A device fault determination method and apparatus, electronic device, and storage medium

Abstract

The application discloses a device fault determination method and device, electronic equipment and storage medium. The method comprises the following steps: acquiring a candidate infrared image of a candidate device, and determining a target region in the candidate infrared image; determining a region Shapley value of the target region according to a region image feature of the target region; determining a region mutual information value of the target region according to a feature score of the region image feature of the target region and a preset classification label value; determining a region score of the target region according to the region Shapley value and the region mutual information value, and judging whether there is a faulty device in the candidate device according to the region score. Through the technical scheme provided in the embodiment of the application, the image region in which the faulty device is most likely to exist can be determined from each candidate infrared image, artificial analysis of the candidate infrared image is avoided, and the efficiency of the faulty device identification is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to image recognition technology, and in particular to a device fault determination method and device, electronic device and storage medium. BACKGROUND

[0002] In a substation, due to poor contact, insulation aging, etc., the equipment is prone to heat and temperature rise, and if not handled in time, it is easy to further worsen the equipment failure condition. Therefore, it is necessary to process the infrared image of the substation equipment to realize the diagnosis and fault recognition of the equipment.

[0003] In the prior art, all image features in the infrared image of the substation equipment are extracted to determine the fault, and the extracted image features may include image features irrelevant to the fault, which reduces the accuracy of fault determination. SUMMARY

[0004] The present application provides a device fault determination method, device, electronic device and storage medium to improve the accuracy and efficiency of medical service appointments.

[0005] According to an aspect of the present application, a device fault determination method is provided, which comprises:

[0006] obtaining a candidate infrared image of a candidate device, and determining a target region in the candidate infrared image;

[0007] determining a regional Shapley value of the target region according to regional image features of the target region;

[0008] determining a regional mutual information value of the target region according to the feature score of the regional image features of the target region and a preset classification label value;

[0009] determining a regional score of the target region according to the regional Shapley value and the regional mutual information value, and determining whether there is a fault device in the candidate device according to the regional score.

[0010] According to another aspect of the present application, a device fault determination device is provided, which comprises:

[0011] a region determination module for obtaining a candidate infrared image of a candidate device, and determining a target region in the candidate infrared image;

[0012] a Shapley value determination module for determining a regional Shapley value of the target region according to regional image features of the target region;

[0013] The mutual information value determination module is configured to determine a region mutual information value of the target region according to the feature score of the region image feature of the target region and a preset classification label value.

[0014] The device presence determination module is configured to determine a region score of the target region according to the region Shapley value and the region mutual information value, and determine whether a faulty device exists in the candidate devices according to the region score.

[0015] According to another aspect of the present application, an electronic device is provided, which comprises:

[0016] at least one processor; and

[0017] a memory connected to the at least one processor in communication; wherein

[0018] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the device fault determination method according to any one of the embodiments of the present application.

[0019] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to implement the device fault determination method according to any one of the embodiments of the present application when executed.

[0020] The technical solution provided in the embodiment determines a target region in a candidate infrared image of a candidate device, determines a region Shapley value of the target region according to a region image feature of the target region, avoids determining a fault by extracting all image features in the infrared image, and reduces the accuracy of fault determination caused by irrelevant image features in the extracted image features. The region Shapley value is used to represent the importance of the target region in all regions, and the region mutual information value is used to determine the mutual dependence of the feature score and the preset classification label value, thereby improving the effectiveness and accuracy of the region score determination and the accuracy of the faulty device identification. The region score is used to determine an image region in which a faulty device is most likely to exist from each candidate infrared image, thereby avoiding artificial analysis of the candidate infrared image in sequence and improving the efficiency of the faulty device identification.

[0021] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 A flow chart of a device fault determination method provided for the first embodiment of the present application;

[0023] Figure 2 A flow chart of a device fault determination method provided for the second embodiment of the present application;

[0024] Figure 3 A structural schematic diagram of a device fault determination apparatus provided for the third embodiment of the present application;

[0025] Figure 4 A structural schematic diagram of an electronic device for implementing the embodiments of the present application. DETAILED DESCRIPTION

[0026] In order to make the personnel in the technical field better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by the personnel in the technical field without creative labor should belong to the protection scope of the present application.

[0027] It should be noted that the terms “first”, “second”, “target” and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be exchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms “include” and “have” and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0028] Embodiment one

[0029] Figure 1 A flow chart of a device fault determination method provided for the first embodiment of the present application, the present embodiment can be applicable to determining the device fault according to the infrared image of the device, the method can be executed by the device fault determination apparatus provided by the embodiments of the present application, and the apparatus can be realized by software and / or hardware. Referring to Figure 1 , the device fault determination method provided by the present embodiment comprises:

[0030] In step 110, a candidate infrared image of the candidate device is acquired, and a target region in the candidate infrared image is determined.

[0031] The candidate device can be a device in the current scene that needs to be focused on whether a fault is generated, such as a device in a working state or all devices in a substation scene, which is not limited in the embodiment.

[0032] The candidate infrared image is an image of the candidate device captured by an infrared thermal imaging instrument. One or more images can be captured for different candidate devices, or one or more images can be captured for multiple candidate devices, which is not limited in the embodiment.

[0033] The target region is a region that can generate a fault, such as a region with higher brightness in the infrared image. The determination method can be to acquire brightness information of pixel points in the candidate infrared image, and to determine a region composed of pixel points with brightness values greater than a preset threshold as the target region.

[0034] In the embodiment, the candidate infrared image of the candidate device is acquired, and the target region in the candidate infrared image is determined, including:

[0035] If the number of candidate infrared images is greater than a preset number threshold, an image correlation relationship between the candidate infrared images is determined.

[0036] At least one image set of the candidate infrared images is acquired according to the image correlation relationship.

[0037] At least one target infrared image is determined from the image set, and a target region in the target infrared image is determined.

[0038] The preset number threshold can be determined by a person, which is not limited in the embodiment. If the number of candidate infrared images is greater than the preset number threshold, the image correlation relationship between the candidate infrared images is determined. The image correlation relationship is used to determine the correlation between different candidate infrared images, which can be represented by a preset type of correlation coefficient. The closer the correlation coefficient is to 1, the more relevant the different candidate infrared images are. For example, the preset type of correlation coefficient can be a Pearson correlation coefficient, which is not limited in the embodiment. For example, the Pearson correlation coefficient r xy between the candidate infrared images can be determined by the following formula:

[0039]

[0040] where x i represents the i th image feature of the candidate infrared image x; y i represents the i th image feature of the candidate infrared image y, and n is the total number of image features.

[0041] The at least one image set of the candidate infrared images can be obtained according to the image correlation relationship. For example, candidate infrared images with a Pearson correlation coefficient greater than 0.5 can be determined as the same image set. The present embodiment is not limited in this regard.

[0042] The at least one target infrared image can be determined from the image set. For example, a random infrared image can be determined as the target infrared image from the image set. The present embodiment is not limited in this regard. The target region is determined from the target infrared image.

[0043] The candidate infrared images can include images taken at different angles or different time periods of the same device. There can be a large number of similar images. If all candidate infrared images are analyzed, the analysis time can be long, and the efficiency of device fault determination can be reduced. According to the image correlation relationship, at least one image set of the candidate infrared images is obtained. The similar image sets are determined, and at least one target infrared image is determined therefrom. The target infrared image is analyzed for device fault. The image analysis integrity is ensured, and the efficiency of device fault determination is improved.

[0044] In step 120, the region Shapley value of the target region is determined according to the region image features of the target region.

[0045] The region Shapley value of the target region can be determined according to the following formula:

[0046]

[0047] I i (C) is the number of features in the candidate infrared image that are not closely related to the target region. For example, the number of features in the target region; K i (C) is the number of features in the candidate infrared image that are not closely related to the target region, for example, the number of features outside the target region; S is all subsets containing the target region i, and N is the number of target regions. In the cooperative game theory, the Shapley value can be used as the average marginal contribution of the participants to each possible alliance. The more the participants contribute, the more benefits they can obtain. Therefore, the importance of the target region in the entire candidate infrared image can be represented by calculating the region Shapley value of the target region.

[0048] In step 130, the region mutual information value of the target region is determined according to the feature score of the region image feature of the target region and the preset classification label value.

[0049] The feature score of the regional image feature is a score indicating whether the image regional feature is related to the equipment fault, for example, the feature score is 1 if related to the equipment fault, and the feature score is 0 if not related to the equipment fault. The feature score of the regional image feature can be obtained according to the calculation of the image feature, for example, by judging whether the image feature value is greater than a preset threshold, if greater, it indicates that the image regional feature is related to the equipment fault, and the like, which is not limited in the embodiment.

[0050] The preset classification label value is a label corresponding to a preset classification related to the image feature type, for example, if the image feature type is a feature related to brightness, the preset classification label value is a value related to the brightness classification, for example, the higher the brightness, the higher the preset classification label value.

[0051] The feature score f of the regional image feature i And the preset classification label value class can be substituted into the following mutual information value formula to determine the regional mutual information value I(f i ; class) of the target region:

[0052]

[0053] Where P xy (x, y) is the joint probability density function of x and y; P x (x)P y (y) is the marginal density function. The mutual information determines the degree of similarity of the joint distribution P xy and the product of the coefficient marginal distribution, provided that the two variables X and Y are completely unrelated, then the value is 0.

[0054] Step 140, determining the regional score of the target region according to the regional shapley value and the regional mutual information value, and judging whether there is a fault equipment in the candidate equipment according to the regional score.

[0055] The regional score L(i) of the target region can be determined by multiplying the regional shapley value and the regional mutual information value, for example:

[0056] L(i) = X(S, i) * I(f i ; class) (4)

[0057] According to the regional score, it is determined whether there is a fault equipment in the candidate equipment, for example, if the regional score is greater than a preset threshold, it is determined that the target region may contain a fault equipment, the candidate infrared image containing the target region can be obtained and sent to the relevant fault solving personnel, and further judgment is performed by the fault solving personnel.

[0058] In the embodiment, after judging whether there is a fault equipment in the candidate equipment, the method further comprises:

[0059] If there is a faulty device, obtain device temperature information associated with the faulty device;

[0060] Determine the fault type of the faulty device according to the device temperature information.

[0061] If it is determined that there is a faulty device, obtain device temperature information associated with the faulty device, such as temperature change information within a preset time period, and the current temperature of the faulty device, and the like, which are not limited in the present embodiment. Determine the fault type of the faulty device according to the device temperature information. For example, determine the fault type of the faulty device by the following formula:

[0062]

[0063] Wherein, θ0, θ1, θ2 are device temperature information, which are respectively the ambient temperature of the environment where the faulty device is located, the temperature of the normal device in the environment where the faulty device is located, and the fault point temperature of the faulty device.

[0064] If the above formula (5) is satisfied, it can be determined that the fault type of the faulty device is a current-induced heating fault, wherein the current-induced heating fault is a heating fault of the power transformation device caused by current.

[0065] When the device temperature information is temperature change information within a preset time period, determine the fault type of the faulty device according to the device temperature information, which can be the temperature before the fault of the faulty device and the temperature after the fault of the faulty device. The temperature before the fault can be collected in advance, and the temperature after the fault can be collected at present. Determine whether the temperature difference is within the range of 0.5-1℃. If yes, it can be determined that the fault type of the faulty device is a voltage-induced heating fault, wherein the current-induced heating fault is a heating fault of the power transformation device caused by voltage.

[0066] Determine the fault type of the faulty device according to the device temperature information associated with the faulty device. Based on the temperature distribution characteristics of the device, improve the pertinence of the fault type determination. Without human judgment, improve the efficiency of the fault type determination. Facilitate subsequent adoption of corresponding fault resolution methods according to the fault type, and improve the effectiveness of the faulty device determination.

[0067] The technical scheme provided by the embodiment is characterized in that: a candidate infrared image of a candidate device is acquired, and a target region in the candidate infrared image is determined; a region Shapley value of the target region is determined according to a region image feature of the target region, so as to avoid the problem that the accuracy of fault determination is reduced due to the fact that there may be image features irrelevant to the fault in the extracted image features when the fault is determined by extracting all image features in the infrared image; a region mutual information value of the target region is determined according to a feature score of the region image feature of the target region and a preset classification label value; a region score of the target region is determined according to the region Shapley value and the region mutual information value, wherein the region Shapley value is used to represent the importance of the target region in all regions, and the region mutual information value is used to determine the mutual dependence of the feature score and the preset classification label value, so as to improve the effectiveness and accuracy of the region score determination, thereby improving the accuracy of the fault device identification; and an image region in which the fault device is most likely to exist is determined from each candidate infrared image according to the region score, so as to avoid the artificial analysis of the candidate infrared image in sequence, and improve the efficiency of the fault device identification.

[0068] Embodiment two

[0069] Figure 2 The flowchart of the device fault determination method provided by the embodiment two of the application is used to supplement the process of determining the region mutual information value of the target region according to the feature score of the region image feature of the target region and the preset classification label value. Compared with the above scheme, the embodiment is specifically optimized as follows: determining the region mutual information value of the target region according to the feature score of the region image feature of the target region and the preset classification label value, comprising:

[0070] determining a feature mutual information value of the region image feature according to the region image feature value of the region image feature and the preset classification label value;

[0071] determining a feature score of the region image feature according to the feature mutual information value and a stage threshold value of a current iteration stage;

[0072] determining the region mutual information value of the target region according to the feature score and the preset classification label value. Specifically, the flowchart of the device fault determination method is as shown in Figure 2

[0073] Step 210: acquiring a candidate infrared image of a candidate device, and determining a target region in the candidate infrared image.

[0074] Step 220: determining a region Shapley value of the target region according to a region image feature of the target region.

[0075] Step 230: determining a feature mutual information value of the region image feature according to a region image feature value of the region image feature and a preset classification label value. ​

[0076] wherein the image feature value of the target region is a feature value of the image feature extracted in the target region, and the feature mutual information value of the region image feature is determined according to the region image feature value of the region image feature and the preset classification label value, which can be obtained by substituting the region image feature value and the preset classification label value into the above formula (3) to obtain the feature mutual information value I(d i , class), wherein d i is the region image feature value.

[0077] Step 240, determining the feature score of the region image feature according to the feature mutual information value and the stage threshold value of the current iteration stage.

[0078] wherein each region mutual information value can be finally determined through multiple iterations, each iteration is recorded as an iteration stage, and different iteration stages can correspond to different stage threshold values, and the present embodiment does not limit the current iteration stage to the stage of the current iteration.

[0079] The feature score of the region image feature is determined according to the feature mutual information value and the stage threshold value of the current iteration stage, which can be realized by the following formula:

[0080]

[0081] that is, when the feature mutual information value is greater than the stage threshold value of the current iteration stage, the feature score of the region image feature is determined as 1; when the feature mutual information value is less than or equal to the stage threshold value of the current iteration stage or other conditions, the feature score of the region image feature is determined as 0, wherein the stage threshold value of the current iteration stage is a random number in 0-1.

[0082] Step 250, determining the region mutual information value of the target region according to the feature score and the preset classification label value.

[0083] Step 260, determining the region score of the target region according to the region shapley value and the region mutual information value, and determining whether there is a faulty device in the candidate device according to the region score.

[0084] In the present embodiment, the determination of whether there is a faulty device in the candidate device according to the region score includes:

[0085] determining the fitness calculation result according to the region score and the preset fitness function;

[0086] determining whether the target region is a faulty region according to the fitness calculation result;

[0087] if yes, determining whether there is a faulty device in the faulty region.

[0088] Wherein, the fitness calculation result F(X) is determined according to the region score and the preset fitness function, which can be realized by the following formula:

[0089]

[0090] Wherein, A(X) is the classification accuracy provided by the feature vector X, wherein the feature vector X is a feature vector corresponding to the region image feature; X i is the state of the i-th feature in X, X i ==1 indicates that the feature with specific characteristics such as heating and lighting is assigned a value of 1; and a and β are weight coefficients; P0 is the number of features in X with a state of 0; and P m is the total number of features in X.

[0091] Since multiple L(i) can be obtained through multiple iterations, multiple fitness calculation results can be obtained accordingly, and whether the target region is a fault region can be determined according to the fitness calculation result, which can be determined by a preset result determination method to determine one of the fitness calculation results as the final target calculation result, and if the target region is a fault region, the target region is determined to be a fault region. The threshold value. The preset result determination method can be one of the mean, maximum, etc. of all fitness calculation results, which is not limited in this embodiment.

[0092] If the target region is a fault region, it is determined whether there is a fault device in the fault region, which can be determined by identifying whether there is a device shape outline in the fault region, manually judging, etc. This embodiment is not limited.

[0093] By determining the fitness calculation result according to the region score and the preset fitness function in the genetic algorithm, the region score with small fitness is excluded, so that the target region which is not a fault region is excluded, avoiding that the non-fault region in the target region is mistakenly determined as a fault region only by the region score, and further improving the accuracy of the fault device determination.

[0094] The technical scheme provided in this embodiment determines the feature mutual information value of the region image feature according to the region image feature value of the region image feature and the preset classification label value; determines the feature score of the region image feature according to the feature mutual information value and the stage threshold value of the current iteration stage, and determines the feature score in combination with the region image feature value, thereby improving the accuracy of the feature score determination, and determining different feature scores through iteration, thereby avoiding the problem of inaccurate calculation caused by calculating the single region mutual information value, improving the accuracy of the region mutual information value determination, and thereby improving the accuracy of the fault device determination.

[0095] Embodiment three

[0096] Figure 3A structural schematic diagram of a device fault determination apparatus provided for Embodiment Three of the present application. The apparatus can be implemented in a hardware and / or software manner, can execute a device fault determination method provided by any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of executing the method. As shown in the figure, the apparatus comprises: Figure 3

[0097] A region determination module 310 is configured to acquire a candidate infrared image of a candidate device and determine a target region in the candidate infrared image.

[0098] A Shapley value determination module 320 is configured to determine a region Shapley value of the target region according to a region image feature of the target region.

[0099] A mutual information value determination module 330 is configured to determine a region mutual information value of the target region according to a feature score of the region image feature of the target region and a preset classification label value.

[0100] A device presence judgment module 340 is configured to determine a region score of the target region according to the region Shapley value and the region mutual information value, and determine whether there is a faulty device in the candidate device according to the region score.

[0101] On the basis of the above technical solutions, optionally, the region determination module comprises:

[0102] An image association relationship determination unit is configured to determine an image association relationship between the candidate infrared images if the number of the candidate infrared images is greater than a preset number threshold.

[0103] An image set acquisition unit is configured to acquire at least one image set of the candidate infrared images according to the image association relationship.

[0104] A region determination unit is configured to determine at least one target infrared image from the image set and determine a target region in the target infrared image.

[0105] On the basis of the above technical solutions, optionally, the mutual information value determination module comprises:

[0106] A feature mutual information value unit is configured to determine a feature mutual information value of the region image feature according to a region image feature value of the region image feature and the preset classification label value.

[0107] A feature score determination unit is configured to determine a feature score of the region image feature according to the feature mutual information value and a stage threshold value of a current iteration stage.

[0108] ​A regional mutual information value determination unit is configured to determine a regional mutual information value of the target region according to the feature score and a preset classification label value.

[0109] On the basis of the above technical solutions, optionally, the device presence determination module comprises:

[0110] A calculation result determination unit is configured to determine a fitness calculation result according to the regional score and a preset fitness function.

[0111] A fault region determination unit is configured to determine whether the target region is a fault region according to the fitness calculation result.

[0112] A device presence determination unit is configured to determine whether the fault device exists in the fault region if the fault region determination unit determines that the target region is a fault region.

[0113] On the basis of the above technical solutions, optionally, the device further comprises:

[0114] A device temperature information acquisition module is configured to acquire device temperature information associated with the fault device if the fault device exists after the device presence determination module.

[0115] A fault type determination module is configured to determine a fault type of the fault device according to the device temperature information.

[0116] Embodiment Four

[0117] Figure 4 A structural schematic diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0118] As Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., connected to the at least one processor 11 in communication. The memory stores a computer program executable by the at least one processor 11, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or loaded into the random access memory (RAM) 13 from the storage unit 18. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0119] A plurality of components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, a speaker, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0120] The processor 11 can be various general and / or special-purpose processing components having processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the device failure determination method.

[0121] In some embodiments, the device failure determination method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the device failure determination method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the device failure determination method by any other appropriate means, such as by means of firmware.

[0122] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0123] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program, when executed, can cause instructions defined in the flow charts and / or block diagrams to be implemented. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a standalone software package and partially on a remote machine or entirely on a remote machine or server.

[0124] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0125] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0126] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0127] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0128] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in sequence, or executed in a different order, as long as the desired results of the present disclosure are achieved, and the present disclosure is not limited herein.

[0129] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and principles of the disclosure. Accordingly, the disclosure is not limited to the specific embodiments described above, but only by the scope of the appended claims.

Claims

1. A method of determining a device failure, the method comprising: The method comprises the following steps: obtaining candidate infrared images of candidate devices, and determining target regions in the candidate infrared images; determining a region Shapley value of the target regions according to region image features of the target regions; determining a region mutual information value of the target regions according to feature scores of the region image features of the target regions and preset classification label values; determining a region score of the target regions according to the region Shapley value and the region mutual information value, and determining whether a faulty device exists in the candidate devices according to the region score.

2. The method of claim 1, wherein, The method comprises the following steps: if the number of the candidate infrared images is greater than a preset number threshold, determining an image association relationship between the candidate infrared images; obtaining at least one image set of the candidate infrared images according to the image association relationship; determining at least one target infrared image from the image set, and determining a target region in the target infrared image.

3. The method of claim 1, wherein, The method comprises the following steps: determining a feature mutual information value of the region image features according to a region image feature value of the region image features and the preset classification label value; determining a feature score of the region image features according to the feature mutual information value and a stage threshold of a current iteration stage; determining a region mutual information value of the target regions according to the feature score and a preset classification label value.

4. The method of claim 1, wherein, The method comprises the following steps: determining an adaptability calculation result according to the region score and a preset adaptability function; determining whether the target region is a faulty region according to the adaptability calculation result; if yes, determining whether the faulty device exists in the faulty region.

5. The method of claim 1, wherein, After determining whether the faulty device exists in the candidate devices, the method further comprises the following steps: if the faulty device exists, obtaining device temperature information associated with the faulty device; determining a fault type of the faulty device according to the device temperature information.

6. An apparatus failure determination device characterized by comprising: The method comprises the following steps: a region determination module, configured to obtain candidate infrared images of candidate devices, and determine target regions in the candidate infrared images; a Shapley value determination module, configured to determine a region Shapley value of the target regions according to region image features of the target regions; a mutual information value determination module, configured to determine a region mutual information value of the target regions according to feature scores of the region image features of the target regions and preset classification label values; a device existence determination module, configured to determine a region score of the target regions according to the region Shapley value and the region mutual information value, and determine whether a faulty device exists in the candidate devices according to the region score.

7. The apparatus of claim 6, wherein, The region determination module comprises: an image association relationship determination unit, configured to determine an image association relationship between the candidate infrared images if the number of the candidate infrared images is greater than a preset number threshold; an image set obtaining unit, configured to obtain at least one image set of the candidate infrared images according to the image association relationship; A region determining unit is configured to determine at least one target infrared image from the image set and determine a target region in the target infrared image.

8. The apparatus of claim 6, wherein, The mutual information value determining module comprises: A feature mutual information value unit is configured to determine a feature mutual information value of the region image feature according to the region image feature value of the region image feature and the preset classification label value; A feature score determining unit is configured to determine a feature score of the region image feature according to the feature mutual information value and a stage threshold value of a current iteration stage; A region mutual information value determining unit is configured to determine a region mutual information value of the target region according to the feature score and a preset classification label value.

9. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the device fault determination method in any one of claims 1-5.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to implement the device fault determination method in any one of claims 1-5 when executed.

Images