KR20210098420A - Method for generating abnormal data - Google Patents

Abstract

In one embodiment of the present disclosure for solving the above problems, provided is a computer program stored in a computer-readable storage medium executable by one or more processors. When the computer program is executed on one or more processors of a computer device, the following operations for data processing are performed. The operations may include: selecting a plurality types of different data from a data set including data consisting of one or more feature groups; transforming a part of each data among the selected plurality types of data; and giving a label to each of the plurality types of transformed data and calculating the transformed data using a model.

Description

How to generate abnormal data {METHOD FOR GENERATING ABNORMAL DATA}

The present disclosure relates to the field of artificial intelligence technology, and more particularly, to a data processing method using artificial intelligence.

As sensor data that can be temporarily or permanently stored in a database is accumulated, research on automated processing of monitoring data of numerous industrial equipment is in progress. In order to implement a method for determining the state of data, research on artificial intelligence technology using an artificial neural network is in progress.

Deep learning models using artificial neural networks provide a method to effectively learn complex nonlinear or dynamic panels, but there was a technical challenge for updating the model when the data to be processed changes.

Korean Patent Publication No. KR1020180055708 discloses an image processing method using artificial intelligence.

The present disclosure has been devised in response to the above-described background technology, and is intended to provide a data processing method utilizing artificial intelligence.

A computer program stored in a computer-readable storage medium according to an embodiment of the present disclosure for solving the above-described problems is disclosed. The computer program, when executed on one or more processors of a computer device, causes the following operations to be performed for data processing: selecting a plurality of different data from a data set comprising data organized into one or more feature groups operation, transforming a portion of each data among the selected plurality of data, assigning a label to each of the plurality of transformed data, and calculating the transformed data using a model.

In an alternative embodiment, the plurality of different data may consist of data included in the same cluster or different clusters.

In an alternative embodiment, the method may further include clustering the data of the data set to generate a plurality of data subsets.

In an alternative embodiment, the operation of clustering the data of the data set to generate a plurality of data subsets may be performed by a classification model trained using a triple loss-based cost function.

In an alternative embodiment, each of the plurality of subsets of data may include a different normal pattern of data.

In an alternative embodiment, modifying a portion of each data of the selected plurality of data may include changing a value of one feature group of one or more feature groups of each data. there is.

In an alternative embodiment, the operation of transforming a portion of each data among the selected plurality of data may include an operation of exchanging a value of one data among the plurality of data and a value of another data.

In an alternative embodiment, exchanging a value of one data of the plurality of data with a value of the other data comprises a value of one or more feature groups of one data of the plurality of data and a value of one or more feature groups of the other data. may include an operation of exchanging

In an alternative embodiment, exchanging a value of one data of the plurality of data with a value of another data may include exchanging values of data belonging to the same feature group of each data with each other.

In an alternative embodiment, the data included in the data set may be normal data.

In an alternative embodiment, the operation of applying a label to each of the plurality of transformed data may include applying an abnormal label to each of the plurality of transformed data.

In an alternative embodiment, the operation of calculating the deformed data using the model may include the operation of testing the performance of the model by calculating the deformed data using the model.

In an alternative embodiment, the operation of operating the deformed data using a model to test the performance of the model may include testing the performance of the model based on whether the model determines the deformed data to be abnormal. It can include actions.

In an alternative embodiment, each of the feature groups may be comprised of an associated one of a plurality of items included in the data.

According to another embodiment of the present disclosure, a data processing method performed in one or more processor computing devices is disclosed. The method includes: selecting a plurality of different data from each other in a data set comprising data consisting of one or more groups of features, transforming a portion of each data of the selected plurality of data, each of the plurality of transformed data It may include the step of giving a label and calculating the transformed data using the model.

A computing device is disclosed according to another embodiment of the present disclosure. The computing device includes one or more processors and a memory storing instructions executable in the processor, wherein the processor selects a plurality of different data from a data set including data consisting of one or more feature groups, the selected A part of each data among the plurality of data may be transformed, a label may be assigned to each of the plurality of transformed data, and the transformed data may be calculated using a model.

According to another embodiment of the present disclosure, a computer-readable recording medium storing a data structure for storing data related to a learning process of a neural network model is disclosed. The data is modified by a computer program, wherein the computer program performs an operation of selecting a plurality of different data from a data set including data consisting of one or more groups of features, and selecting a portion of each data from the selected plurality of data. It may include an operation of transforming and an operation of giving a label to each of the plurality of transformed data.

The present disclosure may provide a data processing method utilizing artificial intelligence.

Various aspects are now described with reference to the drawings, in which like reference numbers are used to refer to like elements collectively. In the following examples, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of one or more aspects. It will be evident, however, that such aspect(s) may be practiced without these specific details.
1 is a block diagram of a computing device for performing a data processing method according to an embodiment of the present disclosure.
2 is a schematic diagram illustrating a network function according to an embodiment of the present disclosure;
3 is an exemplary diagram exemplarily showing a plurality of data constituting a data set related to an embodiment of the present disclosure.
4 is a schematic diagram illustrating a method for training a classification model according to an embodiment of the present disclosure.
5 is a schematic diagram illustrating a solution space of a classification model related to an embodiment of the present disclosure.
6 shows a flowchart for performing data processing related to an embodiment of the present disclosure.
7 illustrates logic for implementing a method of performing data processing related to an embodiment of the present disclosure.
8 depicts a simplified, general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

Various embodiments are now described with reference to the drawings. In this specification, various descriptions are presented to provide an understanding of the present disclosure. However, it is apparent that these embodiments may be practiced without these specific descriptions.

The terms “component,” “module,” “system,” and the like, as used herein, refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or execution of software. For example, a component can be, but is not limited to being, a process running on a processor, a processor, an object, a thread of execution, a program, and/or a computer. For example, both an application running on a computing device and the computing device may be a component. One or more components may reside within a processor and/or thread of execution. A component may be localized within one computer. A component may be distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures stored therein. Components may communicate via a network such as the Internet with another system, for example via a signal having one or more data packets (eg, data and/or signals from one component interacting with another component in a local system, distributed system, etc.) may communicate via local and/or remote processes depending on the data being transmitted).

In addition, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise specified or clear from context, "X employs A or B" is intended to mean one of the natural implicit substitutions. That is, X employs A; X employs B; or when X employs both A and B, "X employs A or B" may apply to either of these cases. It should also be understood that the term “and/or” as used herein refers to and includes all possible combinations of one or more of the listed related items.

Also, the terms "comprises" and/or "comprising" should be understood to mean that the feature and/or element in question is present. However, it should be understood that the terms "comprises" and/or "comprising" do not exclude the presence or addition of one or more other features, elements and/or groups thereof. Also, unless otherwise specified or otherwise clear from context to refer to a singular form, the singular in the specification and claims should generally be construed to mean "one or more."

Those skilled in the art will further appreciate that the various illustrative logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be implemented in electronic hardware, computer software, or combinations of both. It should be recognized that they can be implemented with To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application. However, such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

Descriptions of the presented embodiments are provided to enable those skilled in the art to use or practice the present invention. Various modifications to these embodiments will be apparent to those skilled in the art of the present disclosure. The generic principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present invention is not limited to the embodiments presented herein. This invention is to be construed in its widest scope consistent with the principles and novel features presented herein.

In the present disclosure, a network function, an artificial neural network, and a neural network may be used interchangeably.

Korean patent application 10-2018-0080482, filed on July 11, 2018, Korean patent application 10-2019-0050477, filed on April 30, 2019, and Korean patent application 10-, filed on June 7, 2019 All content contained in 2019-0067175 is incorporated herein by reference.

1 is a block diagram of a computing device for performing a data processing method according to an embodiment of the present disclosure.

The configuration of the computing device 100 shown in FIG. 1 is only a simplified example. In an embodiment of the present disclosure, the computing device 100 may include other components for performing the computing environment of the computing device 100 , and only some of the disclosed components may configure the computing device 100 .

According to an embodiment of the present disclosure, the computing device 100 may include a processor 110 , a memory 130 , and a network unit 150 .

The processor 110 may include one or more cores, and a central processing unit (CPU) of a computing device, a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU). ) may include a processor for data analysis, deep learning, etc.

The processor 110 may read a computer program stored in the memory 130 to perform a data processing method according to an embodiment of the present disclosure. According to an embodiment of the present disclosure, the processor 110 may perform an operation for learning the neural network model. The processor 110 is a neural network such as processing of input data for learning in deep learning (DN), extraction of features from input data, calculation of errors, and weight update of the neural network using backpropagation. Calculations for learning can be performed. At least one of the CPU, GPGPU, and TPU of the processor 110 may process the learning of the network function. For example, the CPU and the GPGPU can process learning of a network function and data classification using the network function together.

In addition, in an embodiment of the present disclosure, learning of a network function and data classification using the network function may be processed by using the processors of a plurality of computing devices together. In addition, the computer program executed in the computing device according to an embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program.

In an embodiment of the present disclosure, the computing device 100 may distribute and process a network function using at least one of a CPU, a GPGPU, and a TPU. Also, in an embodiment of the present disclosure, the computing device 100 may distribute and process a network function together with other computing devices. Descriptions of specific details regarding network function distributed processing of the computing device 100 are provided in US patent applications US15/161080 (filed on May 20, 2016) and US15/217475 (filed on July 22, 2016), which are incorporated herein by reference in their entireties. specifically discussed.

The processor 110 may acquire a data set including one or more data to be learned. In an embodiment of the present disclosure, data processed using a neural network model may include all types of data obtained in an industrial field. For example, it may include operation parameters of a device for production of a product in a production process of a product, sensor data obtained by operation of the device, and the like. For example, a temperature setting of equipment in a specific process, a wavelength of a laser in the case of a process using a laser, etc. may be included in the type of data processed in the present disclosure. For example, the data to be processed may include lot equipment history data from a management execution system (MES), data from an equipment interface data source, processing tool recipes, processing tool test data, probe test data, electrical It may include test data, combined measurement data, diagnostic data, remote diagnostic data, post-processing data, and the like, but the present disclosure is not limited thereto. As a more specific example, work-inprogress information including 120,000 items per lot obtained from a semiconductor fab, raw processing tool data, equipment interface information, process metrology information (For example, including 1000 items per lot), defect information accessible to yield-related engineers, operation test information, sort information (including datalog and bitmap), etc., but the present disclosure is not limited thereto. Description of the types of data described above is only an example, and the present disclosure is not limited thereto.

In an embodiment of the present disclosure, the computing device 100 may pre-process the collected data. The computing device 100 may supplement missing values among the collected data. The computing device 100 may, for example, supplement missing values with a median value or an average value, or delete a column in which a plurality of missing values exist. Also, for example, the computing device 100 may utilize the subject matter expertise of an administrator for data preprocessing by the computing device 100 for matrix completion. For example, the computing device 100 may remove values (eg, values estimated due to a malfunction of a sensor, etc.) that are completely out of bounds and limits from the collected data. In addition, the computing device 100 may adjust the value of the data so that the data has a similar scale while maintaining characteristics. The computing device 100 may apply column-wise standardization of data, for example. The computing device 100 may simplify processing by removing heat irrelevant to processing of the neural network model from data. In an embodiment of the present disclosure, the computing device 100 may perform an appropriate input data preprocessing method for facilitating active learning and learning of a neural network model for generating a classification model. Descriptions of specific examples regarding types, examples, preprocessing, transformations, etc. of input data are specifically discussed in US patent application US10/194920 (filed on July 12, 2002), which is hereby incorporated by reference in its entirety.

The input data of an embodiment of the present disclosure may include all kinds of data obtained in an industrial field as described above. For example, it may include operation parameters of a device for production of a product in a production process of a product, sensor data obtained by operation of the device, and the like. One input data may include data obtained while manufacturing a product using one manufacturing recipe on one manufacturing equipment. Data obtained during manufacture of the article of manufacture may include sensor data. That is, an input data set comprising the entire input data may include data obtained while manufacturing a product using one or more manufacturing recipes on one or more manufacturing equipment (i.e., data for multiple manufacturing equipment and multiple manufacturing recipes). may be mixed, and may have a plurality of steady states), each input data may have one steady state as data obtained in the production of a product by one manufacturing recipe on one manufacturing equipment, respectively. .

In an embodiment of the present disclosure, the manufacturing equipment may include any manufacturing equipment for producing a product in an industrial site, and may include, for example, semiconductor manufacturing equipment, but the present disclosure is not limited thereto.

In an embodiment of the present disclosure, a manufacturing recipe may be configured as a method for producing a product in an industrial site, and more specifically, may include data for controlling manufacturing equipment. In an embodiment of the present disclosure, the manufacturing recipe may include, for example, a semiconductor manufacturing recipe loaded into manufacturing equipment, but the present disclosure is not limited thereto.

The memory 130 may store a computer program for performing the data processing method according to an embodiment of the present disclosure, and the stored computer program may be read and driven by the processor 110 .

The network unit 150 may transmit/receive data for performing the data processing method according to an embodiment of the present disclosure to other computing devices, manufacturing devices, servers, and the like. The network unit 150 may enable communication between a plurality of computing devices to distribute data processing using a neural network model.

The processor 110 may acquire a data set including one or more data to be learned. As described above, in an embodiment of the present disclosure, data may include any type of data obtained in an industrial field, and the processor 110 may obtain data from other computing devices, manufacturing equipment, and the like. The one or more acquired data may constitute a data set, and the data set may be a set of data used for operation of one epoch of training of a neural network model.

The data set may include labeled data and unlabeled data. Unlabeled data may be labeled by the data processing method of an embodiment of the present disclosure, and the data processing method of an embodiment of the present disclosure labels unlabeled data, thereby determining the ratio of labeled data included in the data set. This can improve the performance of the model.

That is, in the initial data set, only some data may be labeled, but unlabeled data may be additionally labeled by the data processing method of an embodiment of the present disclosure.

A data subset is a subset of a data set, which may include one or more data, and the data subset may be constructed by selecting data based on predetermined criteria. In the present disclosure, the data set may consist only of normal data. Each of the plurality of data subsets may include data of a different normal pattern. For example, the learning data of the present disclosure may be sensor data acquired in a semiconductor production process, operation parameters of production equipment, and the like. In this case, when the setting of production equipment (for example, change of the wavelength of laser irradiated in a specific process, etc.) is changed in the semiconductor production process (that is, when there is a change in the recipe), the sensor acquired after the setting change The data may be included in a different data subset than the sensor data obtained before the setting change.

The processor 110 may select a plurality of data different from each other from a data set including data composed of one or more feature groups. A plurality of different data may be composed of data included in different clusters.

The data may each consist of a plurality of items. Each of the plurality of items may be classified into a feature group according to a predetermined criterion. The predetermined criterion for classifying the plurality of items of data into a feature group may be any criterion capable of distinguishing values of the data from other values. Specifically, the feature group may include related items among a plurality of items included in data. For example, data may be composed of a plurality of feature groups grouped by values of the same type. In addition, the data may be composed of a plurality of feature groups grouped by values obtained from the same sensor. Also, the data may be organized into a plurality of feature groups grouped by values obtained from the same monitoring module.

As a specific example, the data may be composed of a plurality of sensing values related to an operation parameter of a sensor data production equipment obtained in a semiconductor production process. The data may be composed of temperature sensor data, angle sensor data of a first joint of the robot arm, angle sensor data of a second joint, and the like. In this case, the temperature sensor data may have a plurality of items, for example, when a plurality of temperature sensors exist. In this case, the temperature sensor data may be classified into one feature group. In this case, since the values of the temperature sensor data and the values of the angle sensor data of the first joint are composed of different types of values (ie, values of different units such as temperature and angle), they may be classified into different feature groups. In addition, since the value of the angle sensor data of the first joint and the value of the angle sensor data of the second joint are obtained from different sensors or monitoring modules, they may be classified into different feature groups. That is, the values of the temperature sensor data are classified into the first feature group, the values of the angle sensor data of the first joint are classified into the second feature group, and the values of the angle sensor data of the second joint are classified into the third feature group. can be classified. In other words, since values having the same shape or values obtained through the same sensor or monitoring module are related to each other, they may be classified into the same feature group. The detailed description of the above-described temperature sensor data and joint angle sensor data is only an example, and the present disclosure is not limited thereto.

Specifically, referring to FIG. 2 , the processor 110 may select a plurality of different pieces of data from the data set 200 including data composed of one or more feature groups. For example, the processor 110 may configure at least one or more of data included in the first data subset 210 classified into different clusters and at least one or more of data included in the second data subset 220 . data can be selected. Data included in each different cluster (ie, data included in each data subset) may be data clustered by the same criterion.

As a specific example, a data set including a plurality of data of the present disclosure may be sensor data acquired in a semiconductor production process, an operation parameter of production equipment, and the like. In this case, when the setting of production equipment (for example, change of the wavelength of laser irradiated in a specific process, etc.) is changed in the semiconductor production process (that is, when there is a change in the recipe), the sensor acquired after the setting change The data may be included in a different data subset than the sensor data obtained before the setting change. That is, the plurality of data included in the first data subset may be sensor data acquired at a time before the setting change of the production equipment or data including information about the operation parameter of the production equipment, and included in the second data subset The plurality of data obtained may be data including sensor data acquired at a time point after the setting change of production equipment or information related to operation parameters of production equipment. A detailed description of data included in each of the above-described data subsets is merely an example, and the present disclosure is not limited thereto. That is, the processor 110 may select a plurality of different data from each of the plurality of data subsets classified into different clusters. The processor 110 may cluster data of the data set to generate a plurality of data subsets. A plurality of data subsets may be classified by a classification model trained using, for example, a triplet loss-based cost function. Hereinafter, a method of clustering data of a data set into each of a plurality of data subsets through a classification model will be described in detail with reference to FIGS. 4 and 5 .

4 is a schematic diagram illustrating a method for training a classification model according to an embodiment of the present disclosure.

The classification model of the present disclosure may be trained by the processor 110 to form a cluster between similar data in the solution space 300 . More specifically, in the classification model, the target data 301 and the target similarity data 302 are included in one cluster 310 , and the target dissimilar data 303 is separated from the target data 301 and the target similarity data 302 . It can be trained to be included in different clusters. Each cluster may be positioned to have a predetermined distance margin 320 on the solution space of the learned classification model.

The classification model receives a training data subset including target data 301, target similar data 302, and target dissimilar data 303, maps each data to a solution space, and labels cluster information on the solution space. We can update the weights of one or more network functions included in the classification model so that they can be clustered according to That is, in the classification model, the target data 301 and the target similar data 302 and the target dissimilar data 303 are such that the distances in the solution space of the target data 301 and the target similar data 302 are close to each other. ) can be taught so that the distance in the solution space between them becomes farther away from each other. A classification model may be trained using, for example, a triplet-based cost function. The triplet-based cost function aims to separate a pair of input data of the same class from third input data of a different class, the first distance between the pair of input data of the same class (i.e. the size of cluster 310); Let the difference value between the second distance (ie, the distance between 301 or 302 and 303) between one of the pairs of input data that is the same classification and the third input data be at least the distance margin 320, and train the classification model The method includes reducing a first distance to less than or equal to a percentage of a distance margin. Here, the distance margin 320 may always be positive. In order to reach the distance margin 320, weights of one or more network functions included in the classification model may be updated, and weight updates may be performed every iteration or every 1 epoch. Details regarding this distance margin are disclosed in "FaceNet: A Unified Embedding for Face Recognition and Clustering" by Schroff et al. and Korean Patent Application Laid-Open No. 10-2018-0068292, which are incorporated herein by reference in their entirety.

In addition, the classification model can be trained as a magnet loss-based model that can consider not only cluster classification of dissimilar data, but also semantic relationships between data in one cluster or another cluster. there is. The initial distance between the center points of each cluster on the solution space of the classification model may be modified in the learning process. After the classification model maps the data on the solution space, the position of each data on the solution space may be adjusted based on the cluster to which each data belongs and the similarity with data inside and outside the cluster. Details regarding the learning of a classification model based on magnet loss are disclosed in "METRIC LEARNING WITH ADAPTIVE DENSITY DISCRIMINATION" by O. Rippel et al., which is incorporated herein by reference in its entirety.

That is, the processor 110 may train the classification model to classify the plurality of data included in the data set into each of the plurality of data subsets according to a specific cluster.

5 is a schematic diagram illustrating a solution space of a classification model related to an embodiment of the present disclosure.

The solution space 300 shown in FIG. 5 is only an example, and the classification model may include any number of clusters and any number of data for each cluster. The shapes of the data 331 , 333 , 341 , 343 , etc. included in the cluster shown in FIG. 5 are merely examples for indicating that they are similar data.

In the present disclosure, a solution space is composed of one or more dimensional space and includes one or more clusters, and each cluster is configured based on a position in the solution space of feature data based on respective target data and feature data based on target similar data. can be

In the solution space, the first cluster 330 and the second cluster 340 may be clusters for dissimilar data. Also, the third cluster 350 may be a cluster for data similar to the first and second clusters. The distances 345 and 335 between the clusters may be a measure indicating a difference between data belonging to each cluster.

The twelfth distance 345 between the first cluster 330 and the second cluster 340 may be a measure indicating a difference between data belonging to the first cluster 330 and data belonging to the second cluster 340 . In addition, the thirteenth distance 335 between the first cluster 330 and the second cluster 340 may be a measure indicating the difference between data belonging to the first cluster 330 and data belonging to the third cluster 350 . there is. In the example shown in FIG. 5 , data belonging to the first cluster 330 may be more dissimilar to data belonging to the second cluster 340 than data belonging to the third cluster 350 . That is, when the distance between the clusters is long, data belonging to each cluster may be more dissimilar, and when the distance between the clusters is short, data belonging to each cluster may be less dissimilar. The distances 335 and 345 between the clusters may be greater than the radius of the clusters by a predetermined percentage or more. The processor 110 may classify the input data based on a location where the feature data of the input data is mapped in the solution space of the classification model by calculating the input data using the classification model.

The processor 110 may process the input data using the pre-trained classification model, thereby mapping the feature data of the input data to the solution space of the pre-trained classification model. The processor 110 may classify the input data based on which cluster the input data belongs to among one or more clusters on the solution space based on the location of the input data in the solution space.

In other words, the processor 110 may generate a plurality of data subsets by clustering a plurality of data included in the data set through the learned classification model. For example, the processor 110 may first store sensor data or data related to operation parameters of production equipment obtained at the time of advantage of setting change of production equipment among a plurality of data included in the data set through the learned classification model. It may be classified into a data subset, and sensor data acquired at a time point after the setting change of the production equipment or data related to an operation parameter of the production equipment may be classified into the second data subset.

Accordingly, the processor 110 may classify input data of a classification model, which is a model learned through the triplet loss method, into clusters and determine data having different normal patterns as data for transformation.

According to an embodiment of the present disclosure, the processor 110 may determine data for performing transformation on a portion of each data among a plurality of data. Specifically, the processor 110 may select data that can be used as valid data even after data transformation as data for performing transformation. Also, after the data is transformed, the processor 110 may select data that can be used as data including an abnormal state as data to be transformed. 2 , the processor 110 may select a plurality of different data from each of a plurality of data subsets classified into different clusters as data for data transformation. The processor 110 may select at least one or more data from among the data included in the first data subset 210 , and may select at least one or more data from among the data included in the second data subset 220 . . In this case, each of the first data subset 210 and the second data subset 220 may include information on the advantage of changing settings of production equipment and sensor data acquired at each subsequent time point. That is, the processor 110 selects the first data 211 from the first data subset 210 so that it is valid as data for learning even after the transformation of the data, and can be used as abnormal data after transformation, and The third data 221 may be selected from the second data subset 220 .

Also, the processor 110 may select a plurality of different data from the data subset classified into the same cluster as data for data transformation. The processor 110 may select the first data 211 and the second data 212 included in the first data subset 210 as one cluster as data for data transformation.

According to an embodiment of the present disclosure, the processor 110 may transform a part of each data among the selected plurality of data. The processor 110 may change a value of one or more feature groups of each data.

Also, the processor 110 may exchange a value of one data among a plurality of data and a value of another data. The plurality of data may include, for example, first data and second data. The processor 110 may exchange a partial value of the first data and a partial value of the second data.

Specifically, the processor 110 may exchange values of one or more feature groups of one data among the plurality of data with values of one or more feature groups of other data. The processor 110 may exchange values of data corresponding to the same feature group of each data. The processor 110 may exchange a value of the first feature group of the first data with a value of the first feature group of the second data. For example, the processor 110 may exchange values of the angle sensor feature group of the first joint of the first data with values of the angle sensor feature group of the first joint of the second data. That is, by exchanging the values of the feature groups related to each other, each data may be data that is valid but includes an abnormal state. For example, when values of a feature group that are not related at all in two or more pieces of data are exchanged with each other, there is a possibility that the data itself is not valid, and may itself be judged as abnormal data. That is, for example, when the values of the feature group related to the operating temperature included in the first data are exchanged with the values of the feature group related to the operating time included in the second data, since the data is invalid, the data itself is abnormal. may be judged, and may not be suitable for training the model. In other words, data in which values of different feature groups are exchanged may be data that does not require much classification performance of the model. However, by exchanging values included in the related feature group with each other, it is possible to generate data in which the data itself is valid but not in a normal state. In other words, by exchanging values included in the related feature group to generate data, abnormal data or data requiring a lot of classification performance of the model can be generated. That is, data with a lot of knowledge for the model to learn can be generated.

A feature group selected from data included in different clusters for exchange may be an associated feature group. For example, a feature group selected for exchange may be a common item in data included in different clusters. For example, when the two data are data related to the motion of the same robot arm, the feature group may correspond to each joint of the robot arm. In this case, the processor 110 may exchange, for example, values of a feature group related to the same joint.

Also, the associated feature group may be selected to generate valid data when exchanging the values of each feature group in the two data sets. For example, a feature group selected from each data for exchange may be a feature group corresponding to the form and validity of a value included in the corresponding feature group. For example, if the two data are data related to the motion of the same robot arm, the feature group may be each joint of the robot arm.

Also, in another example, the associated feature group may be selected as a feature group whose state of data may be changed when the value of each feature group is exchanged in two pieces of data. In this case, as described above, the feature group may be selected so that the data is valid before and after the exchange. For example, if the two data are data related to the motion of the same robot arm, the feature group may be each joint of the robot arm. In addition, the processor 110 may exchange values of a group of features, for example, relating to different joints. That is, the processor 110 may exchange the value of the feature group related to the first joint in the first data with the value of the feature group related to the second joint in the second data. In this case, both the values of the feature group related to the first joint and the values of the feature group related to the second joint may include values related to the joint motion angle, and in this way, data of the feature group are exchanged to generate data. Even so, the data can have a valid form. The foregoing description is merely an example, and the present disclosure is not limited thereto.

As another example, the processor 110 may exchange values of a group of features related to different joints. By exchanging the values of the feature groups related to different joints, if the data before the exchange is the steady state data, the data after the exchange may be in the abnormal state. In addition, values of corresponding feature groups in each data may be exchanged. However, in this case, since the state of data may not change according to values included in other feature groups, the processor 110 may select a feature group so that the state of data is changed when the corresponding feature group is exchanged for learning. .

In more detail with reference to FIG. 2 , the processor 110 may select a plurality of different data from each of a plurality of data subsets classified into different clusters. The processor 110 may select at least one or more data from among the data included in the first data subset 210 , and may select at least one or more data from among the data included in the second data subset 220 . . In this case, each of the first data subset 210 and the second data subset 220 may include information on the advantage of changing settings of production equipment and sensor data acquired at each subsequent time point. When the second data 212 is selected from the first data subset 210 and the fourth data 222 is selected from the second data subset 220 , the processor 110 generates the second data 212 and a value of one feature group among one or more feature groups included in each of the fourth data 222 . The processor 110 exchanges the value of the first feature group among the plurality of feature groups included in the second data 212 with the value of the first feature group among the plurality of feature groups included in the fourth data 222 ( 21), the value of each feature group can be modified. That is, the processor 110 selects data included in each data subset forming a different cluster, and exchanges values of data belonging to the same feature group of each selected data, each of the selected plurality of data It is possible to perform transformations on some of the In this case, each transformation of the selected data may be performed by exchanging values of data belonging to the same feature group (ie, exchanging data values having correlation).

Also, the processor 110 may select two or more pieces of data included in the same data subset and change their values. For example, the processor 110 selects the first data 211 and the second data 212 included in the first data subset 210 to obtain a first feature group and a second data group of the first data 211 . Data of the first feature group of data 212 may be exchanged 22 with each other to generate new data. And in this case, the generated data may be normal or abnormal depending on values included in other feature groups. In the above example, the first data 211 in which the value of the first feature group is changed to the value of the first feature group of the second data 212 according to the values included in the second to third feature groups is normal data. It may be or may be abnormal data.

As another example, the processor 110 selects the first data 211 and the second data 212 included in the first data subset 210 to select the first feature group and the second data 212 of the first data 211 . The second feature group of the two data 212 may be exchanged 23 with each other to generate new data. In this case, the first feature group of the first data 211 may be a feature group consisting of values related to the angle sensing data of the first joint, and the second feature group of the second data 212 is the angle of the second joint. It may be a feature group consisting of values related to sensing data. When the first joint and the second joint have, for example, similar specifications and corresponding motion ranges, valid data may be generated. That is, by transforming data through exchange 23 between groups of features that are not exactly the same feature group, but are related (that is, a feature group consisting of values related to angle sensing data of joints), the data is highly likely to be valid, Transformation into data containing an anomalous state may be possible.

Accordingly, as a result of the processor 110 selecting a plurality of data and exchanging the values of the feature group of each data, normal data included in each data may be transformed into abnormal data. In addition, since the abnormal data transformed by the processor 110 is not generated through the exchange of normal data including completely different manufacturing recipes, but is the exchange of the same feature group of each normal data having relevance, learning and It may be used as data for testing. That is, the processor 110 may additionally generate abnormal data for learning or testing of the neural network through transformation of each of the plurality of data.

According to an embodiment of the present disclosure, the processor 110 may assign a label to each of the plurality of transformed data. The processor 110 may assign an abnormal label to each of the plurality of transformed data. Specifically, the processor 110 selects a plurality of data from each of a plurality of data subsets forming a different cluster, and exchanges values of data belonging to the same feature group of each selected data to each of the selected plurality of data. Abnormal data can be generated by modifying a part of . Also, the processor 110 may assign a number abnormality label to each of the generated abnormal data. The pseudo-abnormal label may be a hard label or a soft label. The pseudo-abnormal label may be, for example, a label indicating that the corresponding data is abnormal, or may indicate the probability that the corresponding data is abnormal (eg, a value obtained by considering the weight of the changed feature group in the data). The foregoing description is merely an example, and the present disclosure is not limited thereto.

For example, the processor 110 may select first data and second data from a data set including a plurality of data, and exchange a specific feature group of each of the first data and the second data. In this case, since the first data includes a value of a specific feature group of the second data, and the second data includes a value of a corresponding specific feature group of the first data, each transformed data may be abnormal data. . In this case, the processor 110 may give each data a label that is also abnormal data. A detailed description of a process of generating abnormal data through each of the above-described data is merely an example, and the present disclosure is not limited thereto.

That is, the processor 110 assigns a number abnormality label to each of the transformed data (ie, each abnormal data) by exchanging one or more feature groups included in each of the plurality of data, thereby determining whether the model is abnormal for the data. It can be taught to perceive.

In general, a neural network model for detecting anomaly based on specific data may be pre-trained through training data including normal data and abnormal data. In other words, in the process of pre-training the neural network model to detect anomalies, both normal data and abnormal data may need to be built. However, since the abnormal data for training the neural network includes time series information, it is difficult to obtain (or build), and a lot of time may be required to construct the abnormal data. According to the present disclosure, since abnormal data can be generated by transforming data by exchanging the same feature group of each of the normal data, there is no need to construct separate abnormal data, so that training data can be easily constructed. In addition, abnormal data generated by transforming a plurality of data of the present disclosure is data belonging to the same feature group, rather than simply transforming some regions of each data into different values (eg, adding some noise to specific data, etc.) Since the value of is performed through exchange (ie, exchange of data values having correlation), it is possible to generate training data suitable for training a neural network (eg, an anomaly sensing model).

According to an embodiment of the present disclosure, the processor 110 may calculate the transformed data using a model. In an embodiment of the present disclosure, the model may be used for anomaly detection. The processor 110 may test the performance of the model by calculating the transformed data using the model. The processor 110 may test the performance of the model based on whether the modified data is determined to be abnormal. For example, the processor 110 may perform transformation on the first data and the second data by exchanging a first feature group among a plurality of feature groups included in each of the first data and the second data. Also, the processor 110 may use each of the deformed first data and the second data (ie, abnormal data) as input to the model, and output whether or not each data is anonymous. When the output result of the model includes information that an anomaly is detected in the first data and includes information that an anomaly is detected in the second data, the processor 110 may determine that the performance of the model is appropriate. .

For another example, when the output result of the model includes information that an anomaly is not detected in at least one of the first data and the second data, the processor 110 determines that the performance of the model is not appropriate. can be discerned. A detailed description of whether an anomaly output based on the above-described first data and second data is an example is only an example, and the present disclosure is not limited thereto.

That is, it may become possible to test the performance of a trained neural network model in an environment in which a test data set is not built. In other words. Even without constructing a separate test set for testing the learned neural network model, the learned neural network model can be tested by generating abnormal data through the transformation of a plurality of data.

Accordingly, since there is no need to build a separate test set, training and performance testing of the neural network is simplified, and the efficiency of generating a neural network model (ie, anomaly detection model) that detects anomalies can be improved.

3 is a schematic diagram illustrating a network function related to an embodiment of the present disclosure.

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. A neural network may be composed of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is configured by including at least one or more nodes. Nodes (or neurons) constituting the neural networks may be interconnected by one or more links.

In the neural network, one or more nodes connected through a link may relatively form a relationship between an input node and an output node. The concepts of an input node and an output node are relative, and any node in an output node relationship with respect to one node may be in an input node relationship in a relationship with another node, and vice versa. As described above, an input node-to-output node relationship may be created around a link. One or more output nodes may be connected to one input node through a link, and vice versa.

In the relationship between the input node and the output node connected through one link, the value of the output node may be determined based on data input to the input node. Here, a node interconnecting the input node and the output node may have a weight. The weight may be variable, and may be changed by the user or algorithm in order for the neural network to perform a desired function. For example, when one or more input nodes are interconnected to one output node by respective links, the output node sets values input to input nodes connected to the output node and links corresponding to the respective input nodes. An output node value may be determined based on the weight.

As described above, in a neural network, one or more nodes are interconnected through one or more links to form an input node and an output node relationship within the neural network. The characteristics of the neural network may be determined according to the number of nodes and links in the neural network, the correlation between the nodes and the links, and the value of a weight assigned to each of the links. For example, when the same number of nodes and links exist and there are two neural networks having different weight values between the links, the two neural networks may be recognized as different from each other.

A neural network may include one or more nodes. Some of the nodes constituting the neural network may configure one layer based on distances from the initial input node. For example, a set of nodes having a distance n from the initial input node may constitute n layers. The distance from the initial input node may be defined by the minimum number of links that must be traversed to reach the corresponding node from the initial input node. However, the definition of such a layer is arbitrary for description, and the order of the layer in the neural network may be defined in a different way from the above. For example, a layer of nodes may be defined by a distance from the final output node.

The initial input node may refer to one or more nodes to which data is directly input without going through a link in a relationship with other nodes among nodes in the neural network. Alternatively, in a relationship between nodes based on a link in a neural network, it may mean nodes that other input nodes connected by a link do not have. Similarly, the final output node may refer to one or more nodes that do not have an output node in relation to other nodes among nodes in the neural network. In addition, the hidden node may mean nodes constituting the neural network other than the first input node and the last output node. The neural network according to an embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer may be the same as the number of nodes in the output layer, and the number of nodes decreases and then increases again as progresses from the input layer to the hidden layer. can In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer may be less than the number of nodes in the output layer, and the number of nodes decreases as the number of nodes progresses from the input layer to the hidden layer. there is. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer may be greater than the number of nodes in the output layer, and the number of nodes increases as the input layer progresses to the hidden layer. can The neural network according to another embodiment of the present disclosure may be a neural network in a combined form of the aforementioned neural networks.

A deep neural network (DNN) may refer to a neural network including a plurality of hidden layers in addition to an input layer and an output layer. Deep neural networks can be used to identify the latent structures of data. In other words, it can identify the potential structure of photos, texts, videos, voices, and music (for example, what objects are in the photos, what the text and emotions are, what the texts and emotions are, etc.) . Deep neural networks include convolutional neural networks (CNNs), recurrent neural networks (RNNs), auto encoders, generative adversarial networks (GANs), and restricted Boltzmann machines (RBMs). boltzmann machine), a deep belief network (DBN), a Q network, a U network, a Siamese network, and the like. The description of the deep neural network described above is only an example, and the present disclosure is not limited thereto.

In an embodiment of the present disclosure, the network function may include an auto-encoder. The auto-encoder may be a kind of artificial neural network for outputting output data similar to input data. The auto encoder may include at least one hidden layer, and an odd number of hidden layers may be disposed between the input/output layers. The number of nodes in each layer may be reduced from the number of nodes of the input layer to an intermediate layer called the bottleneck layer (encoding), and then expanded symmetrically with reduction from the bottleneck layer to the output layer (symmetrically with the input layer). In this case, although the dimensionality reduction layer and the dimension reconstruction layer are illustrated as being symmetrical in the example of FIG. 3 , the present disclosure is not limited thereto, and the nodes of the dimension reduction layer and the dimension reconstruction layer may or may not be symmetrical. The auto-encoder can perform non-linear dimensionality reduction. The number of input layers and output layers may correspond to the number of sensors remaining after pre-processing of input data. In the auto-encoder structure, the number of nodes of the hidden layer included in the encoder may have a structure that decreases as the distance from the input layer increases. If the number of nodes in the bottleneck layer (the layer with the fewest nodes between the encoder and the decoder) is too small, a sufficient amount of information may not be conveyed, so a certain number or more (e.g., more than half of the input layer, etc.) ) may be maintained.

The neural network may be trained by at least one of supervised learning, unsupervised learning, and semi-supervised learning. The training of the neural network is to minimize the error in the output. In the training of a neural network, iteratively inputs the training data to the neural network, calculates the output of the neural network and the target error for the training data, and calculates the error of the neural network from the output layer of the neural network to the input layer in the direction to reduce the error. It is a process of updating the weight of each node in the neural network by backpropagation in the direction. In the case of teacher learning, learning data in which the correct answer is labeled in each learning data is used (ie, labeled learning data), and in the case of comparative learning, the correct answer may not be labeled in each learning data. That is, for example, the learning data in the case of teacher learning regarding data classification may be data in which categories are labeled in each of the learning data. Labeled training data is input to the neural network, and an error can be calculated by comparing the output (category) of the neural network with the label of the training data. As another example, in the case of comparison learning about data classification, an error may be calculated by comparing the input training data with the neural network output. The calculated error is back propagated in the reverse direction (ie, from the output layer to the input layer) in the neural network, and the connection weight of each node of each layer of the neural network may be updated according to the back propagation. A change amount of the connection weight of each node to be updated may be determined according to a learning rate. The computation of the neural network on the input data and the backpropagation of errors can constitute a learning cycle (epoch). The learning rate may be applied differently according to the number of repetitions of the learning cycle of the neural network. For example, in the early stage of training of a neural network, a high learning rate can be used to enable the neural network to quickly acquire a certain level of performance, thereby increasing efficiency, and using a low learning rate at the end of learning can increase accuracy.

In the training of neural networks, in general, the training data may be a subset of real data (that is, data to be processed using the trained neural network), and thus the error on the training data is reduced, but the error on the real data is reduced. There may be increasing learning cycles. Overfitting is a phenomenon in which errors on actual data increase by over-learning on training data as described above. For example, a phenomenon in which a neural network that has learned a cat by showing a yellow cat does not recognize that it is a cat when it sees a cat other than yellow may be a type of overfitting. Overfitting can act as a cause of increasing errors in machine learning algorithms. In order to prevent such overfitting, various optimization methods can be used. In order to prevent overfitting, methods such as increasing training data, regularization, or dropout in which a part of nodes in the network are omitted in the process of learning, may be applied.

A computer-readable medium storing a data structure is disclosed according to an embodiment of the present disclosure.

The data structure may refer to the organization, management, and storage of data that enables efficient access and modification of data. A data structure may refer to an organization of data to solve a specific problem (eg, data retrieval, data storage, and data modification in the shortest time). A data structure may be defined as a physical or logical relationship between data elements designed to support a particular data processing function. The logical relationship between data elements may include a connection relationship between data elements that a user thinks. Physical relationships between data elements may include actual relationships between data elements physically stored on a computer-readable storage medium (eg, a hard disk). A data structure may specifically include a set of data, relationships between data, and functions or instructions applicable to data. Through an effectively designed data structure, a computing device can perform an operation while using the resources of the computing device to a minimum. Specifically, the computing device may increase the efficiency of operations, reads, insertions, deletions, comparisons, exchanges, and retrievals through effectively designed data structures.

A data structure may be classified into a linear data structure and a non-linear data structure according to the type of the data structure. The linear data structure may be a structure in which only one piece of data is connected after one piece of data. The linear data structure may include a list, a stack, a queue, and a deck. A list may mean a set of data in which an order exists internally. The list may include a linked list. The linked list may be a data structure in which data is linked in such a way that each data is linked in a line with a pointer. In a linked list, a pointer may contain information about a link to the next or previous data. A linked list may be expressed as a single linked list, a doubly linked list, or a circularly linked list according to a shape. A stack can be a data enumeration structure with limited access to data. A stack can be a linear data structure in which data can be processed (eg, inserted or deleted) at only one end of the data structure. The data stored in the stack may be a data structure LIFO-Last in First Out. A queue is a data listing structure that allows limited access to data, and unlike a stack, it may be a data structure that comes out later (FIFO-First in First Out) as data stored later. A deck can be a data structure that can process data at either end of the data structure.

The nonlinear data structure may be a structure in which a plurality of data is connected after one data. The nonlinear data structure may include a graph data structure. A graph data structure may be defined as a vertex and an edge, and the edge may include a line connecting two different vertices. A graph data structure may include a tree data structure. The tree data structure may be a data structure in which one path connects two different vertices among a plurality of vertices included in the tree. That is, it may be a data structure that does not form a loop in the graph data structure.

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. (Hereinafter, the neural network is unified and described.) The data structure may include a neural network. And the data structure including the neural network may be stored in a computer-readable medium. Data structures, including neural networks, may also include data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, and loss functions for learning the neural network. there is. A data structure comprising a neural network may include any of the components disclosed above. That is, the data structure including the neural network includes all or all of the data input to the neural network, the weights of the neural network, the hyperparameters of the neural network, the data acquired from the neural network, the activation function associated with each node or layer of the neural network, and the loss function for training the neural network. may be configured including any combination of In addition to the above-described configurations, a data structure including a neural network may include any other information that determines a characteristic of a neural network. In addition, the data structure may include all types of data used or generated in the operation process of the neural network, and is not limited to the above. Computer-readable media may include computer-readable recording media and/or computer-readable transmission media. A neural network may be composed of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is configured by including at least one or more nodes.

The data structure may include data input to the neural network. A data structure including data input to the neural network may be stored in a computer-readable medium. The data input to the neural network may include learning data input in a neural network learning process and/or input data input to the neural network in which learning is completed. Data input to the neural network may include pre-processing data and/or pre-processing target data. The preprocessing may include a data processing process for inputting data into the neural network. Accordingly, the data structure may include data to be pre-processed and data generated by pre-processing. The above-described data structure is merely an example, and the present disclosure is not limited thereto.

The data structure may include the weights of the neural network. (In this specification, a weight and a parameter may be used interchangeably.) And a data structure including a weight of a neural network may be stored in a computer-readable medium. The neural network may include a plurality of weights. The weight may be variable, and may be changed by the user or algorithm in order for the neural network to perform a desired function. For example, when one or more input nodes are interconnected to one output node by respective links, the output node sets values input to input nodes connected to the output node and links corresponding to the respective input nodes. An output node value may be determined based on the parameter. The above-described data structure is merely an example, and the present disclosure is not limited thereto.

By way of example and not limitation, the weight may include a weight variable in a neural network learning process and/or a weight in which neural network learning is completed. The variable weight in the neural network learning process may include a weight at the start of the learning cycle and/or a variable weight during the learning cycle. The weight for which neural network learning is completed may include a weight for which a learning cycle is completed. Accordingly, the data structure including the weight of the neural network may include a data structure including the weight variable in the neural network learning process and/or the weight in which the neural network learning is completed. Therefore, it is assumed that the above-described weights and/or combinations of weights are included in the data structure including the weights of the neural network. The above-described data structure is merely an example, and the present disclosure is not limited thereto.

The data structure including the weights of the neural network may be stored in a computer-readable storage medium (eg, memory, hard disk) after being serialized. Serialization can be the process of converting a data structure into a form that can be reconstructed and used later by storing it on the same or a different computing device. The computing device may serialize the data structure to send and receive data over the network. A data structure including weights of the serialized neural network may be reconstructed in the same computing device or in another computing device through deserialization. The data structure including the weights of the neural network is not limited to serialization. Furthermore, the data structure including the weights of the neural network is a data structure to increase the efficiency of computation while using the resources of the computing device to a minimum (e.g., B-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree). The foregoing is merely an example, and the present disclosure is not limited thereto.

The data structure may include hyper-parameters of the neural network. In addition, the data structure including the hyperparameters of the neural network may be stored in a computer-readable medium. The hyperparameter may be a variable variable by a user. Hyperparameters are, for example, learning rate, cost function, number of iterations of the learning cycle, weight initialization (e.g., setting the range of weight values subject to weight initialization), Hidden Unit The number (eg, the number of hidden layers, the number of nodes of the hidden layer) may be included. The above-described data structure is merely an example, and the present disclosure is not limited thereto.

6 shows a flowchart for performing data processing related to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, the computing device 100 may select a plurality of different data from a data set including data composed of one or more feature groups ( 410 ).

According to an embodiment of the present disclosure, the computing device 100 may transform a portion of each data among a plurality of selected data ( 420 ).

According to an embodiment of the present disclosure, the computing device 100 may assign a label to each of the plurality of transformed data ( 430 ).

According to an embodiment of the present disclosure, the computing device 100 may calculate the transformed data using the model ( 440 ).

The order of the steps illustrated in FIG. 6 described above may be changed if necessary, and at least one or more steps may be omitted or added. That is, the above-described steps are merely embodiments of the present disclosure, and the scope of the present disclosure is not limited thereto.

7 illustrates logic for implementing a method of performing data processing related to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, the computing device 100 may be implemented by the following logic.

According to an embodiment of the present disclosure, the computing device 100 includes a logic 510 for selecting a plurality of different data from a data set including data composed of one or more feature groups, each data of the selected plurality of data. It may include a logic 520 for transforming a part of , a logic 530 for giving a label to each of the plurality of transformed data, and a logic 540 for operating the transformed data using a model.

In an alternative embodiment, the plurality of different data may consist of data included in the same cluster or different clusters.

In alternative embodiments, it may further include logic for clustering the data of the data set to generate a plurality of data subsets.

In an alternative embodiment, the logic for clustering the data of the data set to generate a plurality of data subsets may be performed by a classification model trained using a triple loss based cost function.

In an alternative embodiment, each of the plurality of subsets of data may include a different normal pattern of data.

In an alternative embodiment, the logic for modifying a portion of each data of the selected plurality of data includes logic for changing a value of one of the one or more feature groups of each data. can do.

In an alternative embodiment, the logic for transforming a portion of each data of the selected plurality of data may include logic for exchanging a value of one data of the plurality of data with a value of another data.

In an alternative embodiment, the logic for exchanging a value of one data of the plurality of data with a value of the other data may include: It may contain logic for exchanging values.

In an alternative embodiment, the logic for exchanging a value of one data of the plurality of data with a value of the other data may include logic for exchanging a value of data belonging to the same feature group of each data with each other. .

In an alternative embodiment, the data included in the data set may be normal data.

In an alternative embodiment, the logic for assigning a label to each of the plurality of transformed data may include logic for assigning an abnormal label to each of the plurality of transformed data.

In an alternative embodiment, the logic for calculating the deformed data using the model may include logic for testing the performance of the model by calculating the deformed data using the model.

In an alternative embodiment, the logic for testing the performance of the model by calculating the deformed data using the model tests the performance of the model based on whether the model determines that the deformed data is abnormal. It may contain logic to do this.

In an alternative embodiment, each of the feature groups may be comprised of an associated one of a plurality of items included in the data.

According to an embodiment of the present disclosure, logic for implementing the computing device 100 may be implemented by means, circuits, or modules for implementing a computing program.

Those skilled in the art will further appreciate that the various illustrative logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be combined with electronic hardware, computer software, or combinations of both. It should be recognized that it can be implemented as To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

8 depicts a simplified, general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

Although the present disclosure has been described above generally in the context of computer-executable instructions that may be executed on one or more computers, those skilled in the art will appreciate that the present disclosure may be implemented in combination with other program modules and/or in a combination of hardware and software. will be.

Generally, program modules include routines, procedures, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. In addition, those skilled in the art will appreciate that the methods of the present disclosure can be applied to single-processor or multiprocessor computer systems, minicomputers, mainframe computers as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, etc. (each of which is It will be appreciated that other computer system configurations may be implemented, including operable in conjunction with one or more associated devices.

The described embodiments of the present disclosure may also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

Computers typically include a variety of computer-readable media. Any medium accessible by a computer may be a computer-readable medium, and the computer-readable medium may include a computer-readable storage medium and a computer-readable transmission medium. Such computer-readable storage media includes volatile and nonvolatile media, removable and non-removable media. Computer readable storage media includes volatile and nonvolatile media, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. A computer-readable storage medium may be RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage device, magnetic cassette, magnetic tape, magnetic disk storage device, or other magnetic storage device. device, or any other medium that can be accessed by a computer and used to store the desired information.

Computer-readable transmission media typically embody computer-readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave or other transport mechanism. information delivery media. The term modulated data signal means a signal in which one or more of the characteristics of the signal is set or changed so as to encode information in the signal. By way of example, and not limitation, computer-readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above are also intended to be included within the scope of computer-readable transmission media.

An example environment 1100 implementing various aspects of the disclosure is shown including a computer 1102 , the computer 1102 including a processing unit 1104 , a system memory 1106 , and a system bus 1108 . do. A system bus 1108 couples system components, including but not limited to system memory 1106 , to the processing device 1104 . The processing device 1104 may be any of a variety of commercially available processors. Dual processor and other multiprocessor architectures may also be used as processing unit 1104 .

The system bus 1108 may be any of several types of bus structures that may further interconnect a memory bus, a peripheral bus, and a local bus using any of a variety of commercial bus architectures. System memory 1106 includes read only memory (ROM) 1110 and random access memory (RAM) 1112 . A basic input/output system (BIOS) is stored in non-volatile memory 1110, such as ROM, EPROM, EEPROM, etc., which is the basic input/output system (BIOS) that helps transfer information between components within computer 1102, such as during startup. contains routines. RAM 1112 may also include high-speed RAM, such as static RAM, for caching data.

The computer 1102 may also be configured with an internal hard disk drive (HDD) 1114 (eg, EIDE, SATA) - this internal hard disk drive 1114 may also be configured for external use within a suitable chassis (not shown). Yes—a magnetic floppy disk drive (FDD) 1116 (eg, for reading from or writing to removable diskette 1118), and an optical disk drive 1120 (eg, a CD-ROM) for reading from, or writing to, disk 1122, or other high capacity optical media such as DVD. The hard disk drive 1114 , the magnetic disk drive 1116 , and the optical disk drive 1120 are connected to the system bus 1108 by the hard disk drive interface 1124 , the magnetic disk drive interface 1126 , and the optical drive interface 1128 , respectively. ) can be connected to The interface 1124 for implementing an external drive includes at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

These drives and their associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, and the like. In the case of computer 1102, drives and media correspond to storing any data in a suitable digital format. Although the description of computer readable media above refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those skilled in the art will use zip drives, magnetic cassettes, flash memory cards, cartridges, etc. It will be appreciated that other tangible computer-readable media such as etc. may also be used in the exemplary operating environment and any such media may include computer-executable instructions for performing the methods of the present disclosure.

A number of program modules may be stored in the drive and RAM 1112 , including an operating system 1130 , one or more application programs 1132 , other program modules 1134 , and program data 1136 . All or portions of the operating system, applications, modules, and/or data may also be cached in RAM 1112 . It will be appreciated that the present disclosure may be implemented in various commercially available operating systems or combinations of operating systems.

A user may enter commands and information into the computer 1102 via one or more wired/wireless input devices, for example, a pointing device such as a keyboard 1138 and a mouse 1140 . Other input devices (not shown) may include a microphone, IR remote control, joystick, game pad, stylus pen, touch screen, and the like. Although these and other input devices are often connected to the processing unit 1104 through an input device interface 1142 that is connected to the system bus 1108, parallel ports, IEEE 1394 serial ports, game ports, USB ports, IR interfaces, It may be connected by other interfaces, etc.

A monitor 1144 or other type of display device is also coupled to the system bus 1108 via an interface, such as a video adapter 1146 . In addition to the monitor 1144, the computer typically includes other peripheral output devices (not shown), such as speakers, printers, and the like.

Computer 1102 may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) 1148 via wired and/or wireless communications. Remote computer(s) 1148 may be workstations, server computers, routers, personal computers, portable computers, microprocessor-based entertainment devices, peer devices, or other common network nodes, and are generally Although including many or all of the components described, only memory storage device 1150 is shown for simplicity. The logical connections shown include wired/wireless connections to a local area network (LAN) 1152 and/or a larger network, eg, a wide area network (WAN) 1154 . Such LAN and WAN networking environments are common in offices and companies, and facilitate enterprise-wide computer networks, such as intranets, all of which can be connected to a worldwide computer network, for example, the Internet.

When used in a LAN networking environment, the computer 1102 is connected to the local network 1152 through a wired and/or wireless communication network interface or adapter 1156 . Adapter 1156 may facilitate wired or wireless communication to LAN 1152 , which also includes a wireless access point installed therein for communicating with wireless adapter 1156 . When used in a WAN networking environment, the computer 1102 may include a modem 1158 , connected to a communication server on the WAN 1154 , or otherwise establishing communications over the WAN 1154 , such as over the Internet. have the means A modem 1158 , which may be internal or external and a wired or wireless device, is coupled to the system bus 1108 via a serial port interface 1142 . In a networked environment, program modules described for computer 1102 , or portions thereof, may be stored in remote memory/storage device 1150 . It will be appreciated that the network connections shown are exemplary and other means of establishing a communication link between the computers may be used.

Computer 1102 may be associated with any wireless device or object that is deployed and operates in wireless communication, for example, printers, scanners, desktop and/or portable computers, portable data assistants (PDAs), communications satellites, wireless detectable tags. It operates to communicate with any device or place, and phone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, the communication may be a predefined structure as in a conventional network or may simply be an ad hoc communication between at least two devices.

Wi-Fi (Wireless Fidelity) makes it possible to connect to the Internet, etc. without a wire. Wi-Fi is a wireless technology such as cell phones that allows these devices, eg, computers, to transmit and receive data indoors and outdoors, ie anywhere within range of a base station. Wi-Fi networks use a radio technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks may operate in unlicensed 2.4 and 5 GHz radio bands, for example, at 11 Mbps (802.11a) or 54 Mbps (802.11b) data rates, or in products that include both bands (dual band). there is.

Those of ordinary skill in the art of the present disclosure will recognize that the various illustrative logical blocks, modules, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein include electronic hardware, (convenience For this purpose, it will be understood that it may be implemented by various forms of program or design code (referred to herein as "software") or a combination of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. A person skilled in the art of the present disclosure may implement the described functionality in various ways for each specific application, but such implementation decisions should not be interpreted as a departure from the scope of the present disclosure.

The various embodiments presented herein may be implemented as methods, apparatus, or articles of manufacture using standard programming and/or engineering techniques. The term “article of manufacture” includes a computer program, carrier, or media accessible from any computer-readable device. For example, computer-readable media include magnetic storage devices (eg, hard disks, floppy disks, magnetic strips, etc.), optical disks (eg, CDs, DVDs, etc.), smart cards, and flash memory. devices (eg, EEPROMs, cards, sticks, key drives, etc.). Also, various storage media presented herein include one or more devices and/or other machine-readable media for storing information. The term “machine-readable medium” includes, but is not limited to, wireless channels and various other media capable of storing, holding, and/or carrying instruction(s) and/or data.

It is to be understood that the specific order or hierarchy of steps in the presented processes is an example of exemplary approaches. Based on design priorities, it is understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of the present disclosure. The appended method claims present elements of the various steps in a sample order, but are not meant to be limited to the specific order or hierarchy presented.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure is not intended to be limited to the embodiments presented herein, but is to be construed in the widest scope consistent with the principles and novel features presented herein.

Claims (1)

A computer program stored in a computer-readable storage medium, wherein the computer program performs the following operations for data processing when executed on one or more processors of a computer device.

Images