Product failure reproduction method and device, computer equipment, medium and program product

Abstract

The invention relates to a product failure reproduction method and device, computer equipment, a medium and a program product. The method comprises the following steps: acquiring historical use data of a target product to be subjected to failure reproduction, wherein the target product is an unstable failure product which has failed; based on the historical use data, selecting a currently detected target stress type from the plurality of candidate stress types, and determining a corresponding target stress parameter, the target stress type and the target stress parameter being used for setting a current test condition for reproducing the test equipment; and when the target product in the reproduction test equipment runs under the test condition, obtaining the test data of the target product, and determining the failure reproduction result of the target product based on the test data so as to improve the product failure reproduction accuracy.

Description

Technical Field

[0001] The present application relates to the field of testing technology, and in particular to a product failure reproduction method, apparatus, computer equipment, medium, and program product. Background Art

[0002] With the rapid development of electronic technology, the application of electronic products is becoming increasingly widespread. However, electronic product failures are becoming increasingly common, seriously affecting the stability and reliability of the equipment. In particular, unstable failures (failures that do not reproduce) are becoming increasingly prominent, necessitating the need to reproduce electronic product failures.

[0003] In related technologies, failures of electronic products are usually reproduced through offline testing. However, it is difficult to accurately reproduce failure scenarios using offline methods, that is, there is a problem of low accuracy in failure reproduction. Summary of the Invention

[0004] Based on this, it is necessary to provide a product failure reproduction method, apparatus, computer equipment, medium and program product that can improve the accuracy of failure reproduction in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for reproducing product failure, comprising:

[0006] Obtain historical usage data of a target product for which failure reproduction is to be performed, wherein the target product is an unstable failure product that has experienced failure;

[0007] Based on the historical usage data, a target stress type currently being detected is selected from a plurality of candidate stress types, and corresponding target stress parameters are determined, wherein the target stress type and the target stress parameters are used to set a current test condition of the reproducing test device;

[0008] When the target product in the replication test device is operated under the test conditions, test data of the target product is acquired, and a failure replication result of the target product is determined based on the test data.

[0009] In a second aspect, the present application further provides a product failure reproduction device, comprising:

[0010] An acquisition module is used to acquire historical usage data of a target product for which failure reproduction is to be performed, wherein the target product is an unstable failure product that has experienced failure;

[0011] a first determination module, configured to select a target stress type currently being detected from a plurality of candidate stress types based on the historical usage data, and determine corresponding target stress parameters, wherein the target stress type and the target stress parameters are used to set current test conditions of the replication test device;

[0012] The second determining module is configured to obtain test data of the target product when the target product in the recurrence test device operates under the test conditions, and determine a failure recurrence result of the target product based on the test data.

[0013] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0014] Obtain historical usage data of a target product for which failure reproduction is to be performed, wherein the target product is an unstable failure product that has experienced failure;

[0015] Based on the historical usage data, a target stress type currently being detected is selected from a plurality of candidate stress types, and corresponding target stress parameters are determined, wherein the target stress type and the target stress parameters are used to set a current test condition of the reproducing test device;

[0016] When the target product in the replication test device is operated under the test conditions, test data of the target product is acquired, and a failure replication result of the target product is determined based on the test data.

[0017] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0018] Obtain historical usage data of a target product for which failure reproduction is to be performed, wherein the target product is an unstable failure product that has experienced failure;

[0019] Based on the historical usage data, a target stress type currently being detected is selected from a plurality of candidate stress types, and corresponding target stress parameters are determined, wherein the target stress type and the target stress parameters are used to set a current test condition of the reproducing test device;

[0020] When the target product in the replication test device is operated under the test conditions, test data of the target product is acquired, and a failure replication result of the target product is determined based on the test data.

[0021] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0022] Obtain historical usage data of a target product for which failure reproduction is to be performed, wherein the target product is an unstable failure product that has experienced failure;

[0023] Based on the historical usage data, a target stress type currently being detected is selected from a plurality of candidate stress types, and corresponding target stress parameters are determined, wherein the target stress type and the target stress parameters are used to set a current test condition of the reproducing test device;

[0024] When the target product in the replication test device is operated under the test conditions, test data of the target product is acquired, and a failure replication result of the target product is determined based on the test data.

[0025] The above-mentioned product failure reproduction method, device, computer equipment, medium and program product obtain the historical usage data of the target product to be reproduced, and the target product is an unstable failure product that has failed in the past. In this way, it is possible to select the target stress type currently being detected from multiple candidate stress types based on the historical usage data in advance, and determine the corresponding target stress parameters. The target stress type and target stress parameters are used to set the current test conditions of the reproduction test equipment. Thus, under the premise of avoiding going through all test conditions one by one, the test conditions that match them are determined through the historical usage data to perform effective failure reproduction. Subsequently, when the target product located in the reproduction test equipment is running under the test conditions, that is, the target product is tested online through the test conditions, and the test data of the target product is obtained in real time. In this way, based on the test data, the failure reproduction result of the target product under the online test can be accurately determined, thereby improving the accuracy of failure reproduction. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0027] Figure 1 This is an application environment diagram of a product failure reproduction method in one embodiment;

[0028] Figure 2 1 is a flow chart of a method for reproducing product failure in one embodiment;

[0029] Figure 3 is a schematic diagram of a process for determining a target stress type and target stress parameters in one embodiment;

[0030] Figure 4 A schematic diagram of the failure reproduction steps in one embodiment;

[0031] Figure 5 A schematic diagram of a failure recurrence test in one embodiment;

[0032] Figure 6 This is a structural block diagram of a product failure reproduction device in one embodiment;

[0033] Figure 7 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0035] The product failure reproduction method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the recurrence test device 102 communicates with the computer device 104 via a network. The product failure recurrence method provided in the embodiment of the present application can be executed by the recurrence test device 102 or the computer device 104 alone, or can be executed by the recurrence test device 102 and the computer device 104 in collaboration.

[0036] In some embodiments, a target product is placed in the replication test device 102 and connected to an external power supply or driver, and the replication test device 102 is connected to a computer device 104. The computer device 104 obtains historical usage data of the target product to be failed. The target product is an unstable failure product that has experienced failures. Based on the historical usage data, the computer device 104 selects a target stress type to be tested from multiple candidate stress types and determines corresponding target stress parameters. The target stress type and target stress parameters are used to set the current test conditions of the replication test device 102. When the target product in the replication test device 102 is operating under the test conditions, the computer device 104 receives the test data of the target product sent by the replication test device 102 and determines the failure replication result of the target product based on the test data.

[0037] Illustratively, if the failure reproduction result indicates that the failure reproduction is successful, a failure analysis is performed based on the test data to determine the failure mechanism.

[0038] The reproducible test device 102 can be understood as a test box, used to perform online testing on the target product and collect test data from the target product during runtime (during online testing). The computer device 104 can be a terminal or a server. Terminals include, but are not limited to, various personal computers, laptops, smartphones, tablets, etc. The server can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server providing cloud computing services.

[0039] In an exemplary embodiment, Figure 2 As shown, a product failure reproduction method is provided, which is applied to Figure 1 The computer device 104 in the example is used as an example to illustrate the method, which includes the following steps S202 to S206.

[0040] Step S202 : obtaining historical usage data of a target product for which failure reproduction is to be performed, where the target product is an unstable failure product that has experienced failure.

[0041] Among them, the target product is an electronic product that has experienced unstable failure. Of course, it can also be a non-electronic product with parameters or functions. Unstable failure refers to occasional or instantaneous failure, and its failure phenomenon has unstable characteristics. The target historical usage data refers to the data generated when the target product was used before. For example, the target historical usage data includes the failure phenomenon that has occurred in the target product before. For example, it includes the model information of the target product, and for example, the application circuit used by the target product, etc. The target historical usage data can be compiled by the product user. For example, when the target product is used, if a failure occurs, the product user records the failure phenomenon that occurred, the environmental information of the environment in which the target product is located when the failure phenomenon occurs, and the application circuit used by the target product to obtain the target historical usage data and send it to the computer device (as the product failure reproduction party) to instruct the computer device to reproduce the failure based on the target historical data to determine the failure analysis.

[0042] Exemplarily, after the failure reproduction of the target product is started, the computer device obtains the input historical usage data of the target product based on the data input operation.

[0043] Illustratively, every time a failure reproduction cycle is reached, the computer device automatically obtains historical usage data of the target product in the reproduction test device.

[0044] Step S204 : Based on the historical usage data, a target stress type currently being detected is selected from a plurality of candidate stress types, and corresponding target stress parameters are determined. The target stress type and target stress parameters are used to set the current test conditions of the reproducing test equipment.

[0045] Among them, the candidate stress type is the stress type that can be selected for failure reproduction. For example, the candidate stress type can be temperature type, humidity type, temperature and humidity alternation type, vibration type, etc. Stress parameter refers to the stress value or value range. The target stress parameter and target stress type are matched with the historical usage data, and the current test conditions are determined based on the target stress parameter and target stress type. The test condition acts on the target product, so that the target product can be tested online under the test conditions. For example, a preset stress is applied to the target product in the reproduction test equipment. The stress type of the preset stress is the target stress type, and the parameters of the preset stress are the target stress parameters. For example, the target stress type is temperature change stress, and the target stress parameters include a temperature change range of -55°C to 85°C and a temperature change rate of 15°C / min.

[0046] Exemplarily, the computer device determines, based on the historical usage data, whether a historical failure recurrence record corresponding to the historical usage data exists. If not, the computer device selects a target stress type for current testing from multiple candidate stress types and determines corresponding target stress parameters based on the historical usage data. Based on the target stress type and target stress parameters, the computer device determines the current test conditions of the recurrence test device.

[0047] If there is a historical failure recurrence record corresponding to the historical usage data, the failure recurrence data is obtained from the historical implementation recurrence record, and failure analysis is performed based on the failure recurrence data to determine the failure mechanism.

[0048] Illustratively, after the test conditions are determined, the target product is powered on and begins to operate under the test conditions, such as starting to operate within a set temperature range and temperature change rate.

[0049] Illustratively, based on the historical usage information, after a target stress type is selected from a plurality of candidate stress types, a target stress parameter corresponding to the historical usage information is determined from a plurality of stress parameters belonging to the target stress type.

[0050] Exemplarily, based on the historical usage information, a target stress type is selected from a plurality of candidate stress types and a target stress parameter is selected from a plurality of candidate stress parameters.

[0051] For example, if the target stress type currently being detected cannot be selected from multiple candidate stress types, a type selection failure message is sent to the recurrence test device for display, and the current test conditions are determined in response to the test information input operation on the recurrence test device.

[0052] In some embodiments, the historical usage data includes at least failure phenomena that have occurred in the target product, environmental information of the environment in which the failure phenomena occurred, and product attribute information of the target product.

[0053] For example, the failure phenomenon refers to any unstable failure that the target product has previously experienced, such as short circuit, open circuit instability, or leakage. Environmental information refers to the operating environment of the target product when the failure phenomenon occurred. The target product's attribute information includes at least the application circuit used by the target product.

[0054] To this end, in some embodiments, such as Figure 3 FIG. 1 is a schematic diagram of a target stress type and target stress parameter determination process in one embodiment. Based on historical usage data, the target stress type currently being detected is selected from multiple candidate stress types, and the corresponding target stress parameters are determined, including:

[0055] Step S302: When failure recurrence data related to historical usage data cannot be found locally, a mapping table for determining test conditions is obtained, the mapping table including mapping relationships between failure phenomena, environmental information, product attribute information and test information of test conditions.

[0056] The mapping table contains a many-to-one mapping relationship. For example, the mapping relationship is that the failure phenomenon, environmental information, and product attribute information correspond to one piece of test information. For example, after the failure phenomenon, environmental information, and product attribute information are determined, the corresponding piece of test information is determined based on the mapping relationship.

[0057] For example, the computer device queries locally whether there is a historical failure recurrence record. If so, it determines whether there is failure recurrence data related to the historical usage data and performs failure analysis based on the failure recurrence data. If not, step S302 is executed.

[0058] Step S304 : Based on the failure phenomenon, environmental information, and product attribute information of the target product, the test information corresponding to the target product is searched from the mapping table. The test information includes a recommended stress type and recommended stress parameters.

[0059] Step S306 : When a recommended stress type exists among the multiple candidate stress types, the recommended stress type is used as the target stress type, and the recommended stress parameters are used as the target stress parameters.

[0060] The candidate stress type is the stress type provided by the reproducible test equipment, and the recommended stress type is the stress type automatically recommended based on historical usage data.

[0061] Exemplarily, after obtaining the test information, it is checked whether a recommended stress type exists among a plurality of pre-stored candidate stress types. If so, the recommended stress type is used as the target stress type, and it is determined whether the recommended stress parameters meet the parameter conditions of the recommended stress type. If so, the recommended stress parameters are used as the target stress parameters.

[0062] For example, if the recommended stress parameter is a stress parameter range, the system determines whether the stress parameter range exceeds the standard stress range for the recommended stress type. If it does not (i.e., the stress parameter range is a subset of the standard stress range), the system determines that the parameter conditions for the recommended stress type are met. If the recommended stress parameter is a stress parameter value, the system determines whether the stress parameter value is within the standard stress range for the recommended stress type. If so, the system determines that the parameter conditions for the recommended stress type are met.

[0063] In this embodiment, through the mapping table for determining the test conditions, the test conditions that match the target product can be quickly and accurately determined without going through all the test conditions one by one, thereby improving the efficiency of failure reproduction. At the same time, based on the matching test conditions, the accuracy of failure reproduction can be effectively improved.

[0064] Step S206 : when the target product in the recurrence test device is running under the test conditions, acquiring test data of the target product, and determining a failure recurrence result of the target product based on the test data.

[0065] Test data is data collected in real time while the target product is operating under test conditions, and can be understood as data collected during online testing. Test data includes at least one data type, such as voltage data, current data, resistance data, or waveform data.

[0066] The failure reproduction result is used to indicate whether the failure phenomenon that occurred was successfully reproduced when running under the test conditions.

[0067] Exemplarily, when the target product located in the replication test device operates under test conditions, the replication test device collects data about the target product within a preset collection period and sends it to the computer device. After the computer device preprocesses the received data, it obtains the test data of the target product and determines the failure reproduction result of the target product based on the test data.

[0068] For example, when a target product within a reproducible test device is operating under test conditions, the computer device sends a collection instruction to the reproducible test device, collects data based on the collection duration specified in the collection instruction, and sends the collected data to the computer device. The computer device preprocesses the received data to obtain test data for the target product.

[0069] Preprocessing can include cleaning the data, for example, removing invalid data to avoid interference with the recurrence of failures.

[0070] In some embodiments, determining a failure reproduction result of a target product based on test data includes: obtaining normal data of the target product, and comparing the normal data with the test data; if the comparison result indicates that the normal data is inconsistent with the test data, then extracting data inconsistent with the normal data from the test data, using the extracted data as the failure reproduction data of the target product, and determining that the failure reproduction is successful; if the comparison result indicates that the normal data is consistent with the test data, then determining that the failure reproduction has failed.

[0071] The normal data refers to data collected from the target product when no failure occurs. The normal data may be provided by the product user or may be pre-collected by the computer device before step S202.

[0072] Exemplarily, the computer device obtains normal data of the target product locally, or sends a data acquisition request to the product user to instruct the product user to send normal data corresponding to the product identifier to the computer device based on the product identifier in the data acquisition request.

[0073] Exemplarily, the data types to be compared are determined. For each data type to be compared, the computer device compares whether the first data of the data type in the normal data is consistent with the second data of the data type in the test data to obtain a comparison result of the data type.

[0074] If the computer device verifies that the comparison results of each data type to be compared are consistent, then the failure reproduction is determined to have failed. If the computer device verifies that the comparison results of at least one data type to be compared are inconsistent, then the failure reproduction is determined to have succeeded.

[0075] Exemplarily, the data type to be compared can be determined by the test functions of all test points in the target product, or at least one test point to be selected can be screened out from all test points, and the test function of the selected test point can be used as the data type to be compared, without specific limitation.

[0076] In this embodiment, by comparing normal data with test data, the failure reproduction result can be accurately and quickly determined, thereby improving the accuracy of failure reproduction.

[0077] In the above-mentioned product failure reproduction method, by obtaining the historical usage data of the target product to be reproduced, the target product is an unstable failure product that has failed before. In this way, the target stress type currently being detected can be selected from multiple candidate stress types based on the historical usage data in advance, and the corresponding target stress parameters can be determined. The target stress type and target stress parameters are used to set the current test conditions of the reproduction test equipment. Thus, under the premise of avoiding going through all test conditions one by one, the test conditions that match them are determined through the historical usage data to perform effective failure reproduction. Subsequently, when the target product located in the reproduction test equipment is running under the test conditions, that is, the target product is tested online under the test conditions, and the test data of the target product is obtained in real time. In this way, based on the test data, the failure reproduction result of the target product under the online test can be accurately determined, thereby improving the accuracy of failure reproduction.

[0078] In some embodiments, the method further includes: obtaining multiple candidate test points located on the target product based on product attribute information of the target product; dividing the multiple candidate test points into at least one candidate set based on the degree of correlation between each candidate test point and other candidate test points, and the correlation between multiple candidate test points in the same candidate set is high; for each candidate set, randomly selecting at least one candidate test point from the candidate set as a target test point, and each target test point is used to collect data to obtain test data.

[0079] Among them, the product attribute information includes the circuit information of the circuit used in the product, and the degree of correlation between each candidate test point in the circuit is determined based on the circuit information. The candidate test point is the test point to be selected. The test point is a point on the product circuit that can be used for data collection. For example, the current pin is a candidate test point, the voltage pin is a candidate test point, etc. If the correlation between two candidate test points is high, it means that the failure of the two candidate test points affects each other, that is, if one candidate test point fails, the other candidate test point also fails. If the correlation between the two candidate test points is low, it means that the failure of the two candidate test points does not affect each other, that is, if one candidate test point fails, the other candidate test point does not fail.

[0080] Exemplarily, a computer device obtains circuit information based on product attribute information of a target product. Based on the circuit information, the computer device determines multiple candidate test points on the target product and the correlation between each candidate test point and each other candidate test point. The computer device then obtains a correlation threshold for matching the target product. Based on the correlation threshold and the correlation between each candidate test point and each other candidate test point, the computer device divides the multiple candidate test points into at least one candidate set. The correlation between the multiple test points in each candidate set is higher than the correlation threshold, meaning that the correlation between the candidate test points in the same candidate set is high, while the correlation between the candidate test points in different candidate sets is low.

[0081] For each candidate set, a candidate test point is randomly selected from the candidate set as a target test point, and data values of corresponding data types are collected based on the function of the target test point, thereby obtaining test data.

[0082] Alternatively, for each candidate set, a plurality of candidate test points are randomly selected from the candidate set as target test points, wherein the number of the selected plurality of candidate test points is less than the total number of candidate test points in the candidate set. Data values of corresponding data types are collected based on the functions of the target test points to obtain test data.

[0083] For example, there are five candidate test points, P1-P5. The correlation between any two of P1, P2, and P3 is greater than the correlation threshold, and the correlation between P4 and P5 is greater than the correlation threshold. Therefore, P1, P2, and P3 belong to candidate set 1, and P4 and P5 belong to candidate set 2. Next, P1 is selected from candidate set 1 as the target test point, and P4 is selected from candidate set 2 as the target test point. This eliminates the need to collect data for every candidate test point; data is only collected for the target test points selected from the candidate sets. Compared to the previous method of collecting five types of data, this embodiment only requires collecting two types of data. This reduces the amount of data collected and improves the efficiency of failure reproduction while ensuring the effectiveness of failure reproduction.

[0084] Exemplarily, for each candidate set, the computer device selects the candidate test point with the highest historical failure rate as the target test point based on the historical failure rates corresponding to each candidate test point in the candidate set.

[0085] In this embodiment, based on the degree of correlation between the candidate test points and other candidate test points, at least one candidate set is determined, that is, multiple related candidate test points are placed in one candidate set. Thus, target test points are selected from the candidate set for data collection. Therefore, there is no need to collect data for each candidate test point. Data is only collected for the target test points selected from the candidate set. Under the premise of ensuring the effectiveness of failure reproduction, the amount of data collection is reduced and the efficiency of failure reproduction is improved.

[0086] In some embodiments, the method further includes: when the failure reproduction result indicates that the failure reproduction has failed, obtaining test condition requirement information related to the target product, calling a large language model, performing semantic understanding on the test condition requirement information, and obtaining new test conditions; when the target product located in the reproduction test equipment is running under the new test conditions, obtaining new test data of the target product, and determining the failure reproduction result of the target product based on the new test data.

[0087] A large language model refers to a deep learning model trained using large amounts of text data. It can generate natural language text or understand the meaning of language text. Test condition requirement information is used to request test conditions related to the target product.

[0088] For example, when the failure reproduction result indicates that the failure reproduction has failed, the computer device determines the prompt text based on successful failure reproduction cases of other products, calls the large language model, and performs semantic understanding of the test condition requirement information through the prompt text to obtain new test conditions.

[0089] Illustratively, the new test condition is different from the current test condition.

[0090] In some embodiments, a large language model is called to perform semantic understanding of the test condition requirement information to obtain new test conditions, including: obtaining a prompt text, the prompt text including a question and an answer for answering the question, the question being used to inquire about other test conditions used by other products for failure reproduction; calling a large language model to identify the question-answer format of the prompt text, and using the test condition requirement information as a question, determining the answer to the test condition requirement information according to the question-answer format, and the answer to the test condition requirement information being used to determine the new test conditions.

[0091] For example, the prompt text is a text indicating a successful failure reproduction. The prompt text includes multiple positive question-answer pairs (successful failure reproduction based on the test conditions recommended by the answer). Each positive question-answer pair includes a question and a corresponding answer. The question inquires about other test conditions for other products, and the corresponding answer is that the other test conditions were used to successfully reproduce the failure of the other product after running the other product under the other test conditions. The test condition requirement information indicates that the new test condition should not include a target stress type or target stress parameters.

[0092] For example, a question about test condition requirements might be: "Please determine the test conditions for the target product. The test conditions do not include the target stress type or target stress parameters." Correspondingly, a question-and-answer format for determining test condition requirements might be: "Other stress types and other stress parameters."

[0093] In this way, through the large language model, the prompt text is determined according to other test conditions when other products are reproducing failures, which helps the large language model to semantically understand the test condition requirement information, so as to select new test conditions again from the large language model dimension to ensure the normal execution of the failure reproduction of the target product.

[0094] In this embodiment, after running the target product with the target stress type and target stress parameters to determine the failure of reproduction, the test condition requirement information is semantically understood by calling the large language model, and new test conditions are re-determined to ensure the normal execution of the failure reproduction of the target product.

[0095] In a specific embodiment, after a computer (personal computer, belonging to a terminal) is connected to the recurrence test device, as shown in FIG. Figure 4 The figure is a schematic diagram of the failure reproduction steps in one embodiment, referring to Figure 4 , perform the following steps:

[0096] Step 1: Stress determination, that is, determining the target stress type and target stress parameters.

[0097] Specifically, the computer obtains multiple candidate test points located on the target product based on product attribute information of the target product; divides the multiple candidate test points into at least one candidate set based on the degree of correlation between each candidate test point and other candidate test points, and the degree of correlation between multiple candidate test points in the same candidate set is high; for each candidate set, randomly selects at least one candidate test point from the candidate set as a target test point, and each target test point is used to collect data to obtain test data.

[0098] A computer obtains historical usage data of a target product to be subjected to failure replication, where the target product is an unstable failure product that has experienced failures; the historical usage data includes at least failure phenomena that have occurred in the target product, environmental information of the environment in which the failure phenomena occurred, and product attribute information of the target product; if failure replication data related to the historical usage data cannot be found locally, a mapping table for determining test conditions is obtained, where the mapping table includes a mapping relationship between failure phenomena, environmental information, product attribute information, and test information of the test conditions; based on the failure phenomena, environmental information, and product attribute information of the target product, test information corresponding to the target product is found from the mapping table, where the test information includes a recommended stress type and recommended stress parameters; if a recommended stress type exists among multiple candidate stress types, the recommended stress type is used as a target stress type, and the recommended stress parameters are used as target stress parameters, where the target stress type and target stress parameters are used to set the current test conditions of the replication test equipment.

[0099] Step 2: Stress the target product in the replicated test equipment, i.e., run it under the current test conditions.

[0100] Specifically, if Figure 5 FIG. 1 is a schematic diagram of a failure recurrence test in an embodiment. Figure 5The device under test (DUT) is the target product, and the device under test is located in the reproduction test equipment ( Figure 5 (not shown), environmental stress refers to stress applied to a target product, the type of the stress is a target stress type, and the parameter is a target stress parameter. Figure 5 The computer (personal computer) is a terminal. Data acquisition is performed through a power supply, signal source, electronic load, multi-channel trigger and timing synchronization management module (timing management unit), data acquisition instrument (multiplexer), source meter, multimeter, oscilloscope, and oscilloscope to determine test data.

[0101] Step 3: Conduct failure reproduction testing.

[0102] Step 4: Record the data.

[0103] Specifically, the computer acquires recorded data, that is, when the target product in the replication test equipment is operating under test conditions, the computer acquires test data of the target product. Then, normal data of the target product is acquired and compared with the test data. If the comparison result indicates that the normal data and the test data are inconsistent, the inconsistent data is intercepted from the test data and used as the failure replication data of the target product, and the failure replication is determined to be successful. If the comparison result indicates that the normal data and the test data are consistent, the failure replication is determined to have failed.

[0104] If the failure reproduction results indicate a failure to reproduce, the computer obtains test condition requirement information related to the target product and prompt text, which includes a question and an answer to the question. The question is used to inquire about other test conditions used when reproducing other products. The computer then calls a large language model to identify the question-and-answer format of the prompt text, and uses the test condition requirement information as a question to determine the answer to the test condition requirement information in accordance with the question-and-answer format. The answer to the test condition requirement information is used to determine new test conditions. When the target product in the reproduction test equipment is operating under the new test conditions, new test data for the target product is obtained, and the failure reproduction results for the target product are determined based on the new test data.

[0105] In this embodiment, by obtaining the historical usage data of the target product to be subjected to failure reproduction, the target product is an unstable failure product that has experienced failure. In this way, the target stress type currently being detected can be selected from multiple candidate stress types based on the historical usage data in advance, and the corresponding target stress parameters can be determined. The target stress type and target stress parameters are used to set the current test conditions of the reproduction test equipment. Thus, under the premise of avoiding going through all test conditions one by one, the test conditions that match them are determined through the historical usage data to perform effective failure reproduction. Subsequently, when the target product located in the reproduction test equipment is operated under the test conditions, that is, the target product is tested online under the test conditions, and the test data of the target product is obtained in real time. In this way, based on the test data, the failure reproduction result of the target product under the online test can be accurately determined, thereby improving the accuracy of failure reproduction.

[0106] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0107] Based on the same inventive concept, the present application also provides a product failure reproducing device for implementing the aforementioned product failure reproducing method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations in one or more of the following product failure reproducing device embodiments can be found in the aforementioned limitations on the product failure reproducing method and will not be further elaborated here.

[0108] In an exemplary embodiment, Figure 6 As shown, a product failure recurrence device 600 is provided, comprising: an acquisition module 602, a first determination module 604, and a second determination module 606, wherein:

[0109] An acquisition module 602 is used to acquire historical usage data of a target product for which failure reproduction is to be performed, where the target product is an unstable failure product that has experienced failure;

[0110] A first determination module 604 is configured to select a target stress type to be detected from a plurality of candidate stress types based on historical usage data, and determine corresponding target stress parameters. The target stress type and target stress parameters are used to set the current test conditions of the replication test device.

[0111] The second determining module 606 is configured to obtain test data of the target product when the target product in the recurrence test device is running under the test conditions, and determine a failure recurrence result of the target product based on the test data.

[0112] In some embodiments, the historical usage data includes at least failure phenomena that have occurred in the target product, environmental information of the environment in which the failure phenomenon occurred, and product attribute information of the target product; the first determination module 604 is used to obtain a mapping table for determining test conditions when failure reproduction data related to the historical usage data cannot be found locally, and the mapping table includes a mapping relationship between failure phenomena, environmental information, product attribute information and test information of the test conditions; based on the failure phenomena, environmental information, and product attribute information of the target product, the test information corresponding to the target product is found from the mapping table, and the test information includes a recommended stress type and recommended stress parameters; when a recommended stress type exists among multiple candidate stress types, the recommended stress type is used as the target stress type, and the recommended stress parameters are used as the target stress parameters.

[0113] In some embodiments, the device also includes a selection module, which is used to obtain multiple candidate test points located on the target product based on product attribute information of the target product; based on the degree of correlation between each candidate test point and other candidate test points, the multiple candidate test points are divided into at least one candidate set, and the correlation between multiple candidate test points in the same candidate set is high; for each candidate set, at least one candidate test point is randomly selected from the candidate set as a target test point, and each target test point is used to collect data to obtain test data.

[0114] In some embodiments, the second determination module 606 is used to obtain normal data of the target product and compare the normal data with the test data; if the comparison result indicates that the normal data is inconsistent with the test data, then the data inconsistent with the normal data is intercepted from the test data, and the intercepted data is used as the failure reproduction data of the target product, and the failure reproduction is determined to be successful; if the comparison result indicates that the normal data is consistent with the test data, then the failure reproduction is determined to have failed.

[0115] In some embodiments, the first determination module 604 is further used to obtain test condition requirement information related to the target product when the failure reproduction result indicates that the failure reproduction has failed, call the large language model, perform semantic understanding on the test condition requirement information, and obtain new test conditions; the second determination module 606 is used to obtain new test data of the target product when the target product located in the reproduction test equipment is running under the new test conditions, and determine the failure reproduction result of the target product based on the new test data.

[0116] In some embodiments, the first determination module 604 is further used to obtain a prompt text, which includes a question and an answer for answering the question, wherein the question is used to inquire about other test conditions adopted by other products when reproducing failures; calling a large language model to identify the question-answer format of the prompt text, and using the test condition requirement information as a question, determining the answer to the test condition requirement information according to the question-answer format, and the answer to the test condition requirement information is used to determine new test conditions.

[0117] Each module in the aforementioned product failure reproduction device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0118] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a product failure reproduction method is implemented.

[0119] Those skilled in the art will understand that Figure 7The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0120] In an exemplary embodiment, a computer device is provided, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented: obtaining historical usage data of a target product to be subjected to failure reproduction, where the target product is an unstable failure product that has experienced failures; based on the historical usage data, selecting a target stress type currently being detected from a plurality of candidate stress types, and determining corresponding target stress parameters, wherein the target stress type and target stress parameters are used to set current test conditions of a reproduction test device; when the target product located in the reproduction test device operates under the test conditions, obtaining test data of the target product, and determining a failure reproduction result of the target product based on the test data.

[0121] In one embodiment, the historical usage data includes at least failure phenomena that have occurred in the target product, environmental information of the environment in which the failure phenomena occurred, and product attribute information of the target product; when the processor executes the computer program, it also implements the following steps: when failure reproduction data related to the historical usage data cannot be found locally, a mapping table for determining test conditions is obtained, the mapping table including a mapping relationship between failure phenomena, environmental information, product attribute information and test information of the test conditions; based on the failure phenomena, environmental information, and product attribute information of the target product, test information corresponding to the target product is searched from the mapping table, the test information including a recommended stress type and recommended stress parameters; when a recommended stress type exists among multiple candidate stress types, the recommended stress type is used as the target stress type, and the recommended stress parameters are used as the target stress parameters.

[0122] In one embodiment, when the processor executes the computer program, the following steps are further implemented: based on the product attribute information of the target product, a plurality of candidate test points located on the target product are obtained; based on the degree of correlation between each candidate test point and other candidate test points, the plurality of candidate test points are divided into at least one candidate set, where the degree of correlation between the plurality of candidate test points in the same candidate set is high; for each candidate set, at least one candidate test point is randomly selected from the candidate set as a target test point, and each target test point is used to collect data to obtain test data.

[0123] In one embodiment, when the processor executes the computer program, it also implements the following steps: obtaining normal data of the target product, comparing the normal data and the test data; if the comparison result indicates that the normal data is inconsistent with the test data, then intercepting the data inconsistent with the normal data from the test data, using the intercepted data as the failure reproduction data of the target product, and determining that the failure reproduction is successful; if the comparison result indicates that the normal data is consistent with the test data, then determining that the failure reproduction has failed.

[0124] In one embodiment, when the processor executes the computer program, the following steps are also implemented: when the failure reproduction result indicates that the failure reproduction has failed, test condition requirement information related to the target product is obtained, the large language model is called, the test condition requirement information is semantically understood, and new test conditions are obtained; when the target product located in the reproduction test equipment is running under the new test conditions, new test data of the target product is obtained, and the failure reproduction result of the target product is determined based on the new test data.

[0125] In one embodiment, when the processor executes the computer program, it also implements the following steps: obtaining a prompt text, the prompt text including a question and an answer for answering the question, the question being used to inquire about other test conditions used when other products are performing failure reproduction; calling a large language model to identify the question-and-answer format of the prompt text, and using the test condition requirement information as a question, determining an answer to the test condition requirement information according to the question-and-answer format, and the answer to the test condition requirement information being used to determine new test conditions.

[0126] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: obtaining historical usage data of a target product to be subjected to failure replication, where the target product is an unstable failure product that has experienced failures; based on the historical usage data, selecting a target stress type currently being detected from a plurality of candidate stress types, and determining corresponding target stress parameters, where the target stress type and target stress parameters are used to set current test conditions of a replication test device; when the target product located in the replication test device operates under the test conditions, obtaining test data of the target product, and determining a failure replication result of the target product based on the test data.

[0127] In one embodiment, the historical usage data includes at least failure phenomena that have occurred in the target product, environmental information of the environment in which the failure phenomena occurred, and product attribute information of the target product; when the computer program is executed by the processor, the following steps are also implemented: when failure reproduction data related to the historical usage data cannot be found locally, a mapping table for determining test conditions is obtained, the mapping table including a mapping relationship between failure phenomena, environmental information, product attribute information and test information of the test conditions; based on the failure phenomena, environmental information, and product attribute information of the target product, test information corresponding to the target product is searched from the mapping table, the test information including a recommended stress type and recommended stress parameters; when a recommended stress type exists among multiple candidate stress types, the recommended stress type is used as the target stress type, and the recommended stress parameters are used as the target stress parameters.

[0128] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: based on the product attribute information of the target product, a plurality of candidate test points located on the target product are obtained; based on the degree of correlation between each candidate test point and other candidate test points, the plurality of candidate test points are divided into at least one candidate set, and the degree of correlation between the plurality of candidate test points in the same candidate set is high; for each candidate set, at least one candidate test point is randomly selected from the candidate set as a target test point, and each target test point is used to collect data to obtain test data.

[0129] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining normal data of the target product, comparing the normal data and the test data; if the comparison result indicates that the normal data is inconsistent with the test data, then intercepting the data inconsistent with the normal data from the test data, using the intercepted data as the failure reproduction data of the target product, and determining that the failure reproduction is successful; if the comparison result indicates that the normal data is consistent with the test data, then determining that the failure reproduction has failed.

[0130] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when the failure reproduction result indicates that the failure reproduction has failed, test condition requirement information related to the target product is obtained, the large language model is called, the test condition requirement information is semantically understood, and new test conditions are obtained; when the target product located in the reproduction test equipment is running under the new test conditions, new test data of the target product is obtained, and the failure reproduction result of the target product is determined based on the new test data.

[0131] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining a prompt text, the prompt text including a question and an answer for answering the question, the question being used to inquire about other test conditions used when reproducing failures of other products; calling a large language model to identify the question-answer format of the prompt text, and using the test condition requirement information as a question, determining the answer to the test condition requirement information according to the question-answer format, and the answer to the test condition requirement information being used to determine new test conditions.

[0132] In one embodiment, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the following steps: obtaining historical usage data of a target product to be subjected to failure replication, where the target product is an unstable failure product that has experienced a failure; selecting a target stress type currently being detected from a plurality of candidate stress types based on the historical usage data, and determining corresponding target stress parameters, wherein the target stress type and the target stress parameters are used to set current test conditions of a replication test device; obtaining test data of the target product when the target product located in the replication test device operates under the test conditions, and determining a failure replication result of the target product based on the test data.

[0133] In one embodiment, the historical usage data includes at least failure phenomena that have occurred in the target product, environmental information of the environment in which the failure phenomena occurred, and product attribute information of the target product; when the computer program is executed by the processor, the following steps are also implemented: when failure reproduction data related to the historical usage data cannot be found locally, a mapping table for determining test conditions is obtained, the mapping table including a mapping relationship between failure phenomena, environmental information, product attribute information and test information of the test conditions; based on the failure phenomena, environmental information, and product attribute information of the target product, test information corresponding to the target product is searched from the mapping table, the test information including a recommended stress type and recommended stress parameters; when a recommended stress type exists among multiple candidate stress types, the recommended stress type is used as the target stress type, and the recommended stress parameters are used as the target stress parameters.

[0134] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: based on the product attribute information of the target product, a plurality of candidate test points located on the target product are obtained; based on the degree of correlation between each candidate test point and other candidate test points, the plurality of candidate test points are divided into at least one candidate set, and the degree of correlation between the plurality of candidate test points in the same candidate set is high; for each candidate set, at least one candidate test point is randomly selected from the candidate set as a target test point, and each target test point is used to collect data to obtain test data.

[0135] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining normal data of the target product, comparing the normal data and the test data; if the comparison result indicates that the normal data is inconsistent with the test data, then intercepting the data inconsistent with the normal data from the test data, using the intercepted data as the failure reproduction data of the target product, and determining that the failure reproduction is successful; if the comparison result indicates that the normal data is consistent with the test data, then determining that the failure reproduction has failed.

[0136] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when the failure reproduction result indicates that the failure reproduction has failed, test condition requirement information related to the target product is obtained, the large language model is called, the test condition requirement information is semantically understood, and new test conditions are obtained; when the target product located in the reproduction test equipment is running under the new test conditions, new test data of the target product is obtained, and the failure reproduction result of the target product is determined based on the new test data.

[0137] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining a prompt text, the prompt text including a question and an answer for answering the question, the question being used to inquire about other test conditions used when reproducing failures of other products; calling a large language model to identify the question-answer format of the prompt text, and using the test condition requirement information as a question, determining the answer to the test condition requirement information according to the question-answer format, and the answer to the test condition requirement information being used to determine new test conditions.

[0138] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0139] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0140] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0141] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A product failure recurrence method, characterized in that: The method comprises: Obtain historical usage data of a target product for which failure reproduction is to be performed, wherein the target product is an unstable failure product that has experienced failure; Based on the historical usage data, a target stress type currently being detected is selected from a plurality of candidate stress types, and corresponding target stress parameters are determined, wherein the target stress type and the target stress parameters are used to set a current test condition of the reproducing test device; When the target product in the replication test device is operated under the test conditions, test data of the target product is acquired, and a failure replication result of the target product is determined based on the test data.

2. The method according to claim 1, characterized in that The historical usage data includes at least failure phenomena that occurred in the target product, environmental information of the environment in which the failure phenomena occurred, and product attribute information of the target product; The selecting, based on the historical usage data, a currently detected target stress type from a plurality of candidate stress types and determining corresponding target stress parameters includes: If no failure recurrence data related to the historical usage data can be found locally, obtaining a mapping table for determining test conditions, the mapping table including mapping relationships between failure phenomena, environmental information, product attribute information, and test information of the test conditions; Based on the failure phenomenon, environmental information, and product attribute information of the target product, searching the mapping table for test information corresponding to the target product, the test information including recommended stress types and recommended stress parameters; In a case where the recommended stress type exists among a plurality of candidate stress types, the recommended stress type is used as the target stress type, and the recommended stress parameters are used as the target stress parameters.

3. The method according to claim 1, characterized in that The method further comprises: Based on the product attribute information of the target product, a plurality of candidate test points located on the target product are obtained; Based on the correlation between each candidate test point and other candidate test points, the multiple candidate test points are divided into at least one candidate set, and the correlation between multiple candidate test points in the same candidate set is high; For each candidate set, at least one to-be-selected test point is randomly selected from the candidate set as a target test point, and each target test point is used to collect data to obtain test data.

4. The method according to claim 1, wherein Determining the failure reproduction result of the target product based on the test data includes: Acquire normal data of the target product, and compare the normal data with the test data; If the comparison result indicates that the normal data is inconsistent with the test data, extracting data inconsistent with the normal data from the test data, using the extracted data as failure reproduction data of the target product, and determining that the failure reproduction is successful; If the comparison result indicates that the normal data is consistent with the test data, it is determined that the failure reproduction has failed.

5. The method according to claim 1, wherein The method further comprises: When the failure reproduction result indicates that the failure reproduction has failed, obtaining test condition requirement information related to the target product, calling a large language model to perform semantic understanding on the test condition requirement information, and obtaining new test conditions; When the target product in the replication test device is operated under the new test conditions, new test data of the target product is acquired, and a failure replication result of the target product is determined based on the new test data.

6. The method according to claim 5, characterized in that The calling of the large language model to perform semantic understanding on the test condition requirement information to obtain new test conditions includes: Obtaining a prompt text, the prompt text including a question and an answer for answering the question, the question being used to inquire about other test conditions used when reproducing the failure of other products; A large language model is called to identify the question-answer format of the prompt text, and the test condition requirement information is used as a question sentence, and an answer sentence of the test condition requirement information is determined according to the question-answer format. The answer sentence of the test condition requirement information is used to determine a new test condition.

7. A product failure reproduction device, characterized in that: The device comprises: An acquisition module is used to acquire historical usage data of a target product for which failure reproduction is to be performed, wherein the target product is an unstable failure product that has experienced failure; a first determination module, configured to select a target stress type currently being detected from a plurality of candidate stress types based on the historical usage data, and determine corresponding target stress parameters, wherein the target stress type and the target stress parameters are used to set current test conditions of the replication test device; The second determining module is configured to obtain test data of the target product when the target product in the recurrence test device operates under the test conditions, and determine a failure recurrence result of the target product based on the test data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images