Gas Data Abnormality Detection Method and Device

Abstract

The present application proposes a gas data anomaly detection method and device. The method includes: obtaining a gas data set to be detected; performing granularity division on the gas data set based on the joint information entropy calculated from the gas data set to determine the granularity identifier to which each gas data in the gas data set belongs; extracting features from multiple gas data belonging to the same granularity identifier to determine the corresponding target features; according to the target features corresponding to multiple gas data belonging to various granularity identifiers, passing through a pre-trained gas anomaly detection model to determine an anomaly probability value sequence corresponding to the gas data set; wherein, each anomaly probability value in the anomaly probability value sequence is used to indicate the probability of gas data anomaly occurring in the corresponding gas data in the gas data set. Thus, it is not necessary to consume a large amount of time cost for pre-labeling the gas data, and the accuracy and reliability of the gas anomaly detection model are improved.

Description

Technical Field

[0001] This application relates to the field of computer technologies, and in particular, to a method and apparatus for detecting abnormal gas data. Background Art

[0002] As a highly dangerous gas, in actual scenarios, the dynamic changes of gas are directly related to the safe production of the entire coal mine exploitation. The abnormal accumulation of gas may not only lead to gas explosions, causing significant casualties and property losses, but also trigger other serious safety accidents such as gas outbursts. Therefore, accurate and efficient abnormal detection of gas data has always been one of the core tasks in coal mine safety protection work.

[0003] In related technologies, a machine learning model is usually established to detect gas data. However, in actual working scenarios, the gas data collected is often affected by multi-factor environments and does not exhibit the characteristics of an ideal linear distribution. Subsequently, when using a machine learning model to detect abnormal gas data, it will affect the accuracy of the machine learning model in detecting abnormal gas data. Summary of the Invention

[0004] This application aims to solve at least one of the technical problems in the related technologies to some extent.

[0005] To this end, the first object of this application is to propose a method for detecting abnormal gas data, so as to provide high-quality gas data for the gas abnormal detection model, and greatly improve the accuracy and reliability of the gas abnormal detection model.

[0006] The second object of this application is to propose an apparatus for detecting abnormal gas data.

[0007] The third object of this application is to propose an electronic device.

[0008] The fourth object of this application is to propose a computer-readable storage medium.

[0009] The fifth object of this application is to propose a computer program product.

[0010] To achieve the above object, an embodiment of the first aspect of the present application provides a gas data anomaly detection method, including: obtaining a gas data set to be detected; wherein, the gas data set includes a plurality of gas data collected within at least one time period in the mining area to be detected; based on the joint information entropy calculated from the gas data set, performing granularity division on the gas data set to determine the granularity identifier to which each gas data in the gas data set belongs; for any plurality of gas data belonging to the same type of granularity identifier, performing feature extraction on the plurality of gas data belonging to the same type of granularity identifier to determine at least one target feature corresponding to the plurality of gas data belonging to the same type of granularity identifier; according to the target features corresponding to the plurality of gas data belonging to each type of granularity identifier in the gas data set, through a pre-trained gas anomaly detection model, to determine an anomaly probability value sequence corresponding to the gas data set; wherein, each anomaly probability value in the anomaly probability value sequence is used to indicate the probability that the corresponding gas data in the gas data set has a gas data anomaly.

[0011] To achieve the above object, an embodiment of the second aspect of the present application provides a gas data anomaly detection device, including: a first acquisition module, configured to obtain a gas data set to be detected; wherein, the gas data set includes a plurality of gas data collected within at least one time period in the mining area to be detected; a granularity division module, configured to perform granularity division on the gas data set based on the joint information entropy calculated from the gas data set to determine the granularity identifier to which each gas data in the gas data set belongs; a first determination module, configured to, for any plurality of gas data belonging to the same type of granularity identifier, perform feature extraction on the plurality of gas data belonging to the same type of granularity identifier to determine at least one target feature corresponding to the plurality of gas data belonging to the same type of granularity identifier; a second determination module, configured to, according to the target features corresponding to the plurality of gas data belonging to each type of granularity identifier in the gas data set, through a pre-trained gas anomaly detection model, to determine an anomaly probability value sequence corresponding to the gas data set; wherein, each anomaly probability value in the anomaly probability value sequence is used to indicate the probability that the corresponding gas data in the gas data set has a gas data anomaly.

[0012] To achieve the above object, an embodiment of the third aspect of the present application provides an electronic device, including: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the gas data anomaly detection method disclosed in the embodiments of the present application.

[0013] To achieve the above object, an embodiment of the fourth aspect of the present application provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the gas data anomaly detection method disclosed in the embodiments of the present application when executed by a processor.

[0014] To achieve the above object, an embodiment of the fifth aspect of the present application provides a computer program product, including a computer program, which implements the gas data anomaly detection method disclosed in the embodiments of the present application when executed by a processor.

[0015] The gas data anomaly detection method and device provided by the present application obtain a gas data set to be detected; wherein, the gas data set includes a plurality of gas data collected within at least one time period in the mining area to be detected; based on the joint information entropy calculated from the gas data set, the gas data set is partitioned by granularity to determine the granularity identifier to which each gas data in the gas data set belongs; for any plurality of gas data belonging to the same granularity identifier, feature extraction is performed on the plurality of gas data belonging to the same granularity identifier to determine at least one target feature corresponding to the plurality of gas data belonging to the same granularity identifier; according to the target features corresponding to the plurality of gas data belonging to each granularity identifier in the gas data set, through a pre-trained gas anomaly detection model, an anomaly probability value sequence corresponding to the gas data set is determined; wherein, each anomaly probability value in the anomaly probability value sequence is used to indicate the probability that the corresponding gas data in the gas data set has a gas data anomaly. Thus, before determining the probability that the gas data in the gas data set has a gas data anomaly through the gas anomaly detection model, not only are various factors that affect the occurrence of abnormal gas data in the actual working scenario comprehensively considered, but also the non-linear characteristics presented by the distribution of the plurality of gas data in the gas data set are considered. Therefore, the gas data set is comprehensively partitioned by granularity not only from the perspective of the local fluctuations of the gas data, but also from the perspective of the macroscopic trend of the gas data. Furthermore, by using the gas data belonging to each granularity identifier, through the gas anomaly detection model, the probability of gas data anomaly can be determined without consuming a large amount of time cost for pre-labeling the gas data, which can provide high-quality gas data for the gas anomaly detection model and greatly improve the accuracy and reliability of the gas anomaly detection model.

[0016] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. Description of the Drawings

[0017] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of the embodiments in conjunction with the drawings, where:

[0018] Figure 1 Flow schematic of a gas data anomaly detection method provided by an embodiment of the present application Figure 1 ;

[0019] Figure 2 Flow schematic of a gas data anomaly detection method provided by an embodiment of the present application Figure 2 ;

[0020] Figure 3 Flow example of a gas data anomaly detection method provided by an embodiment of the present application Figure 3 ;

[0021] Figure 4 Flow schematic of a gas data anomaly detection method provided by an embodiment of the present application Figure 4 ;

[0022] Figure 5 Schematic diagram of the framework corresponding to the gas data anomaly detection process provided by an embodiment of the present application;

[0023] Figure 6 Architecture diagram of the gas anomaly detection model provided by an embodiment of the present application;

[0024] Figure 7 Schematic diagram of the structure of a gas data anomaly detection device provided by an embodiment of the present application;

[0025] Figure 8 Schematic diagram of the structure of the electronic device provided by an embodiment of the present application. Detailed implementation manners

[0026] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application, and should not be construed as limiting the present application.

[0027] The technical solutions of the present application and how the technical solutions of the present application solve the above technical problems will be described in detail below with specific embodiments. These several specific embodiments may be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below with reference to the accompanying drawings.

[0028] Figure 1 Flow schematic of a gas data anomaly detection method provided by an embodiment of the present application Figure 1 .

[0029] Step 101: Obtain the gas dataset to be detected; among them, the gas dataset includes multiple gas data collected within at least one time period in the mining area to be detected.

[0030] It should be noted that the gas data anomaly detection method provided in the embodiments of the present application can be executed by a gas data anomaly detection device (which can also be called a gas data anomaly detector), where the gas data anomaly detection device can be implemented by software and / or hardware. The gas data anomaly detection device can be an electronic device or can be configured in an electronic device to implement the gas data anomaly detection function.

[0031] In the embodiments of the present application, the gas data anomaly detection method is configured in an electronic device as an example for illustration.

[0032] The electronic device can be any device with computing capabilities, such as a personal computer, a mobile terminal, a server, etc. The mobile terminal can be a hardware device with various operating systems, touch screens, and / or displays, such as a vehicle-mounted device, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, etc.

[0033] It should be noted that the specific information of the mining area to be detected and the specific number of mining areas are determined according to the actual situation, and no specific limitation is made in this embodiment. For example, the mining areas to be detected can be coal mine mining area A and coal mine mining area B.

[0034] It should be noted that the specific information of the time period is determined according to actual needs, and no specific limitation is made in this embodiment. For example, a time period in the mining area to be detected can be the entire time period in February 2024 in coal mine mining area A.

[0035] It should be understood that in order to ensure the stability of the production environment during the mining process, the collection of gas data is a long-term and continuous process. The detection of gas data is not only to detect the gas data at a certain moment, but also to detect the overall fluctuation trend of the gas data at each moment within a period of time. Therefore, the gas data at each moment within different time periods can be collected, and then the gas dataset can be determined.

[0036] Step 102: Perform granularity partitioning on the gas dataset based on the joint information entropy calculated from the gas dataset to determine the granularity identifier to which each gas data in the gas dataset belongs.

[0037] It should be understood that since each gas data in the gas data set has diverse characteristics at different times and in different environments. For example, even in the same mining environment, the gas data collected at different times is not the same. Therefore, in order to distinguish the characteristics presented by each gas data at different times and in different environments, each gas data can be distinguished, and from the gas data set, the gas data that significantly affects the overall change trend of the gas data and the gas data that significantly affects the local change of the gas data can be determined.

[0038] Step 103: For any multiple gas data belonging to the same class of granularity identifiers, perform feature extraction on the multiple gas data belonging to the same class of granularity identifiers to determine at least one target feature corresponding to the multiple gas data belonging to the same class of granularity identifiers.

[0039] It should be noted that the target features extracted from the gas data under different classes of granularity identifiers are not the same.

[0040] It should be understood that since the gas data in the actual production environment is affected by various factors, in order to better perform anomaly detection on the gas data and adapt to the changes of the gas data even under complex working conditions, the granularity identifier to which the gas data belongs can well reflect which aspect of the gas data is representative in terms of long-term trend and local fluctuation during the subsequent anomaly detection process. Thus, according to different working conditions and environments, the granularity identifier suitable for the working condition environment can be determined, and then, focus on the gas data belonging to the granularity identifier suitable for the working condition environment.

[0041] Step 104: According to the target features corresponding to the multiple gas data belonging to each class of granularity identifiers in the gas data set, through a pre-trained gas anomaly detection model, determine the anomaly probability value sequence corresponding to the gas data set.

[0042] It should be noted that each anomaly probability value in the anomaly probability value sequence is used to indicate the probability of gas data anomaly occurring for the corresponding gas data in the gas data set.

[0043] For example, the abnormal probability value is in the range of (0, 1). Suppose the abnormal probability value sequence includes two abnormal probability values, A (0.9) and B (0.1). Among them, the abnormal probability value A is used to indicate the probability of abnormal gas data corresponding to gas data A in the gas dataset, and the abnormal probability value B is used to indicate the probability of abnormal gas data corresponding to gas data B in the gas dataset. Then, it can be detected that there is a 90% probability of abnormal gas data for gas data A. In the actual scenario, it is more inclined to consider that gas data A belongs to an abnormal situation and needs to be focused on; there is a 10% probability of abnormal gas data for gas data B. In the actual scenario, it is more inclined to consider that gas data B belongs to a normal situation.

[0044] It should be understood that the determined abnormal probability value sequence is a quantitative representation of the possibility of each gas data in the gas dataset being abnormal. However, in the actual application scenario, the abnormal probability value cannot intuitively reflect whether the gas data is abnormal. The abnormal probability value can be further determined to more clearly understand the data state of the gas data.

[0045] In order to intuitively reflect whether the gas data is abnormal, as a possible implementation, it is determined whether the abnormal probability value corresponding to each gas data exceeds the abnormal threshold to determine the data state of the gas data.

[0046] As an example, for each gas data in the gas dataset, it is determined whether the abnormal probability value corresponding to the gas data exceeds the abnormal threshold to determine the data state of the gas data.

[0047] In some examples, if the abnormal probability value corresponding to the gas data exceeds the abnormal threshold, the data state of the gas data is determined to be an abnormal state; if the abnormal probability value corresponding to the gas data is less than the abnormal threshold, the data state of the gas data is determined to be a normal state.

[0048] Among them, it should be noted that the specific value of the abnormal threshold is determined according to the actual situation and is not specifically limited in this embodiment. For example, 0.5 can be set as the abnormal threshold. If the abnormal probability value corresponding to the gas data exceeds 0.5, the data state of the gas data is an abnormal state; if the abnormal probability value corresponding to the gas data is less than 0.5, the data state of the gas data is determined to be a normal state.

[0049] The gas data anomaly detection method provided in the embodiment of the present application obtains a gas data set to be detected; wherein the gas data set includes multiple gas data collected within at least one time period of the mining area to be detected; based on the joint information entropy calculated from the gas data set, the gas data set is granularized to determine the granularity identification to which each gas data in the gas data set belongs; for any multiple gas data belonging to the same type of granularity identification, feature extraction is performed on the multiple gas data belonging to the same type of granularity identification to determine at least one target feature corresponding to the multiple gas data belonging to the same type of granularity identification; according to the target features corresponding to the multiple gas data belonging to each type of granularity identification in the gas data set, a pre-trained gas anomaly detection model is used to determine the abnormal probability value sequence corresponding to the gas data set; wherein each abnormal probability value in the abnormal probability value sequence is used to indicate the gas data. The probability of gas data anomalies occurring in the corresponding gas data in the gas data set is determined by the gas anomaly detection model. Therefore, before determining the probability of gas data anomalies occurring in the gas data set through the gas anomaly detection model, not only the various factors that may affect the abnormal situation of gas data in the actual working scenario are comprehensively considered, but also the nonlinear characteristics of the distribution of multiple gas data in the gas data set are considered. Therefore, the gas data set is comprehensively divided into granularities not only from the perspective of local fluctuations of gas data but also from the perspective of the macro trend of gas data. Then, based on the gas data belonging to various granularity labels, the probability of gas data anomalies is determined through the gas anomaly detection model. Without consuming a lot of time cost, the gas data can be pre-labeled to provide high-quality gas data for the gas anomaly detection model, which greatly improves the accuracy and reliability of the gas anomaly detection model.

[0050] In the embodiment of the present application, in order to make it clear how to calculate the joint information entropy based on the gas data set, the gas data set is divided into granularities to determine the granularity identifier to which each gas data in the gas data set belongs, the following is combined with Figure 2 A possible implementation manner of determining a granularity identifier to which each gas data in a gas data set belongs is described by way of example. Figure 2 The process of the gas data anomaly detection method provided in the embodiment of the present application Figure 2 .

[0051] like Figure 2 As shown, the gas data anomaly detection method may include the following steps:

[0052] Step 201 , obtaining a gas data set to be detected; wherein the gas data set includes a plurality of gas data collected within at least one time period in the mining area to be detected.

[0053] It should be noted that the execution process of step 201 can be implemented in any way in each embodiment of the present application. The embodiments of the present application do not make any limitations in this regard and will not be elaborated further.

[0054] Step 202, obtain the preset number of time steps and the feature dimension.

[0055] It should be noted that the granularity identifier includes but is not limited to a coarse-grained identifier, a medium-grained identifier, and a fine-grained identifier.

[0056] It should be understood that for the gas data under the coarse-grained identifier, what is concerned is the aspect of detecting whether there are abnormalities in the long-term trend of the gas data, so as to grasp the macroscopic trend of the gas data in the gas data set; for the gas data under the fine-grained identifier, what is concerned is the aspect of detecting whether there are abnormalities in the short-term fluctuations and local details of the gas data, so as to capture the local abnormal changes of the gas data in the gas data set; for the gas data under the medium-grained identifier, the aspect of the gas data concerned about abnormalities is between the gas data under the coarse-grained identifier and the gas data under the fine-grained identifier.

[0057] It should be noted that the specific value of the number of time steps is determined according to the actual situation, and no specific limitation is made in this embodiment.

[0058] It should be noted that the specific information of the feature dimension is determined according to the existing technology and the experience of relevant staff, and no specific limitation is made in this embodiment.

[0059] It should be understood that the gas data is comprehensively affected by many complex factors such as geological structure, ventilation conditions, and mining technology. For the gas data under different granularity identifiers, the aspects concerned about detecting gas data abnormalities are different, and for the gas data under different granularity identifiers, the concerned features are also different.

[0060] For example, for the gas data belonging to the coarse-grained identifier, the concerned feature can be the gas concentration; for the gas data belonging to the fine-grained identifier, the concerned features can be the gas concentration, temperature, and humidity.

[0061] Step 203, for any gas data, determine the joint information entropy corresponding to the gas data according to the number of time steps and the feature dimension.

[0062] For example, determining the joint information entropy corresponding to the gas data can be expressed by the formula:

[0063] ;

[0064] where the gas data set , N represents the number of gas data in the gas dataset; T represents the number of time steps, and F represents the feature dimension; for each gas data represents the joint information entropy; is the probability that the f-th eigenvalue appears at the t-th time step in the i-th gas data, obtained by counting all time steps and eigenvalues in the i-th gas data, that is , is the number of times the f-th eigenvalue appears at the t-th time step in the i-th gas data.

[0065] Step 204, determine whether the joint information entropy corresponding to each gas data is greater than the first information entropy threshold or not greater than the second information entropy threshold to determine the granularity identifier to which each gas data belongs; wherein, the first information entropy threshold is greater than the second information entropy threshold.

[0066] It should be noted that the specific value of the first information entropy threshold and the specific value of the second information entropy threshold can be determined according to the actual situation, and no specific limitation is made in this embodiment.

[0067] For example, it can be found by dividing the historical gas data that when the first information entropy threshold is 0.6 and the second information entropy threshold is 0.3, each gas data can be clearly distinguished, so the first information entropy threshold can be set to 0.6 and the second information entropy threshold can be set to 0.3.

[0068] As an example, for the joint information entropy corresponding to each gas data, if the joint information entropy is greater than the first information entropy threshold, determine that the granularity identifier to which the gas data belongs is the coarse granularity identifier; if the joint information entropy is not greater than the second information entropy threshold, determine that the granularity identifier to which the gas data belongs is the fine granularity identifier; if the joint information entropy is not greater than the first information entropy threshold and greater than the second information entropy threshold, determine that the granularity identifier to which the gas data belongs is the medium granularity identifier.

[0069] For example, set the first information entropy threshold and the second information entropy threshold ( 】> )), perform granularity division according to the joint information entropy of the gas data: if , divide the gas data into the gas data belonging to the fine granularity identifier; if , divide the gas data into the gas data belonging to the medium granularity identifier; if , divide the gas data into the gas data belonging to the coarse granularity identifier.

[0070] Step 205: For multiple gas data belonging to the same class of granularity identifiers, perform feature extraction on the multiple gas data belonging to the same class of granularity identifiers to determine at least one target feature corresponding to the multiple gas data belonging to the same class of granularity identifiers.

[0071] Step 206: According to the target features corresponding to the multiple gas data belonging to each class of granularity identifiers in the gas data set, use a pre-trained gas anomaly detection model to determine the sequence of anomaly probability values corresponding to the gas data set.

[0072] It should be noted that the execution processes of Step 205 and Step 206 can be implemented in any one of the embodiments of the present application respectively. The embodiments of the present application do not make any limitations in this regard and will not be elaborated further.

[0073] The gas data anomaly detection method provided by the embodiments of the present application obtains a preset number of time steps and feature dimensions; for any gas data, according to the number of time steps and the feature dimensions, determine the joint information entropy corresponding to the gas data; determine the granularity identifier to which each gas data belongs by judging whether the joint information entropy corresponding to each gas data is greater than the first information entropy threshold or not greater than the second information entropy threshold; wherein, the first information entropy threshold is greater than the second information entropy threshold. Thus, by using the joint information entropy corresponding to the gas data to divide the gas data set, considering that the gas data is affected by many complex factors, from the perspectives of two major categories, namely macroscopic and local, multi-granularity analysis of the gas data is carried out, laying a foundation for accurately detecting gas data anomalies subsequently, avoiding information omission and misjudgment caused by single-granularity analysis, and deepening the understanding of gas data.

[0074] In the embodiments of the present application, in order to clearly understand the process of performing feature extraction on multiple gas data belonging to the same class of granularity identifiers to determine at least one target feature corresponding to the multiple gas data belonging to the same class of granularity identifiers, the following is combined with Figure 3 An exemplary description is given of a possible implementation manner for determining at least one target feature corresponding to the multiple gas data belonging to the same class of granularity identifiers. Figure 3 The flow of the gas data anomaly detection method provided by the embodiments of the present application Figure 3 .

[0075] As Figure 3 shown, the gas data anomaly detection method may include the following steps:

[0076] Step 301: Obtain a gas data set to be detected; wherein, the gas data set includes multiple gas data collected within at least one time period in the mining area to be detected.

[0077] Step 302: Based on the joint information entropy calculated from the gas dataset, perform granularity division on the gas dataset to determine the granularity identifier to which each gas data in the gas dataset belongs.

[0078] It should be noted that the execution processes of Step 301 and Step 302 can be implemented in any of the ways in the various embodiments of the present application. The embodiments of the present application do not make any limitations in this regard and will not be elaborated further.

[0079] Step 303: According to the target granularity identifier to which multiple gas data belonging to the same class of granularity identifiers belong, determine the target feature extraction method corresponding to the target granularity identifier through a preset mapping table of granularity identifiers and feature extraction methods.

[0080] Among them, it should be noted that the mapping table of granularity identifiers and feature extraction methods includes various granularity identifiers and corresponding feature extraction methods.

[0081] For example, the mapping table of granularity identifiers and feature extraction methods is shown in Table 1. In Table 1, there are coarse granularity identifiers, medium granularity identifiers, and fine granularity identifiers. The coarse granularity identifier has a mapping relationship with the principal component analysis method, the medium granularity identifier has a mapping relationship with the wavelet transform method, and the fine granularity identifier has a mapping relationship with the wavelet transform method. Assuming that the target granularity identifier is the fine granularity identifier, then according to the mapping table of granularity identifiers and feature extraction methods, determine that the target feature extraction method corresponding to the target granularity identifier (fine granularity identifier) is the wavelet transform method. Based on the target feature extraction method (wavelet transform method), perform feature extraction on multiple gas data belonging to the same class of granularity identifiers to determine the target features corresponding to multiple gas data belonging to the same class of granularity identifiers.

[0082] Table 1 Mapping Table of Granularity Identifiers and Feature Extraction Methods

[0083]

[0084] Step 304: Based on the target feature extraction method, perform feature extraction on multiple gas data belonging to the same class of granularity identifiers to determine the target features corresponding to multiple gas data belonging to the same class of granularity identifiers.

[0085] It should be understood that for gas data belonging to different classes of granularity identifiers, the directions in which gas data anomalies are detected are different. Therefore, granularity identifiers are not easily understood directly by a computer. In order for the gas anomaly detection model to quickly analyze the granularity identifier to which gas data belongs, one-hot encoding can be performed on the granularity identifier.

[0086] As an example, various granularity identifiers are obtained; for each type of granularity identifier, one-hot encoding is performed on the granularity identifier to determine the one-hot encoding vector corresponding to the granularity identifier; based on the one-hot encoding vectors corresponding to various granularity identifiers, the one-hot encoding vector associated with the gas data is determined; according to the one-hot encoding vectors associated with each gas data, the one-hot encoding vector matrix corresponding to the gas data set is determined.

[0087] For example, for one-hot encoding of the granularity identifier, for each gas data in the gas data set , its granularity identifier is ( ), then the one-hot encoding vector corresponding to the gas data satisfies , and the one-hot encoding vectors of all gas data in the gas data set form a matrix .

[0088] Among them, it should be noted that represents the maximum granularity identifier; N represents the number of gas data in the gas data set.

[0089] Step 305, according to the target features corresponding to multiple gas data belonging to each type of granularity identifier in the gas data set, through a pre-trained gas anomaly detection model, to determine the sequence of anomaly probability values corresponding to the gas data set.

[0090] In order to determine the sequence of anomaly probability values corresponding to the gas data set, as a possible implementation, according to the one-hot encoding vector matrix and the target features corresponding to multiple gas data belonging to each type of granularity identifier, through the gas anomaly detection model, the sequence of anomaly probability values corresponding to the gas data set is determined.

[0091] As an example, according to the one-hot encoding vector matrix corresponding to the gas data set, determine the granularity identifier to which each of the multiple gas data in the gas data set belongs; according to the target features corresponding to multiple gas data belonging to each type of granularity identifier in the gas data set, determine the target features associated with each type of granularity identifier; input the target features associated with each type of granularity identifier into the gas anomaly detection model to determine the sequence of anomaly probability values corresponding to the gas data set.

[0092] The gas data anomaly detection method provided by the embodiments of the present application determines the target feature extraction method corresponding to the target granularity identifier according to the target granularity identifier to which multiple gas data under the same type of granularity identifier belong, through a preset mapping relationship table between the granularity identifier and the feature extraction method; based on the target feature extraction method, feature extraction is performed on multiple gas data under the same type of granularity identifier to determine the target features corresponding to multiple gas data under the same type of granularity identifier. Thus, through the mapping relationship table between the granularity identifier and the feature extraction method, the target feature extraction method corresponding to the target granularity identifier is determined. Therefore, by focusing on the granularity identifier, a suitable feature extraction method for gas data can be quickly determined, and through the suitable feature extraction method, the target features corresponding to the gas data can be completely extracted.

[0093] Figure 4 It is a flow schematic diagram of a gas data anomaly detection method provided by the embodiments of the present application Figure 4 。

[0094] As Figure 4 shown, the gas data anomaly detection method may include the following steps:

[0095] Step 401, obtain a historical gas data set and an actual anomaly probability value sequence corresponding to the historical gas data set.

[0096] Among them, it should be noted that the historical gas data set includes multiple historical gas data collected in at least one historical time period in the detected mining area; each actual anomaly probability value in the actual anomaly probability value sequence is used to indicate the probability of gas data anomaly occurring in the corresponding historical gas data in the historical gas data set.

[0097] Step 402, perform granularity division on the historical gas data set based on the joint information entropy calculated from the historical gas data set to determine the granularity identifier to which each historical gas data in the historical gas data set belongs.

[0098] Step 403, for any multiple historical gas data under the same type of granularity identifier, perform feature extraction on the multiple historical gas data under the same type of granularity identifier to determine the historical target features corresponding to the multiple historical gas data under the same type of granularity identifier.

[0099] Among them, it should be noted that for the specific descriptions of steps 401 - 403, reference can be made to other descriptions of this embodiment, which will not be elaborated here.

[0100] Step 404, determine a trained gas anomaly detection model according to the historical target features corresponding to multiple historical gas data under each type of granularity identifier in the historical gas data set and the actual anomaly probability value sequence corresponding to the historical gas data set.

[0101] In some embodiments, historical target features corresponding to multiple historical gas data under various granularity identifications in a historical gas dataset are input into an initial gas anomaly detection model to determine an anomaly probability value sequence corresponding to the historical gas dataset; the initial gas anomaly detection model is trained according to the anomaly probability value sequence corresponding to the historical gas dataset and the actual anomaly probability value sequence to determine a trained gas anomaly detection model.

[0102] In this embodiment, a historical gas dataset and an actual anomaly probability value sequence corresponding to the historical gas dataset are obtained; based on the joint information entropy calculated from the historical gas dataset, the historical gas dataset is granulated to determine the granularity identification to which each historical gas data in the historical gas dataset belongs; for any multiple historical gas data belonging to the same granularity identification, feature extraction is performed on the multiple historical gas data belonging to the same granularity identification to determine the historical target features corresponding to the multiple historical gas data belonging to the same granularity identification; according to the historical target features corresponding to the multiple historical gas data under various granularity identifications in the historical gas dataset and the actual anomaly probability value sequence corresponding to the historical gas dataset, a trained gas anomaly detection model is determined. Thus, by the difference between the anomaly probability value sequence corresponding to the historical gas dataset and the actual anomaly probability value sequence, the gas anomaly detection model is continuously trained, greatly improving the accuracy of the gas anomaly detection model in detecting gas data anomalies.

[0103] For example, the schematic framework diagram corresponding to the gas data anomaly detection process is as Figure 5 shown. Input X (gas dataset), calculate X to determine the joint information entropy corresponding to each gas data in the gas dataset, and based on the joint information entropy corresponding to each gas data, perform multi-granularity dynamic partitioning on the gas dataset to determine the granularity identification to which each gas data belongs, perform feature extraction on each gas data to determine the target feature Y1 corresponding to the gas data belonging to the coarse granularity identification, the target feature Y2 corresponding to the gas data belonging to the medium granularity identification, and the target feature Y3 corresponding to the gas data belonging to the fine granularity identification, and input Y1, Y2, and Y3 into the gas anomaly detection model to determine the anomaly probability value sequence corresponding to the gas dataset.

[0104] It should be understood that since for the gas data belonging to the medium granularity identification and the gas data belonging to the fine granularity identification, what is concerned is the possibility of whether anomalies occur in the subtle aspects of the gas data. Therefore, in order to efficiently detect anomalies in the subtle data of the gas data based on the gas anomaly detection model in the subsequent stage, the correlation between multiple gas data belonging to the same granularity identification can be strengthened.

[0105] In some embodiments, obtain a first clustering algorithm corresponding to gas data belonging to a medium-grained identifier; obtain a second clustering algorithm corresponding to gas data belonging to a fine-grained identifier; based on the first clustering algorithm, cluster multiple gas data belonging to the medium-grained identifier to determine the gas data belonging to the medium-grained identifier with optimized clustering; based on the second clustering algorithm, cluster multiple gas data belonging to the fine-grained identifier to determine the gas data belonging to the fine-grained identifier with optimized clustering.

[0106] It should be noted that the gas anomaly detection model is composed of a convolutional neural network (CNN), a max pooling layer, and a long short-term memory network (LSTM).

[0107] For example, the architecture diagram of the gas anomaly detection model is as Figure 6 shown. The process of performing anomaly detection on gas data may include: inputting the target features associated with the coarse-grained identifier, the target features associated with the medium-grained identifier, and the target features associated with the fine-grained identifier into the gas anomaly detection model; the convolutional layer included in the gas anomaly detection model: performing a convolution operation by using a convolution function (Conv3-32), where the parameters in Conv3-32 are set as filters = 32, kernel_size = 3, and the activation function is the ReLU function to determine the data after convolution, and inputting the data after convolution into the max pooling layer; the max pooling layer (Max-Pool) included in the gas anomaly detection model: where the parameters in the max pooling function are set as pool_size = 2, performing a max pooling operation on the data after convolution to determine the data after pooling, and inputting the data after pooling into the LSTM layer; the long short-term memory network (LSTM) layer included in the gas anomaly detection model: with the number of units being 32, determining the data output by the LSTM layer; the fusion and output layer included in the gas anomaly detection model: connecting the data output by the LSTM layers under various granularity identifiers to output an anomaly probability value.

[0108] To implement the above embodiments, the present application also proposes a gas data anomaly detection device.

[0109] Figure 7 It represents a schematic structural diagram of a gas data anomaly detection device provided by an embodiment of the present application.

[0110] As Figure 7 shown, the gas data anomaly detection device 700 includes: a first acquisition module 701, a granularity division module 702, a first determination module 703, and a second determination module 704.

[0111] The first acquisition module 701 is configured to acquire a gas data set to be detected; wherein, the gas data set includes a plurality of gas data collected within at least one time period in the mining area to be detected.

[0112] The granularity division module 702 is configured to perform granularity division on the gas data set based on the joint information entropy calculated from the gas data set, so as to determine the granularity identifier to which each gas data in the gas data set belongs.

[0113] The first determination module 703 is configured to perform feature extraction on multiple gas data belonging to the same granularity identifier, so as to determine at least one target feature corresponding to the multiple gas data belonging to the same granularity identifier.

[0114] The second determination module 704 is configured to determine an abnormal probability value sequence corresponding to the gas data set through a pre-trained gas anomaly detection model according to the target features corresponding to the multiple gas data belonging to each granularity identifier in the gas data set; wherein, each abnormal probability value in the abnormal probability value sequence is used to indicate the probability of gas data anomaly occurring in the corresponding gas data in the gas data set.

[0115] In an embodiment of the present application, the granularity identifier includes but is not limited to a coarse granularity identifier, a medium granularity identifier, and a fine granularity identifier; the granularity division module 702 is specifically configured to:

[0116] Obtain a preset number of time steps and feature dimensions.

[0117] For any gas data, determine the joint information entropy corresponding to the gas data according to the number of time steps and the feature dimensions.

[0118] Judge whether the joint information entropy corresponding to each gas data is greater than the first information entropy threshold or not greater than the second information entropy threshold, so as to determine the granularity identifier to which each gas data belongs; wherein, the first information entropy threshold is greater than the second information entropy threshold.

[0119] In an embodiment of the present application, the granularity division module 702 is specifically configured to:

[0120] For the joint information entropy corresponding to each gas data, if the joint information entropy is greater than the first information entropy threshold, determine that the granularity identifier to which the gas data belongs is the coarse granularity identifier.

[0121] If the joint information entropy is not greater than the second information entropy threshold, determine that the granularity identifier to which the gas data belongs is the fine granularity identifier.

[0122] If the joint information entropy is not greater than the first information entropy threshold and greater than the second information entropy threshold, determine that the granularity identifier to which the gas data belongs is the medium granularity identifier.

[0123] In one embodiment of the present application, the first determination module 703 is specifically configured to:

[0124] According to the target granularity identifier to which multiple gas data under the same type of granularity identifier belong, determine the target feature extraction method corresponding to the target granularity identifier through a preset mapping table of granularity identifiers and feature extraction methods; wherein, the mapping table of granularity identifiers and feature extraction methods includes multiple granularity identifiers and corresponding feature extraction methods;

[0125] Based on the target feature extraction method, perform feature extraction on multiple gas data under the same type of granularity identifier to determine the target features corresponding to the multiple gas data under the same type of granularity identifier.

[0126] In one embodiment of the present application, the device further includes a one-hot encoding module, which is specifically configured to:

[0127] Obtain various types of granularity identifiers;

[0128] For each type of granularity identifier, perform one-hot encoding on the granularity identifier to determine the one-hot encoding vector corresponding to the granularity identifier;

[0129] Based on the one-hot encoding vectors corresponding to various types of granularity identifiers, determine the one-hot encoding vector associated with the gas data;

[0130] According to the one-hot encoding vectors associated with each gas data, determine the one-hot encoding vector matrix corresponding to the gas data set.

[0131] In one embodiment of the present application, the second determination module 704 is specifically configured to:

[0132] According to the one-hot encoding vector matrix corresponding to the gas data set, determine the granularity identifier to which each of the multiple gas data in the gas data set belongs;

[0133] According to the target features corresponding to multiple gas data under each type of granularity identifier in the gas data set, determine the target features associated with each type of granularity identifier;

[0134] Input the target features associated with each type of granularity identifier into the gas anomaly detection model to determine the anomaly probability value sequence corresponding to the gas data set.

[0135] In one embodiment of the present application, the device further includes a gas anomaly detection model module, which is specifically configured to:

[0136] Obtain a historical gas dataset and the corresponding sequence of actual anomaly probability values of the historical gas dataset; wherein, the historical gas dataset includes a plurality of historical gas data collected within at least one historical time period in the detected mining area, and each actual anomaly probability value in the sequence of actual anomaly probability values is used to indicate the probability of gas data anomaly occurring in the corresponding historical gas data in the historical gas dataset;

[0137] Perform granularity division on the historical gas dataset based on the joint information entropy calculated from the historical gas dataset to determine the granularity identifier to which each historical gas data in the historical gas dataset belongs;

[0138] For any multiple historical gas data belonging to the same type of granularity identifier, perform feature extraction on the multiple historical gas data belonging to the same type of granularity identifier to determine the corresponding historical target features of the multiple historical gas data belonging to the same type of granularity identifier;

[0139] Determine a trained gas anomaly detection model according to the historical target features corresponding to the multiple historical gas data belonging to various granularity identifiers in the historical gas dataset and the sequence of actual anomaly probability values corresponding to the historical gas dataset.

[0140] In an embodiment of the present application, the gas anomaly detection model module is specifically used for:

[0141] Input the historical target features corresponding to the multiple historical gas data belonging to various granularity identifiers in the historical gas dataset into the initial gas anomaly detection model to determine the sequence of anomaly probability values corresponding to the historical gas dataset;

[0142] Train the initial gas anomaly detection model according to the sequence of anomaly probability values corresponding to the historical gas dataset and the sequence of actual anomaly probability values to determine a trained gas anomaly detection model.

[0143] The gas data anomaly detection device provided by the embodiment of the present application acquires a gas data set to be detected; wherein, the gas data set includes a plurality of gas data collected within at least one time period in the mining area to be detected; based on the joint information entropy calculated from the gas data set, the gas data set is partitioned by granularity to determine the granularity identifier to which each gas data in the gas data set belongs; for any plurality of gas data belonging to the same type of granularity identifier, feature extraction is performed on the plurality of gas data belonging to the same type of granularity identifier to determine at least one target feature corresponding to the plurality of gas data belonging to the same type of granularity identifier; according to the target features corresponding to the plurality of gas data belonging to various granularity identifiers in the gas data set, through a pre-trained gas anomaly detection model, an anomaly probability value sequence corresponding to the gas data set is determined; wherein, each anomaly probability value in the anomaly probability value sequence is used to indicate the probability that the corresponding gas data in the gas data set has a gas data anomaly. Thus, before determining the probability that the gas data in the gas data set has a gas data anomaly through the gas anomaly detection model, not only are various factors that affect the occurrence of abnormal gas data in the actual working scenario comprehensively considered, but also the non-linear characteristics presented by the distribution of the plurality of gas data in the gas data set are considered. Therefore, the gas data set is comprehensively partitioned by granularity not only from the perspective of the local fluctuation of the gas data but also from the perspective of the macro trend of the gas data. Furthermore, by using the gas data belonging to various granularity identifiers, through the gas anomaly detection model, the probability of abnormal gas data can be determined without consuming a large amount of time cost for pre-labeling the gas data, which can provide high-quality gas data for the gas anomaly detection model and greatly improve the accuracy and reliability of the gas anomaly detection model.

[0144] It should be noted that the foregoing explanation of the embodiment of the gas data anomaly detection method is also applicable to the gas data anomaly detection device of this embodiment, and will not be elaborated here.

[0145] To implement the above embodiment, the present application also proposes an electronic device.

[0146] Figure 8 It is a schematic structural diagram of the electronic device provided by the embodiment of the present application.

[0147] As Figure 8 shown, the electronic device 800 may include: a processor 802 and a memory 803 communicatively connected to the processor 802; the memory 803 stores computer-executable instructions; the processor 802 executes the computer-executable instructions stored in the memory 803 to implement the method provided by the foregoing embodiment.

[0148] Further, the electronic device 800 further includes:

[0149] A transceiver 801 for communication between a memory 803 and a processor 802.

[0150] Among them, the memory 803 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.

[0151] If the memory 803, the processor 802, and the transceiver 801 are implemented independently, the transceiver 801, the memory 803, and the processor 802 can be interconnected through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity in representation, Figure 8 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0152] Optionally, in a specific implementation, if the memory 803, the processor 802, and the transceiver 801 are integrated on a single chip, the memory 803, the processor 802, and the transceiver 801 can communicate with each other through an internal interface.

[0153] The processor 802 may be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0154] To implement the above embodiments, the present application also proposes a computer-readable storage medium storing computer-executable instructions, which are used to implement the method provided by the foregoing embodiments when executed by a processor.

[0155] To implement the above embodiments, the present application also proposes a computer program product including a computer program, which implements the method provided by the foregoing embodiments when executed by a processor.

[0156] The collection, storage, use, processing, transmission, provision, and disclosure of the user's personal information involved in the present application and other processes all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0157] It should be noted that personal information from users should be collected for legal and reasonable purposes and should not be shared or sold outside of such legal uses. In addition, such collection / sharing should be carried out after obtaining the informed consent of the users, including but not limited to notifying the users to read the user agreement / user notice and sign an agreement / authorization including authorizing relevant user information before the users use the function. In addition, any necessary steps should be taken to safeguard and protect access to such personal information data and ensure that others with access to the personal information data comply with their privacy policies and procedures.

[0158] This application is expected to provide embodiments in which users can selectively block the use or access of personal information data. That is, the present disclosure is expected to provide hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, the risk can be minimized by restricting data collection and deleting the data. In addition, when applicable, personal identifiers are removed from such personal information to protect the privacy of the users.

[0159] In the description of the foregoing embodiments, the descriptions referring to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0160] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present application, "a plurality of" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0161] Any process or method description shown in the flowchart or described in other ways herein can be understood as representing a module, segment, or part of code including one or more executable instructions for implementing a customized logic function or process, and the scope of the preferred embodiments of the present application includes additional implementations, where the functions may be executed in a manner not shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0162] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definable sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in combination with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection parts with one or more wirings (electronic devices), portable computer disk cartridges (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), fiber optic devices, and portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other appropriate processing when necessary, and then stored in a computer memory.

[0163] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or combinations thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGA), field-programmable gate arrays (FPGA), etc.

[0164] Those of ordinary skill in the art of the present technology can understand that all or part of the steps carried by the methods of the above-described embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0165] In addition, each functional unit in various embodiments of the present application may be integrated into one processing module, may exist separately as individual physical units, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0166] The above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A gas data anomaly detection method, characterized in that, It includes the following steps: Obtain a gas dataset to be detected; wherein, the gas dataset includes a plurality of gas data collected within at least one time period in the mining area to be detected; Based on the joint information entropy calculated from the gas dataset, perform granularity partitioning on the gas dataset to determine the granularity identifier to which each gas data in the gas dataset belongs; For any plurality of gas data belonging to the same class of granularity identifiers, perform feature extraction on the plurality of gas data belonging to the same class of granularity identifiers to determine at least one target feature corresponding to the plurality of gas data belonging to the same class of granularity identifiers, wherein, it includes: according to the target granularity identifier to which the plurality of gas data belonging to the same class of granularity identifiers belong, determine the target feature extraction method corresponding to the target granularity identifier through a preset mapping table of granularity identifiers and feature extraction methods; wherein, the mapping table of granularity identifiers and feature extraction methods includes a variety of granularity identifiers and corresponding feature extraction methods; Based on the target feature extraction method, perform feature extraction on the plurality of gas data belonging to the same class of granularity identifiers to determine the target feature corresponding to the plurality of gas data belonging to the same class of granularity identifiers; According to the target features corresponding to the plurality of gas data belonging to each class of granularity identifiers in the gas dataset, through a pre-trained gas anomaly detection model, determine the sequence of anomaly probability values corresponding to the gas dataset; wherein, each anomaly probability value in the sequence of anomaly probability values is used to indicate the probability of gas data anomaly occurring for the corresponding gas data in the gas dataset.

2. The method according to claim 1, wherein Wherein, The granularity identifier includes a coarse granularity identifier, a medium granularity identifier, and a fine granularity identifier; The performing granularity partitioning on the gas dataset based on the joint information entropy calculated from the gas dataset to determine the granularity identifier to which each gas data in the gas dataset belongs includes: Obtain a preset number of time steps and feature dimensions; For any one of the gas data, determine the joint information entropy corresponding to the gas data according to the number of time steps and the feature dimensions; Judge whether the joint information entropy corresponding to each gas data is greater than a first information entropy threshold or not greater than a second information entropy threshold to determine the granularity identifier to which each gas data belongs; wherein, the first information entropy threshold is greater than the second information entropy threshold.

3. The method according to claim 2, wherein The judging whether the joint information entropy corresponding to each gas data exceeds the first information entropy threshold or is not greater than the second information entropy threshold to determine the granularity identifier to which each gas data belongs; wherein, the first information entropy threshold is greater than the second information entropy threshold includes: For the joint information entropy corresponding to each gas data, if the joint information entropy is greater than the first information entropy threshold, determine that the granularity identifier to which the gas data belongs is the coarse granularity identifier; If the joint information entropy is not greater than the second information entropy threshold, determine that the granularity identifier to which the gas data belongs is the fine granularity identifier; If the combined information entropy is not greater than the first information entropy threshold and greater than the second information entropy threshold, determine that the granularity identifier to which the gas data belongs is the medium granularity identifier.

4. The method according to claim 1, wherein Wherein, After performing feature extraction on multiple gas data belonging to the same granularity identifier for any one, to determine at least one target feature corresponding to the multiple gas data belonging to the same granularity identifier, it includes: Obtain various granularity identifiers; For each type of granularity identifier, perform one-hot encoding on the granularity identifier to determine the one-hot encoding vector corresponding to the granularity identifier; Based on the one-hot encoding vectors corresponding to each type of granularity identifier, determine the one-hot encoding vector associated with the gas data; According to the one-hot encoding vectors associated with each gas data, determine the one-hot encoding vector matrix corresponding to the gas data set.

5. The method according to claim 4, characterized in that The step of determining the abnormal probability value sequence corresponding to the gas data set through the pre-trained gas abnormal detection model according to the target features corresponding to multiple gas data belonging to each type of granularity identifier in the gas data set includes: According to the one-hot encoding vector matrix corresponding to the gas data set, determine the granularity identifier to which each of the multiple gas data in the gas data set belongs; According to the target features corresponding to multiple gas data belonging to each type of granularity identifier in the gas data set, determine the target features associated with each type of granularity identifier; Input the target features associated with each type of granularity identifier into the gas abnormal detection model to determine the abnormal probability value sequence corresponding to the gas data set.

6. The method according to claim 1, wherein The method for obtaining the gas abnormal detection model includes: Obtain a historical gas data set and the actual abnormal probability value sequence corresponding to the historical gas data set; wherein, the historical gas data set includes multiple historical gas data collected within at least one historical time period in the mined area that has been detected, and each actual abnormal probability value in the actual abnormal probability value sequence is used to indicate the probability of gas data abnormality of the corresponding historical gas data in the historical gas data set; Perform granularity division on the historical gas data set based on the combined information entropy calculated from the historical gas data set to determine the granularity identifier to which each historical gas data in the historical gas data set belongs; For any multiple historical gas data belonging to the same granularity identifier, perform feature extraction on the multiple historical gas data belonging to the same granularity identifier to determine the historical target features corresponding to the multiple historical gas data belonging to the same granularity identifier; Determine the trained gas abnormal detection model according to the historical target features corresponding to multiple historical gas data belonging to each type of granularity identifier in the historical gas data set and the actual abnormal probability value sequence corresponding to the historical gas data set.

7. The method according to claim 6, wherein Determining the gas anomaly detection model according to the historical target features corresponding to multiple pieces of the historical gas data belonging to each of the particle size identifications in the historical gas data set and the actual anomaly probability value sequence corresponding to the historical gas data set includes: Inputting the historical target features corresponding to multiple pieces of the historical gas data belonging to each of the particle size identifications in the historical gas data set into an initial gas anomaly detection model to determine the anomaly probability value sequence corresponding to the historical gas data set; Training the initial gas anomaly detection model according to the anomaly probability value sequence corresponding to the historical gas data set and the actual anomaly probability value sequence to determine the trained gas anomaly detection model.

8. A gas data anomaly detection device, characterized in that, It includes the following modules: A first acquisition module, configured to acquire a gas data set to be detected; wherein, the gas data set includes multiple gas data collected within at least one time period in the mining area to be detected; A particle size division module, configured to perform particle size division on the gas data set based on the joint information entropy calculated from the gas data set to determine the particle size identification to which each piece of the gas data in the gas data set belongs; A first determination module, configured to perform feature extraction on multiple pieces of gas data belonging to the same class of particle size identifications to determine at least one target feature corresponding to the multiple pieces of gas data belonging to the same class of particle size identifications, where it includes: determining a target feature extraction method corresponding to the target particle size identification through a preset mapping table of particle size identifications and feature extraction methods according to the target particle size identification to which the multiple pieces of gas data belonging to the same class of particle size identifications belong; wherein, the mapping table of particle size identifications and feature extraction methods includes multiple particle size identifications and corresponding feature extraction methods; performing feature extraction on the multiple pieces of gas data belonging to the same class of particle size identifications based on the target feature extraction method to determine the target feature corresponding to the multiple pieces of gas data belonging to the same class of particle size identifications; A second determination module, configured to determine the anomaly probability value sequence corresponding to the gas data set through a pre-trained gas anomaly detection model according to the target features corresponding to multiple pieces of the gas data belonging to each of the particle size identifications in the gas data set; wherein, each anomaly probability value in the anomaly probability value sequence is used to indicate the probability that the corresponding gas data in the gas data set has a gas data anomaly.

9. An electronic device, characterized in that, It includes: A processor and a memory communicatively connected to the processor; The memory stores computer execution instructions; The processor executes the computer execution instructions stored in the memory to implement the method according to any one of claims 1-7.

Images