Data updating method and related device

Abstract

The invention is suitable for the technical field of data processing, and provides a data updating method and related device.The method comprises the steps that fault data are obtained, and a fault corresponding to the fault data is diagnosed and determined through a fault diagnosis algorithm; and updating a fault data set associated with the fault diagnosis algorithm based on the fault data. According to the scheme, data expansion can be effectively performed on the fault data set, and the data timeliness and the data validity of the fault data set are ensured.

Description

Technical Field

[0001] The present application belongs to the field of data processing technology, and in particular, relates to a data updating method and related devices. Background Art

[0002] Fault diagnosis technology is an important part of equipment management and system management scenarios. For example, in the fields of automobile fault diagnosis and ship fault diagnosis, it can detect equipment or system failures in a timely manner to ensure operational safety and performance.

[0003] How to accurately detect fault information in order to provide effective warnings and prevention measures is a common concern.

[0004] Conventional fault diagnosis test methods will form empirical data based on historical data in advance, and compare the empirical data with the actual operation data of the equipment to achieve fault diagnosis and early warning.

[0005] In this process, the empirical data usually remains stable for a long time, which ensures the data stability of fault diagnosis. However, the reliability of the empirical data decreases over time, and the data accuracy is insufficient. Summary of the invention

[0006] The embodiments of the present application provide a data updating method and related devices to solve the problem in the prior art that the reliability of reference data used for fault diagnosis decreases and the data accuracy is insufficient as time changes.

[0007] A first aspect of an embodiment of the present application provides a data updating method, including:

[0008] Acquiring fault data, wherein the fault corresponding to the fault data is diagnosed and determined by a fault diagnosis algorithm;

[0009] Based on the fault data, a fault data set associated with the fault diagnosis algorithm is updated.

[0010] The above implementation process provides a reliable method for automatically updating fault data sets. Along with the fault diagnosis process, relevant data of the fault diagnosed and determined by the fault diagnosis algorithm are obtained, and the data of the fault data set associated with the fault diagnosis algorithm is automatically updated in real time to ensure that valid data with a relatively recent time is obtained, and that the data in the fault data set is adapted to the latest diagnosis object data. The fault data set can be effectively expanded to ensure the timeliness and validity of the fault data set.

[0011] In some embodiments, the acquiring fault data includes:

[0012] Obtaining diagnostic object data;

[0013] Executing the fault diagnosis algorithm on the diagnosis object data to perform diagnosis, and sending fault warning information to the diagnosis object based on the fault determined by the diagnosis;

[0014] The fault data fed back by the diagnosis object based on the fault warning information is acquired.

[0015] This implementation process is based on the data interaction process of implementing fault diagnosis on the diagnosis object, and obtains fault feedback data corresponding to the diagnosed fault from the diagnosis object side, ensuring that the fault data obtained by the fault diagnosis equipment is the actual measured data from the diagnosis object side, and ensuring the timeliness and authenticity of the data when updating the fault data set.

[0016] In some embodiments, the acquiring the fault data fed back by the diagnosis object based on the fault warning information includes:

[0017] Acquire a fault work order uploaded by the diagnosis object based on the fault alarm information, wherein the fault work order corresponds to an on-site fault detection process of the diagnosis object;

[0018] The fault work order is parsed to obtain the fault data.

[0019] In the above implementation process, a method of backfilling fault data work orders was designed. By parsing the work orders, the real data after field fault detection was obtained from the diagnosis object in a convenient way, thereby improving the efficiency of data acquisition and processing, ensuring that the feedback data from the real fault detection is always used for data update of the fault data set, so that the updated fault data set contains the real fault results, ensuring that the fault data set has high accuracy and reliability, thereby ensuring the accuracy and practical application effect of the fault data set in subsequent applications.

[0020] In some embodiments, parsing the fault work order to obtain the fault data includes:

[0021] Parsing the fault work order to obtain work order data;

[0022] When it is determined that the work order data meets the confidence requirement, specific data is extracted from the work order data as the fault data.

[0023] The above implementation method ensures that valid fault data is selected to update the fault data set, improves the effectiveness and reliability of data update of the fault data set, and provides a high-quality data foundation for the subsequent optimization of the fault diagnosis algorithm.

[0024] In some embodiments, the fault diagnosis algorithm is obtained by training based on the fault data set;

[0025] The updating of the fault data set associated with the fault diagnosis algorithm based on the fault data includes:

[0026] Dividing the plurality of fault data acquired within a target period according to a set ratio to obtain training data and test data;

[0027] The fault data set is updated based on the training data and the test data.

[0028] In this process, effective fault data content is selected in a targeted manner, and the newly added data content is divided into training data and test data in proportion, so that the data in the updated fault data set is evenly and reasonably distributed, avoiding the effect deviation of the training or test indicators of the fault test algorithm in the updated fault data set, and ensuring the data validity of the updated fault data set.

[0029] In some embodiments, after updating the fault data set associated with the fault diagnosis algorithm based on the fault data, the method further includes:

[0030] The fault diagnosis algorithm is trained based on the fault data set, and when the trained fault diagnosis algorithm meets the algorithm index, the fault diagnosis algorithm is updated to the trained fault diagnosis algorithm.

[0031] This process provides an optimization and update method for the fault diagnosis algorithm, which can optimize the fault diagnosis algorithm based on the latest diagnostic feedback data, so that the fault diagnosis algorithm can perform accurate fault analysis and diagnosis according to the actual fault detection results, improve the accuracy and practical application effect of the fault diagnosis algorithm, and enhance the reliability and robustness of fault diagnosis.

[0032] In some embodiments, the method further comprises:

[0033] Based on the fault data set, other fault diagnosis algorithms are trained, and when the other fault diagnosis algorithms meet algorithm indicators, the fault diagnosis algorithms are replaced with the other fault diagnosis algorithms.

[0034] In this way, a new method for updating a fault diagnosis algorithm is provided, so that the fault diagnosis algorithm can be replaced with another fault diagnosis algorithm, thereby meeting the adjustment requirements of the fault diagnosis function of the fault diagnosis device in different application stages or different application scenarios.

[0035] In some embodiments, the method further comprises:

[0036] Marking and classifying the data in the fault data set to obtain data labels;

[0037] Based on the data label, the fault data set is cleaned according to a set frequency.

[0038] Therefore, a data cleaning method for a fault data set is provided to ensure that the cleaned fault data set has reliability, accuracy and better use effect.

[0039] A second aspect of an embodiment of the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the first aspect when executing the computer program.

[0040] A third aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0041] The fourth aspect of the present application provides a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying a computer-readable code. When the computer-readable code is executed in an electronic device, the processor in the electronic device executes the steps in the method described in the first aspect above.

[0042] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Moreover, the same reference numerals are used throughout the drawings to represent the same components. In the drawings:

[0044] Figure 1 is a flow chart of a data updating method in some embodiments of the present application;

[0045] Figure 2 is a flow chart of a data updating method in some embodiments of the present application;

[0046] Figure 3 is a flow chart of a data updating method in some embodiments of the present application;

[0047] Figure 4 is a flow chart of a data updating method in some embodiments of the present application;

[0048] Figure 5 is a structural diagram of a data updating device in some embodiments of the present application;

[0049] Figure 6 It is a structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] The following embodiments of the technical solution of the present application are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0052] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0053] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0054] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0055] Fault diagnosis technology is an important part of equipment management and system management scenarios. For example, in the fields of automobile fault diagnosis and ship fault diagnosis, it can detect equipment or system failures in a timely manner to ensure operational safety and performance.

[0056] Taking the automotive industry as an example, with the popularity of new energy vehicles, the importance of automotive batteries is increasing. Battery fault detection technology is an important part of the battery management system, which can help to detect battery faults in time and ensure the safety and performance of the battery. How to accurately detect battery fault information and give corresponding fault causes and disposal suggestions is a topic that both battery manufacturers and car manufacturers pay close attention to.

[0057] At present, battery fault detection technologies mainly include the following:

[0058] Conventional fault diagnosis and testing methods will form empirical data based on historical data in advance, and compare the empirical data with the actual operation data of the equipment to achieve fault diagnosis and early warning. However, empirical data usually remains stable for a long time.

[0059] For example, cloud diagnosis methods can be used to collect vehicle-side fault data in advance to form a fault data set. As experience data, the vehicle will upload its own operating data to the cloud for the cloud to perform fault diagnosis based on the data in the fault data set. The experience database on the cloud may be fixed for two years or updated once when there is a technology update in the automotive industry, which will ensure the data stability of fault diagnosis. However, the reliability of experience data is also reduced over time, and the data accuracy is not enough.

[0060] Moreover, in some cases, when the fault data set lacks calibration with real results, the fault diagnosis process is prone to computational deviation, which affects the validity of the fault diagnosis results.

[0061] Therefore, it can be analyzed that how to update the fault data set associated with the fault diagnosis process has a great impact on the effectiveness of fault diagnosis.

[0062] In order to illustrate the technical solution described in this application, a specific embodiment is provided below for illustration.

[0063] Combination Figure 1 As shown, in some embodiments, a data updating method is proposed, comprising:

[0064] Step 101, obtaining fault data.

[0065] The fault corresponding to the fault data is determined by a fault diagnosis algorithm.

[0066] Fault data is fault-related data. Specifically, fault data is data obtained after detecting the corresponding fault. For example, fault data includes data such as whether a fault occurs, operation data involved in the fault occurrence process in the diagnosis object, environmental data of the fault occurrence, detected fault location, fault level, and fault cause.

[0067] The fault diagnosis algorithm is used to perform fault diagnosis based on the diagnosis object data. After the fault diagnosis algorithm is executed, in addition to diagnosing and determining the fault, it can also be set to give the corresponding fault cause and disposal suggestions.

[0068] The diagnostic object data specifically refers to the operating data of the diagnostic object or the data involved in the diagnostic object in the process of realizing its own function (such as the original data provided in the subsequent text). In the application, the fault diagnosis algorithm can be presented as a fault diagnosis model, which is pre-trained.

[0069] Here, after the fault diagnosis algorithm determines that a fault has occurred, it is necessary to obtain fault data corresponding to the fault, wherein the fault data may include data directly obtained from the fault diagnosis object, and may also include fault-related data obtained through other means.

[0070] Step 102: based on the fault data, update the fault data set associated with the fault diagnosis algorithm.

[0071] The fault data set is a collection of multiple fault data.

[0072] The association relationship between the fault data set and the fault diagnosis algorithm can be, but is not limited to: the fault data set is a data set used for development training or optimization training of the fault diagnosis algorithm, the fault data set is a data set for result verification or correction of the fault diagnosis algorithm, the fault data set is a data set that provides reference data for the fault diagnosis processing of the fault diagnosis algorithm, etc.

[0073] Since the fault data corresponds to the fault diagnosed and determined by the fault diagnosis algorithm, real-time and effective fault data is obtained as the fault diagnosis is implemented. Then, after the fault data is obtained, the fault data is formed as verification data or correction data for the reliability of the fault diagnosis algorithm. Similarly, when the fault data set associated with the fault diagnosis algorithm is updated based on the fault data, the data in the fault data set is then enhanced or corrected.

[0074] In the process of updating the fault data set, the acquired fault data corresponding to the fault diagnosed by the fault diagnosis algorithm is always used as the update and improvement of the fault data set associated with the fault diagnosis algorithm, so that the fault data set has higher accuracy and reliability, so as to ensure the accuracy and practical application effect of the fault diagnosis algorithm.

[0075] The above implementation process provides a reliable method for automatically updating fault data sets. Along with the fault diagnosis process, relevant data of the fault diagnosed and determined by the fault diagnosis algorithm are obtained, and the data of the fault data set associated with the fault diagnosis algorithm is automatically updated in real time to ensure that valid data with a relatively recent time is obtained, and that the data in the fault data set is adapted to the latest diagnosis object data. The fault data set can be effectively expanded to ensure the timeliness and validity of the fault data set.

[0076] Furthermore, some more specific implementation modes will be described below based on the above implementation modes.

[0077] In some embodiments, in combination Figure 2 As shown, step 101 obtains fault data, including:

[0078] Step 201, obtaining diagnosis object data.

[0079] The diagnosis object is a device, a terminal, etc., or an internal component of the device, the terminal, etc. The diagnosis object is, for example, a personal computer, a mobile terminal, a vehicle, a ship, etc., or a processor in a personal computer or a mobile terminal, a battery in a vehicle, a power device in a ship, etc.

[0080] The diagnosis object data refers to the operation data of the diagnosis object or the data involved in the process of realizing the diagnosis object's own functions.

[0081] In an implementation process, taking the diagnosis object as a vehicle as an example, the diagnosis object data may be vehicle battery temperature, vehicle battery power, vehicle driving speed, etc. These diagnosis object data are uploaded to the fault diagnosis device by the diagnosis object on time.

[0082] Optionally, the fault diagnosis device may be a cloud device, a remote server or a local server. Through data interaction between the fault diagnosis device and the diagnosis object, interactive processing such as data acquisition and diagnosis result feedback is achieved.

[0083] After the fault diagnosis device acquires the diagnosis object data, it executes subsequent fault diagnosis processing.

[0084] Step 202 : diagnose the object data by executing a fault diagnosis algorithm, and send fault warning information to the object based on the fault determined by the diagnosis.

[0085] After the diagnosis object data is acquired, the diagnosis object data can be diagnosed using a fault diagnosis algorithm. When the diagnosis result indicates that a fault has occurred or there is a risk of a fault, fault warning information can be sent to the diagnosis object based on the corresponding fault.

[0086] For example, if the fault diagnosis algorithm is used based on vehicle data to calculate that the driving mileage that has consumed the battery power is lower than the normal mileage, it will be determined that a battery failure may have occurred, and a battery life failure warning message will be sent to the vehicle.

[0087] Step 203: Acquire fault data fed back by the diagnosis object based on the fault warning information.

[0088] Here, the fault data may include fault-related data after the diagnosis object verifies, checks, and repairs the fault warned by the fault warning information. For example, when the fault data corresponds to a field detection of the fault, it may specifically include data such as the operation data of the fault, the environment data of the fault, the location of the fault, the fault level, and the cause of the fault.

[0089] In this way, the fault diagnosis device can obtain valid data fed back by the diagnosis object based on the fault diagnosed by the fault diagnosis algorithm.

[0090] This implementation process is based on the data interaction process of implementing fault diagnosis on the diagnosis object, and obtains fault feedback data corresponding to the diagnosed fault from the diagnosis object side, ensuring that the fault data obtained by the fault diagnosis equipment is the actual measured data from the diagnosis object side, and ensuring the timeliness and authenticity of the data when updating the fault data set.

[0091] When the fault diagnosis device obtains the fault data fed back by the diagnosis object, the diagnosis object can directly upload the valid data one by one, or upload it in a certain file format, such as in the form of a work order.

[0092] Correspondingly, in some embodiments, in combination Figure 3 As shown, step 203, obtaining fault data fed back by the diagnosis object based on the fault warning information, includes:

[0093] Step 301: Obtain a fault work order uploaded by a diagnosis object based on fault alarm information.

[0094] Among them, the fault work order corresponds to the on-site fault detection and processing of the diagnosis object.

[0095] The fault data recorded in the uploaded fault work order corresponds to the on-site fault detection processing performed on the diagnosis object side based on the fault prompted by the fault alarm information. The on-site fault detection processing can be a on-site fault self-check processing performed by the diagnosis object itself in response to the fault alarm information. Alternatively, the on-site fault detection is a on-site fault repair processing performed on the diagnosis object by humans based on the fault prompted by the fault alarm information.

[0096] Here, on-site fault detection processing specifically refers to the fault detection processing performed on the diagnosis object side with the diagnosis object as the detection object for the fault warned by the fault alarm information, which specifically includes verification, inspection, and repair of the warned fault.

[0097] After the diagnosis object obtains the fault alarm information, if the diagnosis object side chooses to conduct an on-site inspection for the fault, the fault diagnosis device can send it a fault reporting invitation message to obtain a work order with real fault information. The work order can be transmitted back to the fault diagnosis device through the diagnosis object, and the fault diagnosis device parses the work order to obtain the real fault data from the fault diagnosis object; or the work order can be transmitted back to the fault diagnosis device from other devices (such as on-site fault detection equipment, or mobile phones, computers and other electronic devices that have a communication connection relationship with the fault diagnosis device, etc.), so that the fault diagnosis device can obtain fault data in other ways.

[0098] In addition, in addition to manually filled work orders, the embodiments of the present application also support work orders connected to external systems, providing multiple ways to obtain fault data, which can effectively improve the efficiency of fault data acquisition.

[0099] Step 302: parse the fault work order to obtain fault data.

[0100] The fault work order can be parsed by extracting corresponding data content as fault data according to various data fields distributed in the fault work order, and further performing data format conversion, data screening, data classification and other processing on the basis of the extracted data content to obtain the fault data.

[0101] A work order may contain a variety of fault detection feedback information. Fault detection feedback information can be used to indicate whether a fault has occurred, the cause of the fault, the treatment method, and other real fault information. When parsing the work order, these information contents can be parsed and data can be selected as fault data according to the required data items.

[0102] In an example, the fault detection feedback information may specifically include: original data and fault detection data.

[0103] The raw data refers to the data related to the operation of the object under diagnosis, such as the battery usage time, temperature, voltage, current and other information, which can be used to analyze whether the object under test is faulty, the cause and trend of the fault, etc.

[0104] The fault detection data is related fault detection data after the prompted fault is detected on the diagnosis object side.

[0105] In a specific example, the original data includes, for example: diagnostic object model, which is used to describe the type, brand and model of the diagnostic object; diagnostic object specifications, which are used to describe the capacity, voltage, charging limit and other specification information of the diagnostic object; user data, which includes relevant data on the user's use and maintenance of the diagnostic object, such as the user's usage of the diagnostic object, the frequency of component replacement, the diagnostic object maintenance record, etc. This information can allow the algorithm model of the fault diagnosis algorithm to learn the diagnostic object fault and the diagnostic object usage, so as to output a better battery maintenance and servicing plan; environmental data, which includes environmental factors related to the current fault of the diagnostic object, such as temperature, humidity, light, wind pressure, etc. This information can allow the algorithm model to learn the correlation between the diagnostic object fault and the environmental factors, so as to provide a better maintenance and servicing plan.

[0106] In a specific example, the fault detection data includes, for example: the fault type, location, severity, time and place of occurrence of the fault of the diagnosed object, etc. This information allows the fault diagnosis algorithm to learn the cause and repair plan of the fault, and can be compared with the fault diagnosis results of the fault diagnosis algorithm; detection purpose, which is used to explain the purpose and content of the detection, such as battery life detection, fault detection, etc.; detection method, which is used to describe the detection method, such as voltage detection, current detection, etc.; detection results, which are used to record the detection results, such as battery life, voltage, current and other data; detection result analysis, which is used to record the detection results and analysis, such as battery life analysis, fault cause analysis, etc.

[0107] In implementation, based on the work order parsing function, the fault diagnosis device can parse the information in the work order into a data model, and store the fault data in the fault data set in the form of the data model.

[0108] After the fault diagnosis device obtains the work order automatically uploaded, it will parse the work order to obtain the fault data, thereby ensuring the automatic update of the fault data set.

[0109] In the above implementation process, a method of backfilling fault data work orders was designed. By parsing the work orders, fault data was obtained from the diagnosis object in a convenient way, which improved the efficiency of data acquisition and processing, ensured that feedback data from real fault detection was always used to update the data of the fault data set, and made sure that the updated fault data set contained real fault results, ensuring that the fault data set had high accuracy and reliability, thereby ensuring the accuracy and practical application effect of the fault data set in subsequent applications.

[0110] Furthermore, in an implementation process, the above step 302 parses the fault work order to obtain fault data, including:

[0111] Parse the fault work order to obtain work order data, and extract specific data from the work order data as fault data when it is determined that the work order data meets the confidence requirements.

[0112] The confidence requirement is, for example, that the confidence is greater than a set threshold, such as greater than 90%.

[0113] The data content included in the work order corresponds to the fault detection feedback information. The work order data obtained by parsing the fault work order includes all or part of the fault detection feedback information.

[0114] Before data extraction, the work order data will be reviewed for confidence.

[0115] The confidence level of work order data can be judged by: comparing the parsed work order data with reference data that conforms to objective laws, and determining the confidence level of the work order data based on the deviation between the data values ​​of the two; or performing relationship analysis between the various data items in the parsed work order data, and determining the confidence level of the work order data based on the analysis results.

[0116] The fault detection feedback information is reviewed and filtered to ensure that it is consistent with the true degree of the fault of the diagnosed object. If there is false or inaccurate information, it will be optimized or deleted to ensure that the information in the fault data set is accurate. Through these measures, the accuracy and reliability of the data in the fault data set are improved.

[0117] When it is determined that the work order data meets the confidence requirements, specific data is extracted from the work order data as fault data. The specific data can be data that meets the data content item requirements in the fault data set. The specific data can be all or part of the data in the work order data. Some required data content can be extracted from the work order data as fault data, and it can also be further processed in data format as fault data. The specific data content corresponding to the specific data can be set according to the actual fault type and the training requirements and functional learning requirements of the fault diagnosis algorithm.

[0118] The above implementation method ensures that valid fault data is selected to update the fault data set, improves the effectiveness and reliability of data update of the fault data set, and provides a high-quality data foundation for the subsequent optimization of the fault diagnosis algorithm.

[0119] In some embodiments, the fault diagnosis algorithm is obtained by training based on the fault data set. That is, the fault data set can realize the training of the fault diagnosis algorithm. Specifically, the fault data set can include a training data set and a test data set to implement model training and test optimization for a specific algorithm.

[0120] On this basis, combined with Figure 4As shown, step 102 updates the fault data set associated with the fault diagnosis algorithm based on the fault data, including:

[0121] Step 401 , divide a plurality of fault data acquired in a target period according to a set ratio to obtain training data and test data.

[0122] In an optional implementation process, the acquired fault data may be temporarily stored in a fault database, and when the fault data set needs to be updated, multiple fault data within a target period are extracted from the fault database as processing objects for updating the fault data set.

[0123] The target period is, for example, the period from the last time the fault data set was updated to the start of the current update of the fault data set; or a period of a set duration from the current time, for example, if the set duration is two years, the corresponding target period is the last two years, and so on.

[0124] Ensure that when the fault data is divided into data sets and then updated, the fault data with the most reasonable data content can be selected, or the fault data with the most recent time period can be selected, and the valid data content can be selected in a targeted manner to ensure the data validity of the updated fault data set and ensure that the effect indicators of the fault diagnosis algorithm are adapted to the latest diagnosis object data.

[0125] In addition, the training data set and the test data set in the fault data set can have a certain data partition ratio. For example, the fault data set can be divided into a training set and a test set at a ratio of 7:3. When partitioning the data, in order to ensure the representativeness of the partitioned data set, that is, to ensure that the data of the training set and the test set have similar distribution and characteristics. You can use a data set partitioning tool, such as the sklearn library in Python, to complete the data partitioning.

[0126] After selecting the fault data of a suitable period, in order to ensure that the update of the fault data set is data-calibrated, the selected fault data needs to be divided into the training set and the test set in proportion as incremental data.

[0127] Optionally, the division ratio of training data and test data in the fault data here is consistent with the division ratio of training data set and test data set in the fault data set, for example, ensuring that 70% of the incremental data enters the training set and 30% enters the test set.

[0128] Step 402: Update the fault data set based on the training data and the test data.

[0129] Each time the fault data set is updated, the incremental data formed by multiple fault data are divided separately instead of being divided together with all the data in the fault data set, to ensure that the newly added fault data will not appear completely in the training set or the test set.

[0130] In the above implementation process, effective fault data content is selected in a targeted manner, and the newly added data content is divided into training data and test data separately in proportion, so that the data in the updated fault data set is evenly and reasonably distributed, avoiding the effect deviation of the training or test indicators of the fault test algorithm in the updated fault data set, and ensuring the data validity of the updated fault data set.

[0131] In one embodiment, after step 102, the data updating method further includes:

[0132] Based on the fault data set, the fault diagnosis algorithm is trained, and when the trained fault diagnosis algorithm meets the algorithm index, the fault diagnosis algorithm is updated to the trained fault diagnosis algorithm.

[0133] Among them, algorithm indicators are used to evaluate the performance of fault diagnosis algorithms, such as accuracy, recall rate, F1 score, etc.

[0134] The updated fault data set can be used continuously to train, test and optimize the fault diagnosis algorithm. On the one hand, the fault data set can be used to train and generate new fault diagnosis algorithms, and on the other hand, the fault data set can be used to continuously train and optimize the fault diagnosis algorithms that have been put into use.

[0135] In specific applications, after training the fault diagnosis algorithm based on the training set in the fault data set, the algorithm test can be performed on the currently trained fault diagnosis algorithm based on the test set. If the performance of the fault diagnosis algorithm is judged to be not good enough and does not meet the requirements for the algorithm to go online, the fault diagnosis algorithm to be tested will be returned to the training process and retrained based on the training set. During the retraining process, the parameters of the fault diagnosis algorithm can be adjusted or the algorithm operation method can be improved until the fault diagnosis algorithm meets the algorithm indicators. After the fault diagnosis algorithm has met the requirements for going online, the fault diagnosis algorithm will be deployed in the production environment of the fault diagnosis equipment to diagnose the fault conditions of the object under test in real time.

[0136] In this process, as the fault diagnosis process and fault feedback proceed, after the fault data set is updated based on the acquired fault data, the fault diagnosis algorithm that has been put online can be re-trained offline based on the updated fault data set. When the algorithm optimization is completed and the algorithm indicators are reached, the trained and optimized fault diagnosis algorithm can be put online and the original fault diagnosis algorithm can be taken offline, so as to update the online fault diagnosis algorithm to the trained fault diagnosis algorithm, so that the fault diagnosis algorithm can implement corresponding model optimization based on the latest diagnosis feedback data, and provide an optimization and update method for the fault diagnosis algorithm, so that the fault diagnosis algorithm can perform accurate fault analysis and diagnosis according to the actual fault detection results, improve the accuracy and practical application effect of the fault diagnosis algorithm, and enhance the reliability and robustness of fault diagnosis.

[0137] In one embodiment, the data updating method further includes:

[0138] Based on the fault data set, other fault diagnosis algorithms are trained, and when other fault diagnosis algorithms meet algorithm indicators, the fault diagnosis algorithms are replaced with other fault diagnosis algorithms.

[0139] The other fault diagnosis algorithms here refer to fault diagnosis algorithms that are different from the fault diagnosis algorithms that have been put into use. Other fault diagnosis algorithms can be based on the fault data sets before or after the update as training and test sample sets to achieve algorithm training and test optimization.

[0140] When there is a need to adjust the fault diagnosis function of the fault diagnosis equipment, other fault diagnosis algorithms that meet the algorithm indicators after training can be put online, and the original fault diagnosis algorithm can be taken offline to replace the fault diagnosis algorithm with other fault diagnosis algorithms, providing a new fault diagnosis algorithm update method to meet the fault diagnosis needs in different application stages or different application scenarios.

[0141] In one embodiment, the data updating method further includes:

[0142] The data in the fault data set is marked and classified to obtain data labels; based on the data labels, the fault data set is cleaned according to the set frequency.

[0143] In order to ensure the timeliness and usage effect of the fault data set itself, ensure that the diagnostic function of the corresponding fault diagnosis algorithm is adapted to the latest diagnostic object data, and improve the computing performance and efficiency of the algorithm, a method of cleaning the fault data set is adopted in the embodiment of the present application, and each data in the fault data set is marked and classified to assign data labels.

[0144] Among them, data can be marked and classified according to different factors such as data type, data function, data format, data storage time, etc., and corresponding data labels can be generated.

[0145] When performing data cleaning, you can select the data that needs to be filtered according to the data type, data function, data format and other information indicated by the data label. At the same time, you can set time intervals or fixed periods to clean the data set, remove invalid or abnormal data, remove outdated data in faulty data sets, fill in missing values, and convert data formats.

[0146] Therefore, the cleaned fault data set is ensured to be reliable, accurate and have better usage effect.

[0147] Below, taking the vehicle-side battery fault diagnosis as an example, the processing flow of the data update method in the cloud diagnosis scenario of battery fault is overall illustrated.

[0148] In the cloud diagnosis scenario of battery failure, the vehicle-side battery data information will be uploaded to the cloud platform, and the fault diagnosis algorithm deployed by the cloud platform will diagnose and warn of the battery failure.

[0149] Among them, the fault diagnosis algorithm is in the development and testing stage before being deployed to the cloud platform. During the development and testing stage, it is necessary to use the fault data set to train and test it. After the fault diagnosis algorithm is trained based on the fault data set to meet the algorithm indicators, it will be launched on the cloud platform. Obtain battery data such as battery temperature, battery voltage, battery current, etc. uploaded by the vehicle side, and use the fault diagnosis algorithm that has been launched to perform fault diagnosis on these battery operation data. When it is determined that a fault has occurred or there is a risk of fault, output a reminder message to the vehicle side.

[0150] After the vehicle receives the fault reminder message, the vehicle owner or the vehicle manufacturer can decide whether to perform fault inspection. If the vehicle owner or the vehicle manufacturer determines that the fault will be inspected on the vehicle side, a fault reporting invitation can be sent to the vehicle side.

[0151] In order to ensure the optimal effect of data collection in the data set, a work order form is designed. After the on-site fault detection is completed on the vehicle side, the measured real fault information is filled in the work order, and the information is backfilled through the work order to obtain the measured fault data from the vehicle side. Optionally, after the real fault information after the on-site fault detection is filled in the work order through the vehicle side or other electronic devices, the work order can be automatically uploaded to the cloud platform. Among them, the work order can include real fault information such as whether a fault has occurred, the cause of the fault, and the disposal method. The specific parameter content is expressed as: battery model, battery specification, detection purpose, detection method, detection result, detection result analysis, etc.

[0152] After the fault diagnosis device obtains the work order, it parses the work order, and when it determines that the parsed work order data is credible data, it extracts specific data from it as fault data, and finally updates the fault data set based on the fault data.

[0153] Through the above processing operations, it is possible to continuously obtain effective field fault detection data during the fault diagnosis and fault detection feedback process, ensure that the data in the fault data set can contain the latest effective data, and ensure the timeliness of the data.

[0154] Moreover, based on the continuous updating of fault data sets, fault data sets can be used for subsequent algorithm development, optimization and testing. New fault diagnosis algorithms can be generated based on the training of updated fault data sets, or optimized training and algorithm updates can be performed on the fault diagnosis algorithms that have been put online based on the updated fault data sets, ensuring that the fault diagnosis algorithms can reflect the laws and characteristics of the latest valid fault data, and improving the performance and effectiveness of fault diagnosis.

[0155] 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 indications of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, 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 may include multiple steps or multiple stages, and these steps or stages are not necessarily executed 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 the steps or stages in other steps.

[0156] Based on the same inventive concept, the embodiment of the present application also provides a data updating device. The data updating device provided in the embodiment of the present application can implement each process of the embodiment of the above-mentioned data updating method and can achieve the same technical effect. Therefore, the specific limitations in one or more data updating device embodiments provided below can refer to the limitations on the data updating method above. To avoid repetition, they will not be repeated here.

[0157] In one embodiment, Figure 5 As shown, a data updating device 500 is provided, comprising:

[0158] An acquisition module 501 is used to acquire fault data, wherein the fault corresponding to the fault data is diagnosed and determined by a fault diagnosis algorithm;

[0159] The data updating module 502 is used to update the fault data set associated with the fault diagnosis algorithm based on the fault data.

[0160] In some embodiments, the acquisition module 501 is used to:

[0161] Obtaining diagnostic object data;

[0162] Executing the fault diagnosis algorithm on the diagnosis object data to perform diagnosis, and sending fault warning information to the diagnosis object based on the fault determined by the diagnosis;

[0163] The fault data fed back by the diagnosis object based on the fault warning information is acquired.

[0164] In some embodiments, the acquisition module 501 is specifically used to:

[0165] Acquire a fault work order uploaded by the diagnosis object based on the fault alarm information, wherein the fault work order corresponds to an on-site fault detection process of the diagnosis object;

[0166] The fault work order is parsed to obtain the fault data.

[0167] In some embodiments, the acquisition module 501 is more specifically used for:

[0168] Parsing the fault work order to obtain work order data;

[0169] When it is determined that the work order data meets the confidence requirement, specific data is extracted from the work order data as the fault data.

[0170] In some embodiments, the fault diagnosis algorithm is obtained by training based on the fault data set;

[0171] The data updating module 502 is specifically used for:

[0172] Dividing the plurality of fault data acquired within a target period according to a set ratio to obtain training data and test data;

[0173] The fault data set is updated based on the training data and the test data.

[0174] In some embodiments, the device further comprises:

[0175] The first algorithm updating module is used to train the fault diagnosis algorithm based on the fault data set, and update the fault diagnosis algorithm to the trained fault diagnosis algorithm when the trained fault diagnosis algorithm meets the algorithm index.

[0176] In some embodiments, the device further comprises:

[0177] The second algorithm updating module is used to train other fault diagnosis algorithms based on the fault data set, and replace the fault diagnosis algorithm with the other fault diagnosis algorithm if the other fault diagnosis algorithm meets the algorithm index.

[0178] In some embodiments, the device further comprises:

[0179] The data cleaning module is used to mark and classify the data in the fault data set to obtain data labels; based on the data labels, the fault data set is cleaned according to a set frequency.

[0180] Each module in the above data updating device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0181] In one embodiment, Figure 6 As shown, a computer device is provided. The computer device 6 of this embodiment includes: at least one processor 600 ( Figure 6 Only one is shown in the figure), a memory 601, and a computer program 602 stored in the memory 601 and executable on the at least one processor 600, wherein the processor 600 implements the steps of any of the above-mentioned method embodiments when executing the computer program 602.

[0182] The computer device 6 may be a computing device such as a desktop computer, a notebook, a palm computer, etc. The computer device 6 may include, but is not limited to, a processor 600 and a memory 601. Those skilled in the art will understand that Figure 6 It is only an example of the computer device 6 and does not constitute a limitation of the computer device 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, buses, etc.

[0183] The processor 600 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0184] The memory 601 may be an internal storage unit of the computer device 6, such as a hard disk or memory of the computer device 6. The memory 601 may also be an external storage device of the computer device 6, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 6. Further, the memory 601 may also include both an internal storage unit and an external storage device of the computer device 6. The memory 601 is used to store the computer program and other programs and data required by the computer device. The memory 601 may also be used to temporarily store data that has been output or is to be output.

[0185] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0186] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0187] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0188] In the embodiments provided in the present application, it should be understood that the disclosed apparatus / computer equipment and methods can be implemented in other ways. For example, the apparatus / computer equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of the apparatus or unit, which can be electrical, mechanical or other forms.

[0189] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0190] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0191] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0192] The present application implements all or part of the processes in the above-mentioned embodiment methods, and may also be implemented through a computer program product. When the computer program product runs on a computer device, the computer device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0193] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A data updating method, characterized in that: include: Acquiring fault data, wherein the fault corresponding to the fault data is diagnosed and determined by a fault diagnosis algorithm; Based on the fault data, a fault data set associated with the fault diagnosis algorithm is updated.

2. The method according to claim 1, characterized in that The acquiring of fault data comprises: Obtaining diagnostic object data; Executing the fault diagnosis algorithm on the diagnosis object data to perform diagnosis, and sending fault warning information to the diagnosis object based on the fault determined by the diagnosis; The fault data fed back by the diagnosis object based on the fault warning information is acquired.

3. The method according to claim 2, characterized in that The acquiring the fault data fed back by the diagnosis object based on the fault warning information includes: Acquire a fault work order uploaded by the diagnosis object based on the fault alarm information, wherein the fault work order corresponds to an on-site fault detection process of the diagnosis object; The fault work order is parsed to obtain the fault data.

4. The method according to claim 3, characterized in that The parsing the fault work order to obtain the fault data includes: Parsing the fault work order to obtain work order data; When it is determined that the work order data meets the confidence requirement, specific data is extracted from the work order data as the fault data.

5. The method according to claim 1, characterized in that The fault diagnosis algorithm is obtained by training based on the fault data set; The updating of the fault data set associated with the fault diagnosis algorithm based on the fault data includes: Dividing the plurality of fault data acquired within a target period according to a set ratio to obtain training data and test data; The fault data set is updated based on the training data and the test data.

6. The method according to claim 1, characterized in that After updating the fault data set associated with the fault diagnosis algorithm based on the fault data, the method further includes: The fault diagnosis algorithm is trained based on the fault data set, and when the trained fault diagnosis algorithm meets the algorithm index, the fault diagnosis algorithm is updated to the trained fault diagnosis algorithm.

7. The method according to claim 1, characterized in that The method further comprises: Based on the fault data set, other fault diagnosis algorithms are trained, and when the other fault diagnosis algorithms meet algorithm indicators, the fault diagnosis algorithms are replaced with the other fault diagnosis algorithms.

8. The method according to claim 1, characterized in that: Also includes: Marking and classifying the data in the fault data set to obtain data labels; Based on the data label, the fault data set is cleaned according to a set frequency.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium storing 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 8 are implemented.

11. A computer program product, characterized in that The invention comprises a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code is executed in an electronic device, a processor in the electronic device executes the steps of the method according to any one of claims 1 to 8.

Images