Abnormality detection method and device, electronic equipment and storage medium

Abstract

The invention provides an anomaly detection method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a test instruction for equipment to be tested; wherein the to-be-tested equipment can run a test model; based on the test instruction, determining a test problem for a to-be-tested device; testing a test model of the to-be-tested equipment by adopting the test problem to obtain a test index measured value for the to-be-tested equipment; obtaining a target standard value of the test index based on the measured value of the test index and the initial standard value of the test index; based on the target standard value and the test index measured value, obtaining a detection result for the to-be-detected equipment; the detection result is used for representing whether the performance of the to-be-detected equipment is abnormal or not. Efficient anomaly detection of the electronic equipment is realized.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an anomaly detection method, device, electronic device and storage medium. Background Art

[0002] One or more AI models can usually be run on electronic devices such as laptops for intelligent question and answer. The test indicators obtained by testing the AI ​​model running on the electronic device can reflect whether the performance of the electronic device is abnormal. In the related art, the AI ​​model of the electronic device is usually tested manually, which is time-consuming and difficult to guarantee accuracy. Therefore, how to achieve efficient anomaly detection of electronic device performance has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The present application provides an anomaly detection method, device, electronic device and storage medium to at least solve the above technical problems existing in the prior art.

[0004] According to a first aspect of the present application, a method for detecting anomalies is provided, the method comprising:

[0005] Obtaining a test instruction for a device under test, wherein the device under test is capable of running a test model;

[0006] Based on the test instruction, determining a test problem for the device under test;

[0007] Using the test problem, testing the test model of the device to be tested, and obtaining the actual measured value of the test index of the device to be tested;

[0008] Based on the actual measured value of the test indicator and the initial standard value of the test indicator, a target standard value of the test indicator is obtained;

[0009] Based on the target standard value and the actual measured value of the test index, a test result for the device under test is obtained; the test result is used to characterize whether the performance of the device under test is abnormal.

[0010] In the above solution, the step of determining the test problem for the device under test based on the test instruction includes:

[0011] Based on the test instructions and the preset test question mapping table, the test questions for the device under test are determined.

[0012] In the above solution, before obtaining the actual measured value of the test index for the device under test, the method further includes:

[0013] Determine whether the response time of the test model of the device under test to the test question is less than a preset time;

[0014] When the response time of the test model to the test question is less than a preset time, a measured value of the test indicator for the device under test is obtained.

[0015] In the above scheme, the target standard value of the test indicator is obtained based on the actual value of the test indicator and the initial standard value of the test indicator, including:

[0016] Based on the actual measured value of the test indicator and the configuration information of the device under test, obtaining the correlation between the configuration information of the device under test and the test indicator;

[0017] Based on the correlation, the actual measured value of the test indicator and the initial standard value of the test indicator, a target standard value of the test indicator is obtained.

[0018] In the above scheme, the number of the measured values ​​of the test index is multiple; the test result for the device under test is obtained based on the target standard value and the measured value of the test index, including:

[0019] Compare the actual measured value of each test indicator with the target standard value. When the actual measured value of each test indicator among the multiple actual measured values ​​of the test indicators is less than the target standard value, a test result indicating that the performance of the device under test is normal is obtained.

[0020] When at least one test indicator value among the multiple test indicator actual measured values ​​is not less than the target standard value, a detection result for abnormal performance of the device under test is obtained.

[0021] The above scheme also includes:

[0022] When the response time of the test model to the test question is greater than or equal to the preset time,

[0023] Determine whether the device under test is operating abnormally;

[0024] When the device under test operates abnormally, a detection result of the abnormal performance of the device under test is obtained.

[0025] According to a second aspect of the present application, there is provided an abnormality detection device, the device comprising:

[0026] A first acquisition unit is used to acquire a test instruction for a device under test; wherein the device under test is capable of running a test model;

[0027] A first determining unit, configured to determine a test problem for the device under test based on the test instruction;

[0028] A second acquisition unit is used to use the test problem to test the test model of the device to be tested, and obtain the actual measured value of the test index of the device to be tested;

[0029] A third acquisition unit, configured to obtain a target standard value of the test indicator based on the actual value of the test indicator and the initial standard value of the test indicator;

[0030] The fourth acquisition unit is used to obtain a test result for the device under test based on the target standard value and the actual value of the test indicator; the test result is used to indicate whether the performance of the device under test is abnormal.

[0031] In the above solution, the first determining unit is used to determine the test questions for the device under test based on the test instructions and a preset test question mapping table.

[0032] According to a third aspect of the present application, an electronic device is provided, including:

[0033] at least one processor; and

[0034] a memory communicatively connected to the at least one processor; wherein,

[0035] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the present application.

[0036] According to a fourth aspect of the present application, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described in the present application.

[0037] In the present application, a test instruction for the device under test is obtained; wherein the device under test can run a test model; based on the test instruction, a test question for the device under test is determined; using the test question, the test model of the device under test is tested to obtain a measured value of the test index for the device under test; based on the measured value of the test index and the initial standard value of the test index, a target standard value of the test index is obtained; based on the target standard value and the measured value of the test index, a test result for the device under test is obtained; the test result is used to characterize whether the performance of the device under test is abnormal. The scheme of the present application is an automated scheme that does not require human intervention and can achieve efficient abnormality detection of electronic equipment performance.

[0038] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become readily understood. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, wherein:

[0040] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts.

[0041] Figure 1 A schematic diagram of the implementation process of the abnormality detection method according to the embodiment of the present application is shown;

[0042] Figure 2 A schematic block diagram showing the interaction between the client and the server in an embodiment of the present application is shown;

[0043] Figure 3 A schematic diagram showing an application of the anomaly detection method according to an embodiment of the present application is shown;

[0044] Figure 4 A schematic diagram of the structure of an abnormality detection device according to an embodiment of the present application is shown;

[0045] Figure 5 A schematic diagram of the structure of an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0046] In order to make the purpose, features, and advantages of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0047] It is understandable that before electronic devices such as laptops leave the factory, they are usually tested for abnormal performance. Considering that electronic devices such as laptops can run intelligent test models, by testing the test model of the electronic device, test indicators reflecting the performance of the electronic device can be obtained, and then the performance of the electronic device can be determined to be abnormal. In the related art, each electronic device is tested one by one manually, but due to the large number of electronic devices tested in batches, the large number of test models run by each electronic device, the large number of test functions of each test model, and the large number of test questions for each test function, the overall test is time-consuming and inefficient. In addition, to obtain the test index, its value needs to be compared with the standard index value to determine whether the performance of the electronic device is normal or abnormal. However, the standard index value in the related art is usually taken according to artificial experience, and the accuracy of the test result of whether the performance of the electronic device is abnormal by comparing the value of the test index with the standard index value is difficult to guarantee.

[0048] The embodiment of the present application provides an abnormality detection method, which obtains a test instruction for a device under test; wherein the device under test can run a test model; based on the test instruction, a test question for the device under test is determined; using the test question, the test model of the device under test is tested to obtain a measured value of a test indicator for the device under test; based on the measured value of the test indicator and the initial standard value of the test indicator, a target standard value of the test indicator is obtained; based on the target standard value and the measured value of the test indicator, a test result for the device under test is obtained; the test result is used to characterize whether the performance of the device under test is abnormal. The solution of the present application is an automated solution, which does not require human participation, and can automatically update the standard value of the test indicator, thereby ensuring the accuracy and rate of abnormality detection of electronic device performance, and can achieve efficient abnormality detection of electronic devices.

[0049] The present application embodiment provides an abnormality detection method, such as Figure 1 As shown, the method includes:

[0050] S101: Acquire a test instruction for a device under test; wherein the device under test is capable of running a test model.

[0051] In this step, the device to be tested is an electronic device that can run the test model and is to be tested for performance anomalies, such as a laptop computer. The number of devices to be tested is one or more. The test model includes an AI (Artificial Intelligence) model, which is mainly used for intelligent question and answer. The intelligent question and answer types (functions) of the test model include text-generated text, picture-generated picture, text-generated picture, and document summary, etc. Exemplarily, text-generated text means that when the input content is text type, the test model gives a text type response. Picture-generated picture means that when the input content is picture type, the test model gives a picture type response. Text-generated picture means that when the input content is text type, the test model gives a picture type response. Document summary means that when a document is input, the test model gives a summary response.

[0052] The test instruction is an instruction input by the client user for testing the device under test, including the test model name and the test model function for the device under test, such as the device under test can run three test models (model 1 to model 3), and the function of each test model includes at least one of the intelligent question and answer functions described above. Then the test instruction may be to specify the test of the Wenshengwen function of model 1. In addition, the test instruction also includes the initial standard value of the test indicator. In the embodiment of the present application, the test indicator includes the response time of the test model (i.e., the time to give a reply) and the system occupancy rate after the test model responds, such as CPU (Central Processing Unit) occupancy rate, GPU (Graphics Processing Unit) occupancy rate, memory occupancy rate and NPU (Embedded Neural Network Processor, Neural Processing Unit) occupancy rate, etc. The initial standard value of the test indicator is the user input experience value of each test indicator.

[0053] S102: Determine test questions for the device under test based on the test instruction.

[0054] In this step, the embodiment of the present application is applied to the server side, such as Figure 2 As shown, after the server obtains the test instruction for the device to be tested input by the user of the client (i.e., the device to be tested end), the server selects the test items (when the device to be tested is a laptop, the test items can be different models of laptops), and replaces the configuration file (such as the selection of the test model, the selection of the test function) according to the test instruction, selects a certain number of devices to be tested (not all laptops of the same model may participate in the test) and issues corresponding test questions to them. In the embodiment of the present application, considering the standardization of the test questions, the test questions are pre-set questions. The number of test questions can be one or more, preferably more than one. Exemplarily, assuming that as described above, the test instruction is to test the Wenshengwen function of model 1, then based on the instruction, a plurality of test questions pre-set for the Wenshengwen function of model 1 are issued to the device to be tested, so as to test the test model 1 of the device to be tested.

[0055] S103: Using the test problem, testing the test model of the device to be tested, and obtaining actual test index values ​​of the device to be tested.

[0056] In this step, after determining the test problem for the device under test in step S102, refer to Figure 2As shown, the obtained test questions are used to test the test model of the device under test (client), that is, the test questions are used as the input of the test model of the device under test, so that the test model responds to the test questions, thereby obtaining the actual measured values ​​of the test indicators that can reflect the performance of the device under test, such as the response time of the test model and the system occupancy rate after the test model responds to the test questions. The client can automatically capture and recognize images, such as automatically obtaining the resolution and zoom ratio of the display of the device under test, modeling key operation buttons, screenshot large models, and positioning key focuses (such as input / output windows, copy buttons, document / image upload buttons, document summary buttons, etc.) according to the operation step flow action search buttons and modeling picture comparison, and automatically transmit the obtained test data (including the actual measured values ​​of the test indicators) back to the server side, and the server side can view the initial test state of the device under test (whether it is normal or abnormal compared with the initial standard value), test indicator monitoring (distribution trend charts of all response times and system occupancy rates respectively), data statistical analysis (table statistics of the test indicators obtained by the test model for each test question, so as to obtain the target standard value of the test indicators) and log download analysis.

[0057] S104: Obtaining a target standard value of the test indicator based on the actual measured value of the test indicator and the initial standard value of the test indicator.

[0058] In this step, the target standard value of the test indicator is the updated standard value, which is more accurate and representative than the initial standard value of the test indicator, and can make a more accurate performance abnormality judgment for the device under test. The target standard value of the test indicator is obtained based on the actual measured value of the test indicator and the initial standard value of the test indicator. For the specific process, please refer to the detailed description of the relevant parts below, which will not be repeated here.

[0059] S105: Based on the target standard value and the actual value of the test index, a test result for the device under test is obtained; the test result is used to indicate whether the performance of the device under test is abnormal.

[0060] In this step, each time a test question is tested, a group of test index measured values ​​(response time and system occupancy rate) will be generated. By comparing the test index measured values ​​of each group with their corresponding target standard values, the test results for the device under test can be obtained, that is, it can be determined whether the performance of the device under test is normal or abnormal. For the specific process of obtaining the test results, please refer to the detailed description of the relevant parts below, which will not be repeated here.

[0061] In the scheme shown in steps S101 to S105, a test instruction for the device under test is obtained; wherein the device under test can run a test model; based on the test instruction, a test question for the device under test is determined; using the test question, the test model of the device under test is tested to obtain the actual measured value of the test index for the device under test; based on the actual measured value of the test index and the initial standard value of the test index, a target standard value of the test index is obtained; based on the target standard value and the actual measured value of the test index, a test result for the device under test is obtained; the test result is used to characterize whether the performance of the device under test is abnormal. The scheme of the present application is an automated scheme that does not require human participation, and can automatically update the standard value of the test index, thereby ensuring the accuracy and rate of abnormal performance detection of electronic equipment, and enabling efficient abnormal detection of electronic equipment.

[0062] In an optional solution, determining the test problem for the device under test based on the test instruction includes:

[0063] Based on the test instructions and the preset test question mapping table, the test questions for the device under test are determined.

[0064] In the present application, there is a preset mapping relationship between test instructions and test questions, that is, each test instruction has a corresponding test question. The user inputs the test instruction in the form of coded instructions, traverses the preset test question mapping table, finds the test question corresponding to the test instruction and uses it as the test question for the device to be tested. Compared with the related art, there is no need to manually type in the test question, and the test question can be automatically issued, thereby improving the efficiency of the test.

[0065] In an optional solution, before obtaining the actual measured value of the test indicator for the device under test, the method further includes:

[0066] Determine whether the response time of the test model of the device under test to the test question is less than a preset time;

[0067] When the response time of the test model to the test question is less than a preset time, a measured value of the test indicator for the device under test is obtained.

[0068] In this application, reference Figure 3As shown, after determining the test questions for the device under test based on the test instructions and the preset test question mapping table, the corresponding model (model 1, model 2...model P) is issued through the program to determine the test questions and log in to find its specific test functions (function 1 to function 4). The preset time is the time preset for the test model to test each test question, for example, 30 seconds is preset as the approximate time for the test model of the device under test to respond to a test question. The test model of the device under test responds to all test questions one by one. When the response time of the test model to each test question is less than the preset time, such as the test model gives a reply to test question 1 within the preset 30 seconds, the actual response time of the test model to test question 1 at this time and the actual system occupancy at this time are obtained. If the overall preset test time is not reached at this time, the test model continues to respond to test question 2, test question 3..., and each time a test question is responded to within the preset time, the actual response time and actual system occupancy for the test question are obtained once. Until the overall preset test time is reached, the actual measured value of the test index is used to determine the target standard value of the test index and to determine whether it meets the target standard value, and then determine whether the performance of the device under test is abnormal. If the target standard value is met, the performance of the device under test is normal. If the target standard value is not met, the performance of the device under test is abnormal (the specific determination process of whether the performance of the device under test is abnormal or normal, please refer to the following relevant instructions for obtaining the test results of the device under test, which will not be repeated). In an optional scheme, a tolerance time (such as 5 minutes) can also be set for the test model when testing each test question. In the case that the test model does not give a response to a certain test question within 30 seconds, if the test model can give a response to the test question within the tolerance time, the actual response time and actual system occupancy rate for the test question are obtained, and it is considered that the performance of the test model is abnormal for the test question, and the next test question is continued to be tested from the time point when the test model gives a response to the test question. If the test model does not give a response to the test question within the tolerance time, the test of this test question is terminated, a timeout is recorded, and the performance of the test model is considered to be abnormal for the test question, and then the next test question is continued to be tested. It provides a data basis for efficient performance anomaly detection of the equipment under test.

[0069] In an optional solution, obtaining the target standard value of the test indicator based on the actual measured value of the test indicator and the initial standard value of the test indicator includes:

[0070] Based on the actual measured value of the test indicator and the configuration information of the device under test, obtaining the correlation between the configuration information of the device under test and the test indicator;

[0071] Based on the correlation, the actual measured value of the test indicator and the initial standard value of the test indicator, a target standard value of the test indicator is obtained.

[0072] In the embodiment of the present application, the configuration information of the device under test includes hardware configuration information and software configuration information. Among them, the hardware configuration information includes the model of the CPU, the size of the memory, etc. The software configuration information includes the name of the test model, the test function of the test model, the test questions corresponding to the test functions, etc. Considering that the configuration information of the device under test is different, the response time to the test question and the system occupancy rate are also different. In the related art, only the empirical value is set artificially as the standard value of the test index, and the influence of different configurations on the measured value of the test index is not taken into account. The embodiment of the present application is based on different configuration information, and the standard value (target standard value) of the test index corresponding to the different configuration information can be automatically updated, so that the abnormal detection result of the device under test is more accurate. In order to ensure the calculation accuracy of the target standard value, the embodiment of the present application screens the measured value of the test index based on the initial standard value (eliminating the measured value of the test index whose measured value is greater than the initial standard value), and based on the measured value of the test index obtained after screening and the configuration information of the device under test, the correlation between each configuration information of the device under test and the test index is calculated according to the following formula (1):

[0073] y=β0+β1x1+β2x2+…+β n x n +ε formula (1)

[0074] Among them, y is the dependent variable, which represents the actual measured value of the test index obtained after screening. n is the independent variable, which indicates the code corresponding to the configuration information of the device under test. For example, x1 is 001, which indicates the CPU model, and x2 is 002, which indicates the memory size. ε is the error term. β0~β n is the regression coefficient, which indicates the influence of the independent variable on the dependent variable, that is, the correlation between different types of hardware configuration information and the actual measured values ​​of the test indicators. This is equivalent to substituting the configuration information corresponding to all the measured values ​​of the test indicators obtained after screening into formula (1) to jointly obtain ε and β0~β n The value of .

[0075] After obtaining the correlation between different configuration information and the measured value of the test index through formula (1), the specific values ​​of the configuration information ranked in the top m (m is greater than or equal to 1, which is customized by the user according to the actual situation) are substituted into formula (1) to obtain the corresponding standard prediction values ​​under various specific configurations. This is equivalent to substituting all the configuration information involved in formula (1) to obtain the correlation and error term, and after obtaining the correlation, the configuration information with higher correlation is given a specific value, and other configuration information with lower correlation is automatically given values ​​by big data. The standard prediction values ​​corresponding to different configuration information can be obtained in a targeted manner. For example, the standard prediction values ​​(standard response time prediction value, standard system occupancy prediction value) corresponding to the configuration information of CPU model A, test model 1, and test function Wensheng diagram can be obtained in a targeted manner. The target standard values ​​corresponding to different configuration information can be calculated by formula (2):

[0076]

[0077] Where W is the confidence interval of the target standard value. is the standard prediction value corresponding to a certain set of configuration information. For the specific acquisition process, see the above description. t is the critical value of the normal distribution of the standard prediction values ​​corresponding to all groups of different configuration information. The standard prediction value corresponding to different configuration information of all groups The standard error of the test indicator. The confidence interval of the target standard value of the test indicator corresponding to different specific configuration information can be obtained through formula (2). The maximum value in the confidence interval is used as the target standard value of the test indicator corresponding to different configuration information, which can make the abnormal detection results of the device under test more representative and universal.

[0078] In an optional solution, the number of the measured values ​​of the test index is multiple; the test result for the device to be tested is obtained based on the target standard value and the measured value of the test index, including:

[0079] Compare the actual measured value of each test indicator with the target standard value. When the actual measured value of each test indicator among the multiple actual measured values ​​of the test indicators is less than the target standard value, a test result indicating that the performance of the device under test is normal is obtained.

[0080] When at least one of the multiple test indicator measured values ​​is not less than the target standard value, a detection result of abnormal performance of the device under test is obtained.

[0081] In this application, a test function of any test model usually corresponds to multiple test problems, and the test model will produce a set of test index measured values ​​(response time, system occupancy rate) for any test problem. Since the number of test models of the device under test may be multiple, there may also be multiple test functions corresponding to a test model, so the number of test index measured values ​​obtained for a device under test is also multiple. Each test index measured value is compared with the target standard value obtained above. When each test index measured value in multiple test index measured values ​​is less than the target standard value (response time is less than the target standard value of response time, system occupancy rate is less than the target standard value of system occupancy rate), it is considered that the performance of the device under test is normal. When there is at least one test index measured value not less than the target standard value, it is considered that the performance of the device under test is abnormal. In addition, it is possible to determine which specific configuration information causes performance abnormality based on the test index measured value that is not less than the target standard value, which provides a priori basis for subsequent performance improvement.

[0082] In an optional solution, it also includes:

[0083] When the response time of the test model to the test question is greater than or equal to the preset time,

[0084] Determine whether the device under test is operating abnormally;

[0085] When the device under test operates abnormally, a detection result of the abnormal performance of the device under test is obtained.

[0086] In this application, reference Figure 3 As shown in the figure, when the response time of the test model to a certain test question is greater than or equal to the preset time, it is determined whether the device under test has an operation anomaly such as software freezing. If the device under test has an operation anomaly, it is directly considered that the performance of the device under test is abnormal. If there is no operation anomaly, a timeout is recorded and the test index value for the device under test is continued. The solution is simple and easy to implement, and can achieve efficient anomaly detection for the performance of the device under test.

[0087] The present application embodiment provides an abnormality detection device, such as Figure 4 As shown, the device comprises:

[0088] A first acquisition unit 401 is used to acquire a test instruction for a device under test, wherein the device under test is capable of running a test model;

[0089] A first determining unit 402, configured to determine a test problem for the device under test based on the test instruction;

[0090] The second acquisition unit 403 is used to use the test problem to test the test model of the device to be tested, and obtain the actual measured value of the test index of the device to be tested;

[0091] A third obtaining unit 404 is used to obtain a target standard value of the test indicator based on the actual value of the test indicator and the initial standard value of the test indicator;

[0092] The fourth acquisition unit 405 is used to obtain a test result for the device under test based on the target standard value and the actual test index value; the test result is used to indicate whether the performance of the device under test is abnormal.

[0093] In an optional solution, the first determining unit 402 is used to determine the test questions for the device under test based on the test instructions and a preset test question mapping table.

[0094] In an optional solution, it also includes:

[0095] The fifth acquisition unit is used to determine whether the response time of the test model of the device under test to the test question is less than the preset time; when the response time of the test model to the test question is less than the preset time, the actual measured value of the test indicator for the device under test is obtained.

[0096] In an optional scheme, the third acquisition unit 404 is used to obtain the correlation between the configuration information of the device to be tested and the test indicator based on the actual measured value of the test indicator and the configuration information of the device to be tested; and obtain the target standard value of the test indicator based on the correlation, the actual measured value of the test indicator and the initial standard value of the test indicator.

[0097] In an optional scheme, the number of the actual measured values ​​of the test indicators is multiple; the fourth acquisition unit 405 is used to compare the actual measured value of each test indicator with the target standard value, and when the actual measured value of each test indicator among the multiple actual measured values ​​of the test indicators is less than the target standard value, a detection result that the performance of the device under test is normal is obtained; when there is at least one actual measured value of the test indicator among the multiple actual measured values ​​of the test indicators that is not less than the target standard value, a detection result that the performance of the device under test is abnormal is obtained.

[0098] In an optional scheme, the fifth acquisition unit is used to determine whether the device under test operates abnormally when the response time of the test model to the test question is greater than or equal to a preset time; when the device under test operates abnormally, obtain a detection result of the abnormal performance of the device under test.

[0099] It should be noted that the anomaly detection device in the embodiment of the present application solves the problem based on a principle similar to that of the aforementioned anomaly detection method. Therefore, the implementation process, implementation principle, and beneficial effects of the anomaly detection device can all be referred to the description of the implementation process, implementation principle, and beneficial effects of the aforementioned method, and the repeated parts will not be repeated.

[0100] According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.

[0101] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0102] like Figure 5 As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0103] Multiple components in the electronic device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the electronic device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0104] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as anomaly detection methods. For example, in some embodiments, the anomaly detection method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the anomaly detection method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the anomaly detection method in any other appropriate manner (e.g., by means of firmware).

[0105] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0106] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0107] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0108] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer 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 pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the 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 input, voice input, or tactile input).

[0109] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may 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), and the Internet.

[0110] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0111] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0112] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0113] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An anomaly detection method, characterized in that: The method comprises: Obtaining a test instruction for a device under test, wherein the device under test is capable of running a test model; Based on the test instruction, determining a test problem for the device under test; Using the test problem, testing the test model of the device to be tested, and obtaining the actual measured value of the test index of the device to be tested; Based on the actual measured value of the test indicator and the initial standard value of the test indicator, a target standard value of the test indicator is obtained; Based on the target standard value and the actual measured value of the test index, a test result for the device under test is obtained; the test result is used to characterize whether the performance of the device under test is abnormal.

2. The method according to claim 1, characterized in that The step of determining a test problem for the device under test based on the test instruction includes: Based on the test instructions and the preset test question mapping table, the test questions for the device under test are determined.

3. The method according to claim 1, characterized in that Before obtaining the actual measured value of the test index for the device under test, the method further includes: Determine whether the response time of the test model of the device under test to the test question is less than a preset time; When the response time of the test model to the test question is less than a preset time, a measured value of the test indicator for the device under test is obtained.

4. The method according to any one of claims 1 to 3, characterized in that: The step of obtaining a target standard value of the test indicator based on the actual value of the test indicator and the initial standard value of the test indicator comprises: Based on the actual measured value of the test indicator and the configuration information of the device under test, obtaining the correlation between the configuration information of the device under test and the test indicator; Based on the correlation, the actual measured value of the test indicator and the initial standard value of the test indicator, a target standard value of the test indicator is obtained.

5. The method according to claim 4, characterized in that The number of the measured values ​​of the test index is multiple; the test result for the device under test is obtained based on the target standard value and the measured value of the test index, including: Compare the actual measured value of each test indicator with the target standard value. When the actual measured value of each test indicator among the multiple actual measured values ​​of the test indicators is less than the target standard value, a test result indicating that the performance of the device under test is normal is obtained. When at least one of the multiple test indicator measured values ​​is not less than the target standard value, a detection result of abnormal performance of the device under test is obtained.

6. The method according to claim 3, characterized in that Also includes: When the response time of the test model to the test question is greater than or equal to the preset time, Determine whether the device under test is operating abnormally; When the device under test operates abnormally, a detection result of the abnormal performance of the device under test is obtained.

7. An abnormality detection device, characterized in that: The device comprises: A first acquisition unit is used to acquire a test instruction for a device under test; wherein the device under test is capable of running a test model; A first determining unit, configured to determine a test problem for the device under test based on the test instruction; A second acquisition unit is used to use the test problem to test the test model of the device to be tested, and obtain the actual measured value of the test index of the device to be tested; A third acquisition unit, configured to obtain a target standard value of the test indicator based on the actual value of the test indicator and the initial standard value of the test indicator; The fourth acquisition unit is used to obtain a test result for the device under test based on the target standard value and the actual value of the test indicator; the test result is used to indicate whether the performance of the device under test is abnormal.

8. The device according to claim 7, characterized in that The first determining unit is used to determine the test questions for the device under test based on the test instructions and a preset test question mapping table.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to make a computer execute the method according to any one of claims 1-6.

Images