Verification evaluation index recommendation method and device for fault detection model

Abstract

The embodiment of the invention provides a verification evaluation index recommendation method and device for a fault detection model, and the method comprises the steps: obtaining the equipment operation information of target equipment, the equipment operation information comprises use condition information, equipment fault information and data processing information of the target equipment; inputting the equipment operation information as an input set into an evaluation index recommendation model to obtain a coding vector of the input set; and determining the similarity between the target device and each historical device in a plurality of historical devices based on the coding vector, and determining a to-be-recommended evaluation index corresponding to the target device according to the similarity and outputting the to-be-recommended evaluation index.

Description

Technical Field

[0001] The embodiments of the present specification relate to the field of computer technology, and in particular to a method for recommending verification evaluation indicators of a fault detection model. Background Art

[0002] Fault detection refers to the process in which the system can determine, locate and analyze the location of abnormal conditions under a certain working environment, find out the specific reasons that cause the system to be abnormal, determine the type and level of the fault, and even perform automatic repairs or give corresponding repair suggestions. Bearings, gears, etc., as key components for transmitting force and torque in mechanical equipment, are prone to local failures. Any minor failure may bring huge risks to the reliability of the entire mechanical system. Therefore, fault detection is crucial for the safe operation of mechanical equipment.

[0003] At present, the method of fault detection for equipment is usually to first determine some detection indicators related to the equipment, and then determine whether the equipment has a fault by determining the indicator value of the equipment under each detection indicator. Therefore, how to ensure the accuracy of the selected detection indicators has become an urgent problem to be solved. Summary of the invention

[0004] In view of this, an embodiment of this specification provides a method for recommending verification evaluation indicators of a fault detection model. One or more embodiments of this specification also involve a verification evaluation indicator recommendation device for a fault detection model, a computing device, a computer-readable storage medium, and a computer program to solve the technical defects existing in the prior art.

[0005] According to a first aspect of an embodiment of this specification, a method for recommending verification evaluation indicators of a fault detection model is provided, comprising:

[0006] Acquire device operation information of the target device, wherein the device operation information includes usage condition information, device failure information, and data processing information of the target device;

[0007] Inputting the equipment operation information as an input set into an evaluation index recommendation model to obtain a coding vector of the input set;

[0008] The similarity between the target device and each of the multiple historical devices is determined based on the encoding vector, and the evaluation index to be recommended corresponding to the target device is determined and output according to the similarity.

[0009] Optionally, determining the similarity between the target device and a plurality of historical devices based on the encoding vector includes:

[0010] Determine a coding vector corresponding to each historical device in the plurality of historical devices;

[0011] The similarity between the encoding vector of the input set and the encoding vector corresponding to each historical device is calculated by a cosine similarity algorithm.

[0012] Optionally, determining and outputting the evaluation index to be recommended corresponding to the target device according to the similarity includes:

[0013] Determining a maximum value among similarities between the target device and the plurality of historical devices;

[0014] The target historical device corresponding to the maximum value is determined, and the historical evaluation index corresponding to the target historical device is determined as the evaluation index to be recommended corresponding to the target device and outputted.

[0015] Optionally, the method for recommending verification evaluation indicators of the fault detection model further includes:

[0016] Obtaining device operation information and multiple historical evaluation indicators corresponding to each of the multiple historical devices;

[0017] The device operation information corresponding to each historical device and the multiple historical evaluation indicators are input as sample data into the evaluation indicator recommendation model to be trained for training, so as to obtain the evaluation indicator recommendation model.

[0018] Optionally, the step of inputting the device operation information corresponding to each historical device and the plurality of historical evaluation indicators as sample data into the evaluation indicator recommendation model to be trained for training includes:

[0019] Input the device operation information corresponding to each historical device and the multiple historical evaluation indicators as sample data into the evaluation indicator recommendation model to be trained;

[0020] Vectorizing the sample data using the evaluation index recommendation model to be trained to generate a corresponding sample encoding vector;

[0021] The plurality of historical devices are clustered based on the sample coding vectors by using a target clustering algorithm to generate at least two device categories.

[0022] Optionally, determining the similarity between the target device and a plurality of historical devices based on the encoding vector includes:

[0023] Determine a central point device of each device category in the at least two device categories, and determine a coding vector of the central point device;

[0024] Classifying the target device into a target device category according to the encoding vector of the input set and the encoding vector of the central point device;

[0025] A similarity between the target device and historical devices included in the target device category is determined based on the encoding vector of the input set.

[0026] Optionally, determining and outputting the evaluation index to be recommended corresponding to the target device according to the similarity includes:

[0027] determining a maximum value among similarities between the target device and historical devices included in the target device category;

[0028] The target historical device corresponding to the maximum value is determined, and the historical evaluation index corresponding to the target historical device is determined as the evaluation index to be recommended corresponding to the target device and outputted.

[0029] According to a second aspect of an embodiment of this specification, a verification evaluation index recommendation device for a fault detection model is provided, comprising:

[0030] An acquisition module is configured to acquire device operation information of a target device, wherein the device operation information includes usage condition information, device failure information, and data processing information of the target device;

[0031] An input module is configured to input the device operation information as an input set into an evaluation index recommendation model to obtain a coding vector of the input set;

[0032] The output module is configured to determine the similarity between the target device and each of the multiple historical devices based on the encoding vector, and determine and output the evaluation index to be recommended corresponding to the target device according to the similarity.

[0033] According to a third aspect of an embodiment of this specification, a computing device is provided, including:

[0034] Memory and processor;

[0035] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement any step of the method for recommending verification and evaluation indicators of the fault detection model.

[0036] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of any one of the methods for recommending verification evaluation indicators of the fault detection model are implemented.

[0037] According to a fifth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned method for recommending verification evaluation indicators of the fault detection model.

[0038] The embodiments of this specification obtain the device operation information of the target device, wherein the device operation information includes the operating condition information, device failure information and data processing information of the target device; input the device operation information as the input set into the evaluation index recommendation model to obtain the encoding vector of the input set; determine the similarity between the target device and each of the multiple historical devices based on the encoding vector, and determine and output the evaluation index to be recommended corresponding to the target device based on the similarity. By analyzing the specific characteristics and working environment of the device, the matching of the recommendation result with the actual situation of the device is achieved, and corresponding evaluation indicators are given to different types of devices under different working conditions, environments and other conditions, which is conducive to improving the accuracy of the recommendation results and verification results. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flowchart of a method for recommending verification and evaluation indicators of a fault detection model provided by an embodiment of this specification;

[0040] Figure 2 is a schematic diagram of an evaluation index recommendation process provided by an embodiment of this specification;

[0041] Figure 3 is a schematic diagram of another evaluation index recommendation process provided by an embodiment of this specification;

[0042] Figure 4 It is a structural schematic diagram of a verification evaluation index recommendation device for a fault detection model provided by an embodiment of this specification;

[0043] Figure 5 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0044] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0045] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0046] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0047] In this specification, a method for recommending verification and evaluation indicators of a fault detection model is provided. This specification also involves a device for recommending verification and evaluation indicators of a fault detection model, a computing device, a computer-readable storage medium, and a computer program, which are described in detail one by one in the following embodiments.

[0048] Figure 1 A flowchart of a method for recommending verification evaluation indicators of a fault detection model provided according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0049] Step 102: Acquire device operation information of the target device, wherein the device operation information includes usage condition information, device fault information, and data processing information of the target device.

[0050] Specifically, the target device may be a mechanical device.

[0051] The usage condition information of the target equipment may include engineering fields, equipment objects, usage conditions, and other usage background information.

[0052] Among them, the attribute parameters contained in the engineering field are usually the field type, and the field type refers to the industry field type to which the verification object belongs during the process of determining the test verification sample of the current verification system, such as aircraft, hydraulic machinery, wind turbines, ships, etc.

[0053] The attribute parameters contained in the equipment object are usually based on the object type, and the object type refers to the common fault components in the system object, such as the gears and bearings in the gearbox.

[0054] Operating conditions may include common environmental stresses and working stresses, etc. Environmental stresses may include temperature stress, humidity stress, vibration stress (maximum vibration, weighted vibration, minimum vibration, cruising continuous vibration, etc.), and working stresses may include electrical stress, speed, flow, pressure, load and other information.

[0055] Other usage background information mainly includes some background information not involved in the usage environment and operating conditions, such as constant speed conditions (single operating condition) / variable speed (multiple operating conditions) conditions of rotating machinery, marked sample conditions, single fault type / multiple fault types and other qualitative descriptions.

[0056] The equipment fault information of the target equipment may include fault type information and fault severity information. The attribute parameters included in the fault type information are diagnosable fault types, and the diagnosable fault types cover some common fault types of the target equipment. Taking the gearbox as an example, they include broken teeth, wear, crack faults of gears, inner ring, outer ring, and rolling element faults of bearings, etc. The attribute parameters included in the fault severity information are diagnosable fault severity, which is used to describe the diagnostic capability of the diagnostic scheme. It can diagnose whether the fault is an initial fault or a severe fault, so as to determine whether it meets the actual needs of the project.

[0057] The data processing information of the target device may include data transmission delay information (bandwidth, delay, transmission rate), data transmission packet loss information (packet loss rate, packet loss time, number of retransmissions), data transmission sampling rate fluctuation information (actual transmission rate, fluctuation and its impact on application performance) as well as CPU utilization, memory usage, disk I / O rate, network bandwidth, etc.

[0058] Step 104: Input the equipment operation information as an input set into the evaluation index recommendation model to obtain a coding vector of the input set.

[0059] Specifically, after obtaining the device operation information of the target device, the device operation information may be input into a pre-trained evaluation index recommendation model, so that the evaluation index recommendation model determines the evaluation index to be recommended for the target device according to the device operation information.

[0060] In an optional implementation, the method for recommending verification evaluation indicators of the fault detection model further includes:

[0061] Obtaining device operation information and multiple historical evaluation indicators corresponding to each of the multiple historical devices;

[0062] The device operation information corresponding to each historical device and the multiple historical evaluation indicators are input as sample data into the evaluation indicator recommendation model to be trained for training, so as to obtain the evaluation indicator recommendation model.

[0063] Furthermore, the step of inputting the device operation information corresponding to each historical device and the plurality of historical evaluation indicators as sample data into the evaluation indicator recommendation model to be trained for training includes:

[0064] Input the device operation information corresponding to each historical device and the multiple historical evaluation indicators as sample data into the evaluation indicator recommendation model to be trained;

[0065] Vectorizing the sample data using the evaluation index recommendation model to be trained to generate a corresponding sample encoding vector;

[0066] The plurality of historical devices are clustered based on the sample coding vectors by using a target clustering algorithm to generate at least two device categories.

[0067] Specifically, the equipment operation information corresponding to each historical device has the same information type as the equipment operation information corresponding to the aforementioned target device, that is, the equipment operation information corresponding to each historical device can also include engineering fields, equipment objects, operating conditions, and other usage background information. The historical evaluation indicators corresponding to each historical device can include fault detection rate, missed detection rate, false alarm rate, F1 weighted value, and mean square error, etc.

[0068] After obtaining the equipment operation information and multiple historical evaluation indicators corresponding to each historical equipment, the equipment operation information and multiple historical evaluation indicators corresponding to each historical equipment can be input as sample data into the evaluation indicator recommendation model to be trained to obtain the evaluation indicator recommendation model.

[0069] Since the database will store the evaluation data of various types of equipment as well as information such as the equipment usage environment and usage conditions, different equipment or different usage conditions will have different evaluation focuses. Therefore, the embodiments of this specification capture the equipment operation information of each historical device and the features in the historical evaluation indicators, and convert them into coding vectors through the evaluation indicator recommendation model to be trained. These coding vectors can effectively represent each historical device, that is, they can approximately uniquely identify the feature set of each historical device. The coding vectors are then used to train the evaluation indicator recommendation model to be trained, so that the evaluation indicator recommendation model can extract key information from the equipment data of the historical equipment and accurately obtain the similarity between each device.

[0070] In addition, when training the model, a clustering algorithm can be used to classify devices with high similarity into the same category to save subsequent computing costs. A clustering algorithm is an unsupervised learning method that can classify objects in a data set into several categories based on similarities and differences, so that objects in the same category have high similarity, while objects in different categories have low similarity. The embodiments of this specification can use a clustering algorithm to classify multiple historical devices into several categories, and the historical devices in each category have high similarity in evaluation indicators.

[0071] In the embodiment of this specification, the target clustering algorithm includes a K-means clustering algorithm.

[0072] The K-means clustering algorithm can classify multiple historical devices into different categories based on evaluation indicators. The rules and characteristics of similar evaluation indicators are also similar. After classifying them into the same category, it can provide support for subsequent evaluation indicator recommendations.

[0073] The Euclidean distance between different points in the K-means clustering algorithm is an indicator used to measure the similarity between different devices. In the K-means clustering algorithm, when the distance between different points and a certain point is close, the point will be classified into the same category as the point closest to it. The traditional K-means clustering algorithm first takes the centroid as the core, and then calculates the Euclidean distance from the remaining points to the centroid, so that the points close to the centroid are classified into the same category as the centroid, and so on to achieve classification.

[0074] The specific execution steps are as follows:

[0075] (1) Randomly select k historical devices from a given set of multiple historical devices as the centroid.

[0076] (2) For the remaining historical devices, calculate the distance from their encoding vector to the centroid, and group the historical devices close to the centroid into the same category as the corresponding centroid.

[0077] (3) Recalculate the centroid of each class.

[0078] (4) Repeat steps (2) to (3) until each clustering result no longer changes.

[0079] In practical applications, the target clustering algorithm may also be a K-means++ clustering algorithm or a K-modes clustering algorithm, which may be selected according to actual needs and is not limited here.

[0080] Step 106: Determine the similarity between the target device and each of the multiple historical devices based on the encoding vector, and determine and output the evaluation index to be recommended corresponding to the target device according to the similarity.

[0081] Specifically, after determining the coding vector of the target device, the evaluation index recommendation model can determine the similarity between the target device and each historical device based on the coding vector of the target device and the coding vectors corresponding to multiple historical devices, and determine the recommended evaluation index of the target device based on the similarity.

[0082] In an optional implementation, determining the similarity between the target device and a plurality of historical devices based on the encoding vector includes:

[0083] Determine a coding vector corresponding to each historical device in the plurality of historical devices;

[0084] The similarity between the encoding vector of the input set and the encoding vector corresponding to each historical device is calculated by a cosine similarity algorithm.

[0085] Further, the determining and outputting the evaluation index to be recommended corresponding to the target device according to the similarity includes:

[0086] Determining a maximum value among similarities between the target device and the plurality of historical devices;

[0087] The target historical device corresponding to the maximum value is determined, and the historical evaluation index corresponding to the target historical device is determined as the evaluation index to be recommended corresponding to the target device and outputted.

[0088] A schematic diagram of an evaluation index recommendation process provided in the embodiments of this specification is as follows Figure 2 shown.

[0089] After obtaining data such as the target device's operating conditions, operating environment, field type, signal type, number of paths, sample size, fault severity, fault type, CPU, memory, data transmission packet loss rate, and delay, mining can be performed based on this data. Specifically, this data is input into the evaluation index recommendation model, and the evaluation index recommendation model encodes this data to generate a corresponding encoding vector. The cosine similarity algorithm is used to calculate the angle between the encoding vector of the target device and the encoding vector of each historical device, thereby determining the similarity between the target device and each historical device based on the size of the angle, and then determining the recommended evaluation index corresponding to the target device based on the similarity.

[0090] Specifically, when determining the recommended evaluation indicator corresponding to the target device based on the similarity, the similarity between the target device and each historical device can be determined first, and then the maximum similarity value is selected from multiple similarities, and the target historical device corresponding to the maximum similarity value is determined, and then the historical evaluation indicator corresponding to the target historical device is determined as the recommended evaluation indicator corresponding to the target device.

[0091] Figure 2 The conventional indicators, group indicators and multi-condition indicators shown in are general descriptions of the evaluation indicators. As mentioned above, the historical evaluation indicators corresponding to each historical device may include at least two of the indicators such as fault detection rate, missed detection rate, false alarm rate, F1 weighted value and mean square error. For example, if the historical evaluation indicators corresponding to the target historical device are fault detection rate, missed detection rate and false alarm rate, then the evaluation indicators to be recommended corresponding to the target device are also fault detection rate, missed detection rate and false alarm rate.

[0092] In an optional implementation, determining the similarity between the target device and a plurality of historical devices based on the encoding vector includes:

[0093] Determine a central point device of each device category in the at least two device categories, and determine a coding vector of the central point device;

[0094] Classifying the target device into a target device category according to the encoding vector of the input set and the encoding vector of the central point device;

[0095] A similarity between the target device and historical devices included in the target device category is determined based on the encoding vector of the input set.

[0096] Further, the determining and outputting the evaluation index to be recommended corresponding to the target device according to the similarity includes:

[0097] determining a maximum value among similarities between the target device and historical devices included in the target device category;

[0098] The target historical device corresponding to the maximum value is determined, and the historical evaluation index corresponding to the target historical device is determined as the evaluation index to be recommended corresponding to the target device and outputted.

[0099] A schematic diagram of another evaluation index recommendation process provided in the embodiments of this specification is as follows Figure 3 shown.

[0100] Specifically, in the aforementioned embodiment, it is necessary to calculate the similarity between the target device and each historical device. In order to reduce the amount of calculation, the embodiment of this specification can first classify the target device into categories based on clustering each historical device and determining the recommended evaluation index corresponding to the target device.

[0101] Furthermore, based on the aforementioned embodiment of clustering multiple historical devices by using the K-means clustering algorithm, Figure 3 As shown in the figure, assuming that n device categories are generated after clustering, namely device category 1, device category 2, ..., device category n, then there is a central point device (centroid) in each device category. When the target device needs to be categorized, the central point device of each device category can be determined first, and the encoding vector of the central point device can be determined. Then, the distance between the encoding vector of the target device and the encoding vector of each central point device can be calculated. Then, based on the distance calculation result, the target device can be classified into the device category where the central point device closest to it is located. Figure 3 As shown, the target device is classified into device class i.

[0102] After the target device is classified, the similarity between the target device and each historical device contained in device class i can be calculated by using the cosine similarity algorithm based on the coding vector of the target device and the coding vector corresponding to the historical devices contained in device class i; then the largest similarity value is selected from multiple similarities, and the target historical device corresponding to the largest similarity value is determined, and then the historical evaluation index corresponding to the target historical device is determined as the recommended evaluation index corresponding to the target device and output.

[0103] In practical applications, the recommended evaluation index can be used to evaluate and verify the output result of the fault detection model, and the output result of the fault detection model can be the result generated by the fault detection model for fault diagnosis or detection of the target device.

[0104] In the embodiment of this specification, since the evaluation index recommendation model obtained through training can extract key information from the device data of historical devices and accurately obtain the similarity between each device, when there is a new target device, the evaluation index recommendation model can determine the similarity between the target device and each historical device based on the device operation information of the target device, and determine the evaluation index to be recommended for the target device based on the similarity.

[0105] Specifically, when a new target device needs to be introduced, the trained evaluation index recommendation model is first used to quickly classify the target device and determine the device category to which it belongs. This process helps to narrow the scope of subsequent similarity calculations, and similarity calculations only need to be performed within the device category to which the target device belongs. Within the device category, the cosine similarity calculation method is used between the encoding vectors of the target device and the historical device to evaluate the similarity between the target device and the historical device. This method not only reduces the amount of calculation, but also helps to improve the pertinence and accuracy of the similarity evaluation.

[0106] By performing information mining in the above manner, the output information that can be obtained may include a recommended evaluation indicator set suitable for selection, evaluation indicator results, reference ranges, and devices similar to the target device and verification cases, etc.

[0107] The embodiments of this specification use an evaluation index recommendation model based on information mining to mine and recommend evaluation indicators. Due to the diversity of mechanical and electronic product equipment, appropriate cases are used as references for different equipment and appropriate evaluation indicators are recommended for them. By deeply mining the intrinsic connection between each equipment and engineering practice, a more accurate and comprehensive evaluation system is constructed. This system not only considers basic information such as equipment type and fault model, but also considers differences in working conditions and characteristics of the engineering field to ensure that the selected evaluation indicators accurately reflect the evaluation standards required by the equipment, thereby improving the pertinence and effectiveness of equipment verification.

[0108] In addition, through information mining, the characteristics of equipment failures can be discovered from the data level, thereby optimizing the evaluation index recommendation model. By introducing information mining technology, a large amount of historical data can be fully utilized, and the existing verification and evaluation cases can be used as the basis for new equipment to be verified. The growing verification and evaluation data can continuously supplement the verification and evaluation case library and continuously improve the verification and evaluation information mining and recommendation capabilities. It can be seen that the mining of historical verification case data can provide indicator recommendations and case references for the verification and evaluation of new equipment, which is conducive to ensuring the accuracy of the evaluation index recommendation results of new equipment.

[0109] The embodiments of this specification obtain the device operation information of the target device, wherein the device operation information includes the operating condition information, device failure information and data processing information of the target device; input the device operation information as the input set into the evaluation index recommendation model to obtain the encoding vector of the input set; determine the similarity between the target device and each of the multiple historical devices based on the encoding vector, and determine and output the evaluation index to be recommended corresponding to the target device based on the similarity. By analyzing the specific characteristics and working environment of the device, the matching of the recommendation result with the actual situation of the device is achieved, and corresponding evaluation indicators are given to different types of devices under different working conditions, environments and other conditions, which is conducive to improving the accuracy of the recommendation results and verification results.

[0110] Corresponding to the above method embodiment, this specification also provides an embodiment of a verification evaluation index recommendation device for a fault detection model. Figure 4 FIG. 1 is a schematic diagram showing a structure of a verification evaluation index recommendation device for a fault detection model provided by an embodiment of the present specification. Figure 4 As shown, the device comprises:

[0111] The acquisition module 402 is configured to acquire device operation information of the target device, wherein the device operation information includes usage condition information, device failure information and data processing information of the target device;

[0112] An input module 404 is configured to input the device operation information as an input set into an evaluation index recommendation model to obtain a coding vector of the input set;

[0113] The output module 406 is configured to determine the similarity between the target device and each of the multiple historical devices based on the encoding vector, and determine and output the evaluation index to be recommended corresponding to the target device according to the similarity.

[0114] Optionally, the output module 406 is further configured to:

[0115] Determine a coding vector corresponding to each historical device in the plurality of historical devices;

[0116] The similarity between the encoding vector of the input set and the encoding vector corresponding to each historical device is calculated by a cosine similarity algorithm.

[0117] Optionally, the output module 406 is further configured to:

[0118] Determining a maximum value among similarities between the target device and the plurality of historical devices;

[0119] The target historical device corresponding to the maximum value is determined, and the historical evaluation index corresponding to the target historical device is determined as the evaluation index to be recommended corresponding to the target device and outputted.

[0120] Optionally, the verification evaluation index recommendation device of the fault detection model further includes a training module 408 configured to:

[0121] Obtaining device operation information and multiple historical evaluation indicators corresponding to each of the multiple historical devices;

[0122] The device operation information corresponding to each historical device and the multiple historical evaluation indicators are input as sample data into the evaluation indicator recommendation model to be trained for training, so as to obtain the evaluation indicator recommendation model.

[0123] Optionally, the training module 408 is further configured to:

[0124] Input the device operation information corresponding to each historical device and the multiple historical evaluation indicators as sample data into the evaluation indicator recommendation model to be trained;

[0125] Vectorizing the sample data using the evaluation index recommendation model to be trained to generate a corresponding sample encoding vector;

[0126] The plurality of historical devices are clustered based on the sample coding vectors by using a target clustering algorithm to generate at least two device categories.

[0127] Optionally, the output module 406 is further configured to:

[0128] Determine a central point device of each device category in the at least two device categories, and determine a coding vector of the central point device;

[0129] Classifying the target device into a target device category according to the encoding vector of the input set and the encoding vector of the central point device;

[0130] A similarity between the target device and historical devices included in the target device category is determined based on the encoding vector of the input set.

[0131] Optionally, the output module 406 is further configured to:

[0132] determining a maximum value among similarities between the target device and historical devices included in the target device category;

[0133] The target historical device corresponding to the maximum value is determined, and the historical evaluation index corresponding to the target historical device is determined as the evaluation index to be recommended corresponding to the target device and outputted.

[0134] The above is a schematic scheme of a verification and evaluation index recommendation device for a fault detection model of this embodiment. It should be noted that the technical scheme of the verification and evaluation index recommendation device for the fault detection model and the technical scheme of the verification and evaluation index recommendation method for the fault detection model mentioned above belong to the same concept, and the details not described in detail in the technical scheme of the verification and evaluation index recommendation device for the fault detection model can be found in the description of the technical scheme of the verification and evaluation index recommendation method for the fault detection model mentioned above.

[0135] Figure 5 The structure block diagram of a computing device 500 provided according to an embodiment of the present specification is shown. The components of the computing device 500 include but are not limited to a memory 510 and a processor 520. The processor 520 is connected to the memory 510 via a bus 530, and the database 550 is used to store data.

[0136] The computing device 500 also includes an access device 540 that enables the computing device 500 to communicate via one or more networks 560. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 540 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a World Wide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0137] In one embodiment of the present specification, the above components of the computing device 500 and Figure 5 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 5 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0138] The computing device 500 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. The computing device 500 may also be a mobile or stationary server.

[0139] The processor 520 is used to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the verification evaluation index recommendation method of the above-mentioned fault detection model.

[0140] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned method for recommending verification and evaluation indicators of a fault detection model belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be found in the description of the technical scheme of the above-mentioned method for recommending verification and evaluation indicators of a fault detection model.

[0141] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned method for recommending verification evaluation indicators of the fault detection model.

[0142] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned method for recommending verification and evaluation indicators of fault detection models belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be found in the description of the technical scheme of the above-mentioned method for recommending verification and evaluation indicators of fault detection models.

[0143] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned method for recommending verification evaluation indicators of the fault detection model.

[0144] The above is a schematic scheme of a computer program of this embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the above-mentioned method for recommending verification and evaluation indicators of a fault detection model are of the same concept, and the details not described in detail in the technical scheme of the computer program can be found in the description of the technical scheme of the above-mentioned method for recommending verification and evaluation indicators of a fault detection model.

[0145] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0146] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0147] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0148] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0149] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A method for recommending verification and evaluation indicators of a fault detection model, comprising: Acquire device operation information of the target device, wherein the device operation information includes usage condition information, device failure information, and data processing information of the target device; Inputting the equipment operation information as an input set into an evaluation index recommendation model to obtain a coding vector of the input set; The similarity between the target device and each of the multiple historical devices is determined based on the encoding vector, and the evaluation index to be recommended corresponding to the target device is determined and output according to the similarity.

2. According to the method for recommending verification evaluation indicators of a fault detection model according to claim 1, the determining the similarity between the target device and a plurality of historical devices based on the encoding vector comprises: Determine a coding vector corresponding to each historical device in the plurality of historical devices; The similarity between the encoding vector of the input set and the encoding vector corresponding to each historical device is calculated by a cosine similarity algorithm.

3. The verification evaluation index recommendation method for a fault detection model according to claim 1 or 2, wherein the step of determining and outputting the evaluation index to be recommended corresponding to the target device according to the similarity comprises: Determining a maximum value among similarities between the target device and the plurality of historical devices; The target historical device corresponding to the maximum value is determined, and the historical evaluation index corresponding to the target historical device is determined as the evaluation index to be recommended corresponding to the target device and outputted.

4. The method for recommending verification and evaluation indicators of a fault detection model according to any one of claims 1 to 3, further comprising: Acquire device operation information and multiple historical evaluation indicators corresponding to each historical device in the multiple historical devices; The device operation information corresponding to each historical device and the multiple historical evaluation indicators are input as sample data into the evaluation indicator recommendation model to be trained for training, so as to obtain the evaluation indicator recommendation model.

5. According to the method for recommending verification evaluation indicators of a fault detection model in claim 4, the step of inputting the device operation information corresponding to each historical device and the plurality of historical evaluation indicators as sample data into the evaluation indicator recommendation model to be trained for training comprises: Input the device operation information corresponding to each historical device and the multiple historical evaluation indicators as sample data into the evaluation indicator recommendation model to be trained; Vectorizing the sample data using the evaluation index recommendation model to be trained to generate a corresponding sample encoding vector; The plurality of historical devices are clustered based on the sample coding vectors by using a target clustering algorithm to generate at least two device categories.

6. According to the method for recommending verification evaluation indicators of a fault detection model according to claim 5, the determining the similarity between the target device and a plurality of historical devices based on the encoding vector comprises: Determine a central point device of each device category in the at least two device categories, and determine a coding vector of the central point device; Classifying the target device into a target device category according to the encoding vector of the input set and the encoding vector of the central point device; A similarity between the target device and historical devices included in the target device category is determined based on the encoding vector of the input set.

7. The method for recommending verification evaluation indicators of a fault detection model according to claim 6, wherein the step of determining and outputting the evaluation indicator to be recommended corresponding to the target device according to the similarity comprises: determining a maximum value among similarities between the target device and historical devices included in the target device category; The target historical device corresponding to the maximum value is determined, and the historical evaluation index corresponding to the target historical device is determined as the evaluation index to be recommended corresponding to the target device and outputted.

8. A verification evaluation index recommendation device for a fault detection model, comprising: An acquisition module is configured to acquire device operation information of a target device, wherein the device operation information includes usage condition information, device failure information, and data processing information of the target device; An input module is configured to input the device operation information as an input set into an evaluation index recommendation model to obtain a coding vector of the input set; The output module is configured to determine the similarity between the target device and each of the multiple historical devices based on the encoding vector, and determine and output the evaluation index to be recommended corresponding to the target device according to the similarity.

9. A computing device comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method for recommending verification and evaluation indicators of the fault detection model described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for recommending verification and evaluation indicators of a fault detection model according to any one of claims 1 to 7.

Images