variables. t The abnormal data x t Reconstructed (i.e. To ensure that the algorithm can learn accurate feature representations in the presence of missing measurements, it is necessary to ensure that the proportion of non-missing variables in each data set, ρ, is large enough. For data with insufficient observations, no algorithm can learn accurate features from a pathological data set. The following theorem gives the minimum bound for ρ:

[0169] For the time length t B The variable dimensions in Data. The rank of In order to get the missing data x t The projection operator Get accurate feature representation, the non-missing ratio of each data due:

[0170]

[0171] In order to obtain some of the observed data To learn accurate feature representations, we must ensure that the number of observations is at least equal to the matrix The degrees of freedom are equivalent. Therefore, the minimum non-missing proportion ρ is limited by the degrees of freedom. Since the number of variables successfully observed in each data is ρS t , requiring ρS t T B ≥2T B RR 2 -R, where 2T B RR 2 -R is the degree of freedom of the matrix of rank R. By changing this inequality, we can get ρ.

[0172] If the proportion of non-missing variables in the sample is less than ρ, then no algorithm can convert Refactor to Thus, it is impossible to learn accurate feature representation q t It should be noted that this condition is only a necessary condition. In some cases, such as the case of random missingness, due to the influence of the coupon effect, simply satisfying ρ is not sufficient. Usually more observations are needed to ensure this.

[0173] The performance of the proposed incremental anomaly diagnosis model is evaluated by introducing the concept of regret field. t and batch diagnosis models The performance difference is quantified by the cumulative loss difference between:

[0174]

[0175] Among them, set (q1,y1),…,(q T ,y T ) is based on the formula The obtained subspace feature representation, W t ,t∈[T] is given by the formula By setting the learning rate to For any The following sublinear regret bound can be obtained:

[0176]

[0177] According to the update rule of the classifier, we can get:

[0178]

[0179] The above formula can be changed to:

[0180]

[0181] Due to the convexity of the classifier loss function l(), the following formula is obtained:

[0182]

[0183] Combining the above two formulas and summing them on T, we get:

[0184]

[0185] According to the second assumption, we can get Substituting into the above formula we get:

[0186]

[0187] Since the learning rate is set to Then we can get the sublinear upper bound of the regret domain:

[0188]

[0189] Since the regret domain is sublinear, it can be concluded that when T→+∞, This shows that over time, the performance of the proposed anomaly diagnosis model can asymptotically approach the performance of the optimal anomaly diagnosis model. Therefore, the incremental update strategy of the anomaly diagnosis model is effective in the case of variable space evolution.

[0190] The specific implementation of the above steps can be found in the previous embodiments and will not be repeated here.

[0191] To facilitate better implementation of the data processing method provided in the embodiment of the present application, the embodiment of the present application also provides a device based on the above data processing method. The meanings of the terms are the same as those in the above data processing method, and the specific implementation details can be referred to the description in the method embodiment.

[0192] See also Figure 5 , Figure 5 This is a schematic diagram of the structure of a data processing device provided in an embodiment of the present application, which is applied to a computer device. The data processing device may include an input unit 601, a first determination unit 602, a screening unit 603, and a second determination unit 604.

[0193] An input unit 601 is configured to obtain abnormal data, input the abnormal data into a trained feature representation estimator, and determine a feature representation of the abnormal data in a preset subspace;

[0194] A first determining unit 602 is configured to determine a correlation degree between each trained classifier and the feature representation, and obtain a correlation degree corresponding to each trained classifier;

[0195] A screening unit 603 is configured to screen out a target correlation degree with the greatest correlation degree from the plurality of correlation degrees, and determine a trained target classifier corresponding to the target correlation degree;

[0196] The second determining unit 604 is configured to determine a target abnormality type corresponding to the trained target classifier based on a preset mapping relationship between abnormality types and trained classifiers.

[0197] In some embodiments, the apparatus is further configured to:

[0198] Determine unused target abnormal sample data in the abnormal sample data set according to time sorting, and obtain previous control abnormal sample data that is before the target abnormal sample data in time sorting, wherein the abnormal sample data set includes a plurality of abnormal sample data ordered according to time, and each abnormal sample data is marked with an abnormality type;

[0199] Adjusting the feature representation estimator to be trained based on the target variable included in the target abnormal sample data and the control variable of the control abnormal sample data to obtain the adjusted feature representation estimator to be trained, and constructing a target diagonal matrix;

[0200] Determining an initial feature representation of the target abnormal sample data based on the adjusted feature representation estimator to be trained, the target diagonal matrix, and the target abnormal sample data;

[0201] Determining a correlation between the initial feature representation and each classifier to be trained, and determining a loss value based on the target anomaly type marked by the target anomaly sample data and the correlation between each classifier to be trained;

[0202] Based on the adjusted feature representation estimator to be trained, the target diagonal matrix, the target abnormal sample data, and the loss value, updating the initial feature representation to obtain a target feature representation corresponding to the target abnormal sample data;

[0203] Based on the adjusted feature representation estimator to be trained, the target feature representation, and the target diagonal matrix, iteratively updating the network parameters of the feature representation estimator to be trained until the number of training times reaches a preset number of training times, thereby obtaining an updated feature representation estimator to be trained;

[0204] Updating network parameters of the classifier to be trained based on the target feature representation, the loss value, and the correlation degree corresponding to each classifier to be trained;

[0205] When there is unused abnormal sample data in the abnormal sample data set, return to the step of determining the unused target abnormal sample data in the abnormal sample data set according to the time sorting until there is no unused abnormal sample data in the abnormal sample data set, thereby obtaining a trained feature representation estimator and each trained classifier.

[0206] In some embodiments, the apparatus is further configured to:

[0207] Determine the intersection of the target variable included in the target abnormal sample data and the control variable of the control abnormal sample data to obtain an identical variable set;

[0208] Determining a new variable in the target variable that is not in the same variable set;

[0209] determining missing variables in the control variables that are not in the same set of variables;

[0210] The rows corresponding to the missing variables in the feature representation estimator to be trained are deleted, and new row processing is performed in the feature representation estimator to be trained according to the new variables to obtain an adjusted feature representation estimator to be trained.

[0211] In some embodiments, the apparatus is further configured to:

[0212] Determine the sum of the variables in the same variable set, the newly added variables, and the missing variables to obtain the total number of variables;

[0213] Constructing an initial diagonal matrix according to the total number, wherein the values ​​of the corresponding positions of the rows and columns with the same values ​​in the initial diagonal matrix are 1;

[0214] The values ​​in the rows corresponding to the missing variables in the initial diagonal matrix are changed from one to zero to obtain a target diagonal matrix.

[0215] In some embodiments, the apparatus is further configured to:

[0216] Determine a first classifier to be trained corresponding to a target abnormality type marked by the target abnormal sample data;

[0217] Screening out a second classifier to be trained with the greatest correlation from other classifiers to be trained, wherein the other classifier to be trained is a classifier other than the first classifier to be trained in each classifier to be trained;

[0218] Obtaining a first correlation degree of the first classifier to be trained and a second correlation degree of the second classifier to be trained;

[0219] determining a difference from the first correlation degree to obtain a first determination result;

[0220] determining a sum of the first determination result and the second correlation degree to obtain a second determination result;

[0221] When the second determination result is greater than zero, determining the second determination result as a loss value;

[0222] When the second determination result is less than zero, zero is determined as the loss value.

[0223] In some embodiments, the apparatus is further configured to:

[0224] When the loss value is not zero, calculating the product of a preset learning rate and the target feature representation to obtain an updated parameter;

[0225] Determining a sum of the first classifier to be trained and the updated parameter to obtain a third determination result;

[0226] Updating the network parameters of the first classifier to be trained to the third determination result;

[0227] Determining a difference between the second classifier to be trained and the updated parameter to obtain a fourth determination result;

[0228] The network parameters of the second classifier to be trained are updated to the fourth determination result.

[0229] In some embodiments, the apparatus is further configured to:

[0230] Determining whether the loss value is zero to determine a target optimization formula from a preset optimization formula;

[0231] Bringing the adjusted feature representation estimator to be trained, the target diagonal matrix, and the target abnormal sample data into the target optimization formula to determine optimization parameters;

[0232] The difference between the initial feature representation and the optimized parameter is determined to obtain a target feature representation corresponding to the target abnormal sample data.

[0233] In some embodiments, the apparatus is further configured to:

[0234] Determining adjustment parameters based on the adjusted feature representation estimator to be trained, the target feature representation, and the target diagonal matrix;

[0235] Determine a difference between the adjusted feature characterization estimator to be trained and the adjustment parameter, and update the difference as a network parameter of the adjusted feature characterization estimator to be trained;

[0236] Increase the number of iterations by one;

[0237] When the number of iterations does not reach the preset number of training times, return to the step of determining the adjustment parameters based on the adjusted feature representation estimator to be trained, the target feature representation and the target diagonal matrix until the number of iterations reaches the preset number of training times, thereby obtaining the updated feature representation estimator to be trained.

[0238] The specific implementation of each of the above units can be found in the previous embodiments and will not be described again here.

[0239] As can be seen from the above, the embodiment of the present application obtains abnormal data through the input unit 601, inputs the abnormal data into the trained feature representation estimator, and determines the feature representation of the abnormal data in the preset subspace; the first determination unit 602 determines the degree of association between each trained classifier and the feature representation, and obtains the degree of association corresponding to each trained classifier; the screening unit 603 screens out the target correlation degree with the largest correlation degree from the multiple correlation degrees, and determines the trained target classifier corresponding to the target correlation degree; the second determination unit 604 determines the target abnormal type corresponding to the trained target classifier based on the preset mapping relationship between the abnormal type and the trained classifier. In this way, the feature representation of the abnormal data in the preset subspace is determined by the trained feature representation estimator, so that the data in different variable spaces are measurable in this preset subspace, and then the abnormal type is determined according to the feature representation, which can avoid the problem of poor abnormal diagnosis accuracy caused by assuming that the monitoring data has a homogeneous variable space, thereby improving the accuracy of abnormal diagnosis.

[0240] The specific implementation of each of the above units can be found in the previous embodiments and will not be described again here.

[0241] Reference Figure 6 , Figure 6 This is a block diagram of the structure of a portion of a computer device 110 for implementing an embodiment of the present disclosure. The computer device 110 may vary greatly due to different configurations or performance, and may include one or more central processing units (CPUs) 622 (for example, one or more processors) and memories 632, and one or more storage media 630 (for example, one or more mass storage devices) for storing application programs 642 or data 644. The memories 632 and storage media 630 may be temporary storage or permanent storage. The program stored in the storage medium 630 may include one or more modules (not shown in the figure), each module may include a series of instruction operations on the server 600. Furthermore, the central processing unit 622 may be configured to communicate with the storage medium 630 to execute a series of instruction operations in the storage medium 630 on the server 600.

[0242] The computer device 110 may also include one or more power supplies 626, one or more wired or wireless network interfaces 650, one or more input and output interfaces 658, and / or one or more operating systems 641, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0243] The central processing unit 622 in the computer device 110 may be used to execute the data processing method of the embodiment of the present disclosure, for example:

[0244] Acquire abnormal data, input the abnormal data into a trained feature representation estimator, and determine a feature representation of the abnormal data in a preset subspace;

[0245] Determining the degree of association between each trained classifier and the feature representation, and obtaining the degree of association corresponding to each trained classifier;

[0246] Screening out a target correlation degree with the greatest correlation degree from the plurality of correlation degrees, and determining a trained target classifier corresponding to the target correlation degree;

[0247] Based on a preset mapping relationship between anomaly types and trained classifiers, a target anomaly type corresponding to the trained target classifier is determined.

[0248] The embodiments of the present disclosure further provide a computer-readable storage medium, which is used to store program codes, and the program codes are used to execute the data processing methods of the aforementioned embodiments.

[0249] The present disclosure also provides a computer program product, which includes a computer program. A processor of a computer device reads and executes the computer program, so that the computer device executes the above-mentioned data processing method. For example:

[0250] Acquire a first object image, and determine a first segmentation mask of a target object in the first object image, where the first segmentation mask is used to represent different parts of the target object, and the first object image is an image of the target object at the first viewing angle;

[0251] Determining a first posture image of the target object at a second viewing angle;

[0252] Inputting the first segmentation mask and the first pose image into a trained pose encoder to extract pose features of the target object at the second perspective;

[0253] Inputting the first object image into a trained appearance encoder to extract overall appearance features of the target object, the overall appearance features including appearance features corresponding to each appearance dimension;

[0254] Inputting each of the appearance features and the posture features into different trained part feature generators to obtain multiple part features;

[0255] Each of the part features is fused to obtain a fused feature, and the fused feature is input into the trained rendering network to generate a second object image, where the second object image is an image of the target object at the second perspective.

[0256] In addition, the terms "comprises" and "comprising" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or apparatus that comprises a series of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, product or apparatus.

[0257] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0258] It should be understood that in the description of the embodiments of the present application, multiple (or multiple items) means more than two, greater than, less than, exceed, etc. are understood to exclude the number itself, and above, below, within, etc. are understood to include the number itself.

[0259] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0260] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0261] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0262] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0263] It should also be understood that the various implementation methods provided in the embodiments of the present application can be combined arbitrarily to achieve different technical effects.

[0264] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0265] The above is a specific description of the implementation methods of the present application, but the present application is not limited to the above implementation methods. Technical personnel familiar with the art can also make various equivalent modifications or substitutions without violating the spirit of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. An industrial data processing method, characterized in that: include: Acquire industrial anomaly data, input the industrial anomaly data into a trained feature representation estimator, and determine the feature representation of the industrial anomaly data in a preset subspace by calculating a projection operator of the industrial anomaly data and then calculating the inner product of the projection operator and the pseudo-inverse matrix of the trained feature representation estimator. The industrial anomaly data is composed of different variables collected by multiple industrial monitoring sensors at the same time. The industrial anomaly data refers to data in an industrial process that exceeds a normal range, is missing data, or is caused by the operation of a certain industrial machine, or is caused by the addition, removal, or abnormality of an industrial monitoring sensor. Determining the degree of association between each trained industrial anomaly type classifier and the feature representation, and obtaining the degree of association corresponding to each trained industrial anomaly type classifier; Screening out a target correlation degree with the greatest correlation degree from the plurality of correlation degrees, and determining a trained target industrial anomaly type classifier corresponding to the target correlation degree; Based on a preset mapping relationship between the industrial anomaly type and the trained industrial anomaly type classifier, a target industrial anomaly type corresponding to the trained target industrial anomaly type classifier is determined.

2. The industrial data processing method according to claim 1, characterized in that: Before obtaining the industrial abnormal data, inputting the industrial abnormal data into the trained feature representation estimator, and determining the feature representation of the industrial abnormal data in a preset subspace, the method further includes: Determine unused target industrial abnormal sample data in the industrial abnormal sample data set in time order, and obtain previous reference industrial abnormal sample data that is before the target industrial abnormal sample data in time order, wherein the industrial abnormal sample data set includes a plurality of abnormal sample data in time order, each abnormal sample data being marked with an abnormality type; Adjusting the feature characterization estimator to be trained based on the target variables included in the target industrial abnormal sample data and the control variables of the control industrial abnormal sample data to obtain the adjusted feature characterization estimator to be trained, and constructing a target diagonal matrix; Determining an initial feature representation of the target industrial abnormal sample data based on the adjusted feature representation estimator to be trained, the target diagonal matrix, and the target industrial abnormal sample data; Determining a correlation between the initial feature representation and each industrial anomaly type classifier to be trained, and determining a loss value based on the target industrial anomaly type labeled by the target industrial anomaly sample data and the correlation between each industrial anomaly type classifier to be trained; Based on the adjusted feature representation estimator to be trained, the target diagonal matrix, the target industrial abnormal sample data, and the loss value, updating the initial feature representation to obtain a target feature representation corresponding to the target industrial abnormal sample data; Based on the adjusted feature representation estimator to be trained, the target feature representation, and the target diagonal matrix, iteratively updating the network parameters of the feature representation estimator to be trained until the number of training times reaches a preset number of training times, thereby obtaining an updated feature representation estimator to be trained; updating the network parameters of the industrial anomaly type classifier to be trained based on the target feature representation, the loss value, and the correlation degree corresponding to each industrial anomaly type classifier to be trained; When there is unused abnormal sample data in the industrial abnormal sample data set, return to the step of determining the unused target industrial abnormal sample data in the industrial abnormal sample data set according to the time sorting until there is no unused industrial abnormal sample data in the industrial abnormal sample data set, thereby obtaining a trained feature representation estimator and each trained industrial abnormality type classifier.

3. The industrial data processing method according to claim 2, characterized in that: Each row of the feature characterization estimator to be trained represents a variable, and adjusting the feature characterization estimator to be trained based on the target variable included in the target industrial abnormal sample data and the control variable of the control abnormal sample data to obtain the adjusted feature characterization estimator to be trained includes: Determine the intersection of the target variables included in the target industrial abnormal sample data and the control variables of the control abnormal sample data to obtain a set of identical variables; Determining a new variable in the target variable that is not in the same variable set; determining missing variables in the control variables that are not in the same set of variables; The rows corresponding to the missing variables in the feature representation estimator to be trained are deleted, and new row processing is performed in the feature representation estimator to be trained according to the new variables to obtain an adjusted feature representation estimator to be trained.

4. The industrial data processing method according to claim 3, characterized in that: The constructing of the target diagonal matrix includes: Determine the sum of the variables in the same variable set, the newly added variables, and the missing variables to obtain the total number of variables; Constructing an initial diagonal matrix according to the total number, wherein the values ​​of the corresponding positions of the rows and columns with the same values ​​in the initial diagonal matrix are 1; The values ​​in the rows corresponding to the missing variables in the initial diagonal matrix are changed from one to zero to obtain a target diagonal matrix.

5. The industrial data processing method according to claim 2, characterized in that: The determining of the loss value based on the target industrial anomaly type marked by the target industrial anomaly sample data and the correlation degree of each of the industrial anomaly type classifiers to be trained includes: Determine a first industrial anomaly type classifier to be trained corresponding to the target industrial anomaly type marked by the target industrial anomaly sample data; Screening out a second industrial anomaly type classifier to be trained with the greatest degree of correlation from other industrial anomaly type classifiers to be trained, wherein the other industrial anomaly type classifier to be trained is an industrial anomaly type classifier other than the first industrial anomaly type classifier to be trained in each industrial anomaly type classifier to be trained; Obtaining a first correlation degree of the first industrial anomaly type classifier to be trained and a second correlation degree of the second industrial anomaly type classifier to be trained; determining a difference from the first correlation degree to obtain a first determination result; determining a sum of the first determination result and the second correlation degree to obtain a second determination result; When the second determination result is greater than zero, determining the second determination result as a loss value; When the second determination result is less than zero, zero is determined as the loss value.

6. The industrial data processing method according to claim 5, characterized in that: The updating of network parameters of the industrial anomaly type classifier to be trained based on the target feature representation, the loss value, and the correlation degree corresponding to each industrial anomaly type classifier to be trained includes: When the loss value is not zero, calculating the product of a preset learning rate and the target feature representation to obtain an updated parameter; determining a sum of the first industrial abnormality type classifier to be trained and the updated parameter to obtain a third determination result; Updating the network parameters of the first industrial abnormality type classifier to be trained to the third determination result; determining a difference between the second industrial anomaly type classifier to be trained and the updated parameter to obtain a fourth determination result; The network parameters of the second industrial abnormality type classifier to be trained are updated to the fourth determination result.

7. The industrial data processing method according to claim 2, characterized in that: The updating of the initial feature representation based on the adjusted feature representation estimator to be trained, the target diagonal matrix, the target industrial abnormal sample data, and the loss value to obtain a target feature representation corresponding to the target industrial abnormal sample data includes: Determining whether the loss value is zero to determine a target optimization formula from a preset optimization formula; Substitute the adjusted feature characterization estimator to be trained, the target diagonal matrix, and the target industrial abnormal sample data into the target optimization formula to determine optimization parameters; The difference between the initial feature representation and the optimized parameter is determined to obtain a target feature representation corresponding to the target industrial abnormal sample data.

8. The industrial data processing method according to claim 2, characterized in that: The iterative updating of the network parameters of the feature representation estimator to be trained based on the adjusted feature representation estimator to be trained, the target feature representation, and the target diagonal matrix until the number of training times reaches a preset number of training times, thereby obtaining the updated feature representation estimator to be trained, includes: Determining adjustment parameters based on the adjusted feature representation estimator to be trained, the target feature representation, and the target diagonal matrix; Determine a difference between the adjusted feature characterization estimator to be trained and the adjustment parameter, and update the difference as a network parameter of the adjusted feature characterization estimator to be trained; Increase the number of iterations by one; When the number of iterations does not reach the preset number of training times, return to the step of determining the adjustment parameters based on the adjusted feature representation estimator to be trained, the target feature representation and the target diagonal matrix until the number of iterations reaches the preset number of training times, thereby obtaining the updated feature representation estimator to be trained.

9. An industrial data processing device, characterized in that: include: An input unit is configured to obtain industrial abnormality data, input the industrial abnormality data into a trained feature characterization estimator, and determine the feature characterization of the industrial abnormality data in a preset subspace by calculating a projection operator of the industrial abnormality data and then calculating the inner product of the projection operator and the pseudo-inverse matrix of the trained feature characterization estimator. The industrial abnormality data is composed of different variables collected by multiple industrial monitoring sensors at the same time. The industrial abnormality data refers to data in an industrial process that exceeds a normal range, is missing data, or is caused by the operation of a certain industrial machine, or is caused by the addition, removal, or abnormality of an industrial monitoring sensor. A first determining unit is configured to determine a correlation degree between each trained industrial anomaly type classifier and the feature representation, and obtain a correlation degree corresponding to each trained industrial anomaly type classifier; a screening unit, configured to screen out a target correlation degree having the greatest correlation degree from the plurality of correlation degrees, and determine a trained target industrial anomaly type classifier corresponding to the target correlation degree; The second determining unit is configured to determine a target industrial anomaly type corresponding to the trained target industrial anomaly type classifier based on a preset mapping relationship between the industrial anomaly type and the trained industrial anomaly type classifier.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the industrial data processing method according to any one of claims 1 to 8.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the industrial data processing method according to any one of claims 1 to 8 is implemented.

Images