Automated detection and processing of vehicle accessory anomaly information and related devices

Abstract

The embodiment of the application belongs to the field of artificial intelligence, is applied to the field of vehicle accessory anomaly detection, and relates to a vehicle accessory anomaly information automatic detection processing method and a related device thereof, which comprises the following steps: obtaining an anomaly detection set; obtaining an anomaly type corresponding to the anomaly detection set, and adding the anomaly type to a preset vehicle accessory anomaly list; judging whether the result in the vehicle accessory anomaly list is null; if yes, updating vehicle accessory information to a preset damage determination platform; if no, sending an anomaly early warning to the damage determination platform; searching vehicle accessory information containing a keyword in the damage determination platform by taking the anomaly type as the keyword, and performing a release invalidation processing on the vehicle accessory information. The embodiment realizes full automation of classification and collection of anomaly accessories, reduces the time cost of manual screening of platform maintenance personnel, guarantees the satisfaction of users, and is more intelligent.

Description

Technical Field

[0001] The present application relates to the technical field of artificial intelligence and intelligent detection of abnormal vehicle parts, and in particular to a method for automatically detecting and processing abnormal vehicle parts information and related equipment. Background Art

[0002] The traditional vehicle standard damage assessment system maintains spare parts information for major manufacturers by bundling three factors: regional and local city and county market prices, vehicle series level, and spare parts quality attributes.

[0003] However, combined maintenance based on manufacturers, organizations, quality, and original parts results in large and complex data volumes and a long data collection cycle. Despite spending a lot of manpower on information collection and maintenance, a large number of parts information anomalies cannot be avoided. In order to reduce the anomaly rate of vehicle parts information, the parts information maintenance post spends a lot of valuable time every day on manual screening and sorting of simple, repetitive, and abnormal types. This is not automated enough and also increases the time cost of manual screening by platform maintenance personnel. Summary of the Invention

[0004] The purpose of the embodiments of this application is to propose a method for automatic detection and processing of abnormal information of vehicle parts and related equipment, so as to realize the full automation of classification and collection of abnormal parts, reduce the time cost of manual screening by platform maintenance personnel, ensure user satisfaction and be more intelligent.

[0005] In order to solve the above technical problems, the present invention provides a method for automatically detecting and processing abnormal information of vehicle parts, which adopts the following technical solutions:

[0006] A method for automatically detecting and processing abnormal information of vehicle parts includes the following steps:

[0007] Obtain several pieces of vehicle parts information from the big data platform in real time and build an anomaly detection set;

[0008] Based on a preset vehicle parts anomaly classification model and the anomaly detection set, obtaining an anomaly type corresponding to the anomaly detection set, and adding the anomaly type to a preset vehicle parts anomaly list;

[0009] Determine whether the result in the vehicle parts abnormality list is a null value;

[0010] If so, the vehicle parts information obtained in real time from the big data platform is updated to the preset damage setting platform;

[0011] If not, obtain the abnormality type from the abnormal list of vehicle parts and send an abnormality warning to the damage assessment platform;

[0012] After receiving the abnormal warning, the damage assessment platform uses the abnormal type as a keyword to search for vehicle parts information containing the keyword that has been published by the damage assessment platform, and performs invalidation processing on the vehicle parts information.

[0013] Furthermore, before the step of obtaining the abnormality type corresponding to the abnormality detection set based on the preset vehicle parts abnormality classification model and the abnormality detection set, the method further includes:

[0014] Predetermine the types of anomalies and obtain a data set with a certain amount of anomaly data as a training set;

[0015] Constructing the same number of classifiers as the number of the anomaly types, wherein each classifier only classifies the anomaly type corresponding to it, and the anomaly types corresponding to each classifier are different;

[0016] Inputting the training set into each classifier in turn to obtain classification results;

[0017] Based on the amount of abnormal data corresponding to each abnormal type, determine whether the classification result corresponding to each abnormal type reaches a preset threshold;

[0018] If not, adjust the classification conditions of the classifier corresponding to the current abnormality type, input the training set into the adjusted classifier again, and obtain the classification results until the classification results reach the preset threshold. The learning and training of the classifier corresponding to the current abnormality type is completed;

[0019] After all classifiers have been trained, all classifiers are integrated to generate the vehicle parts abnormality classification model.

[0020] Furthermore, the step of obtaining the abnormality type corresponding to the abnormality detection set based on the preset vehicle parts abnormality classification model and the abnormality detection set specifically includes:

[0021] Entering the anomaly detection set into the vehicle parts anomaly classification model;

[0022] Based on the AdaBoost algorithm in the vehicle parts anomaly classification model, preliminarily determine the anomaly types corresponding to the abnormal vehicle parts information in the anomaly detection set;

[0023] Based on the naive Bayes algorithm in the vehicle parts anomaly classification model and the preliminary results, an anomaly type corresponding to the anomaly detection set is obtained.

[0024] Furthermore, the step of preliminarily determining the abnormality types corresponding to the abnormal vehicle parts information in the abnormality detection set based on the AdaBoost algorithm in the vehicle parts abnormality classification model specifically includes:

[0025] Based on the AdaBoost algorithm: Obtain the abnormal prediction scores corresponding to each classifier in the vehicle parts abnormal classification model, where i represents the number of the sample in the abnormal detection set, α i Indicates the classification weight obtained by the current classifier when performing the i-th classification, G i (x) represents the classification function corresponding to the i-th classification performed by the current classifier, and n represents the number of samples in the anomaly detection set;

[0026] Based on the preset abnormal classification score interval and the abnormal prediction score, the abnormal types corresponding to the abnormal vehicle parts information in the abnormal detection set are preliminarily determined.

[0027] Furthermore, the step of obtaining the anomaly type corresponding to the anomaly detection set based on the naive Bayes algorithm in the vehicle parts anomaly classification model and the preliminary results specifically includes:

[0028] Counting the abnormal types corresponding to the abnormal vehicle parts information in the abnormal detection set;

[0029] Based on the statistical results, the proportion of vehicle parts information with the same abnormal type to the number of samples in the abnormality detection set is obtained;

[0030] Based on the preset naive Bayes algorithm: Get the conditional probability corresponding to different abnormal types, where P(A j ) represents the proportion value corresponding to the abnormal type numbered j, j represents the type number of the abnormal type, P(B) represents the proportion of abnormal data in the abnormal detection set, P(A j |B) represents the ratio of the amount of data corresponding to the anomaly type numbered j to the total amount of data with anomalies in the anomaly detection set;

[0031] The conditional probabilities corresponding to the different anomaly types are obtained, compared, and the anomaly type corresponding to the maximum conditional probability is selected as the anomaly type of the anomaly detection set.

[0032] Furthermore, after the step of obtaining the abnormality type from the vehicle parts abnormality list and sending an abnormality warning to a preset damage setting platform, the method further includes:

[0033] Send the vehicle parts information to the manual channel for abnormality verification and obtain the verification result;

[0034] Determine whether the verification result is consistent with the abnormality type based on a preset judgment condition;

[0035] If the verification result is inconsistent with the abnormality type, feedback adjustment is performed on the vehicle parts abnormality classification model, wherein the conditions for the verification result to be inconsistent with the abnormality type include:

[0036] First condition: the verification result indicates that the vehicle parts information has an abnormality, but the abnormality type is inconsistent with the abnormality type obtained from the vehicle parts abnormality list;

[0037] The second condition is that the verification result shows that there is no abnormality in the vehicle accessories information.

[0038] Furthermore, it is characterized in that the step of performing feedback adjustment on the vehicle parts abnormality classification model specifically includes:

[0039] Adjust the algorithm based on preset weights: Feedback adjustment is performed on each classifier in the vehicle parts abnormal classification model, where α i Indicates the classification weight obtained by the current classifier when performing the i-th classification, e i Indicates the classification error rate corresponding to the i-th classification performed by the current classifier;

[0040] Feedback adjustment is completed until the number of classifications completed by each classifier reaches the corresponding preset classification number threshold or the classification error rate corresponding to each classifier is less than the corresponding preset classification error rate threshold.

[0041] In order to solve the above technical problems, the present application also provides an automatic detection and processing device for abnormal information of vehicle parts, which adopts the following technical solution:

[0042] A device for automatically detecting and processing abnormal information of vehicle parts, comprising:

[0043] The data collection module is used to obtain a number of vehicle parts information from the big data platform in real time and build an anomaly detection set;

[0044] An automatic detection module, configured to obtain an anomaly type corresponding to the anomaly detection set based on a preset vehicle parts anomaly classification model and the anomaly detection set, and add the anomaly type to a preset vehicle parts anomaly list;

[0045] A judgment module, used to judge whether the result in the vehicle parts abnormality list is a null value;

[0046] The first processing module is configured to update the plurality of pieces of vehicle parts information obtained in real time from the big data platform to a preset damage setting platform if yes;

[0047] A second processing module is configured to, if not, obtain the abnormality type from the vehicle parts abnormality list and send an abnormality warning to the damage assessment platform;

[0048] The third processing module is used for the damage assessment platform to use the abnormality type as a keyword to search for vehicle parts information containing the keyword that has been published by the damage assessment platform after receiving the abnormality warning, and to perform invalidation processing on the vehicle parts information.

[0049] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0050] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the above-mentioned method for automatically detecting and processing abnormal information of vehicle parts when executing the computer-readable instructions.

[0051] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0052] A computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the above-mentioned method for automatically detecting and processing abnormal information of vehicle parts.

[0053] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0054] The method for automatically detecting and processing abnormal information of vehicle parts described in the embodiment of the present application comprises the following steps: obtaining an abnormal detection set; obtaining the abnormal type corresponding to the abnormal detection set, and adding the abnormal type to a preset vehicle parts abnormal list; determining whether the result in the vehicle parts abnormal list is a null value; if so, updating the vehicle parts information to a preset damage assessment platform; if not, sending an abnormality warning to the damage assessment platform; using the abnormal type as a keyword to search for vehicle parts information containing the keyword published by the damage assessment platform, and invalidating the vehicle parts information. The present application realizes the fully automated classification and collection of abnormal parts, reduces the time cost of manual screening by platform maintenance personnel, ensures user satisfaction, and is more intelligent. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the solutions in this application, a brief introduction will be given below to the drawings required for use in the description of the embodiments of this application. Obviously, the drawings described below are some embodiments of this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0056] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0057] Figure 2A flowchart of an embodiment of a method for automatically detecting and processing abnormal information of vehicle parts according to the present application;

[0058] Figure 3 This is the implementation Figure 2 A flowchart of a specific implementation of training a vehicle parts anomaly classification model before step 202 is shown;

[0059] Figure 4 yes Figure 2 A flowchart of a specific implementation of step 202 is shown;

[0060] Figure 5 yes Figure 4 A flowchart of a specific implementation of step 402 is shown;

[0061] Figure 6 yes Figure 4 A flowchart of a specific implementation of step 403 is shown;

[0062] Figure 7 A schematic structural diagram of an embodiment of a device for automatically detecting and processing abnormal information of vehicle parts according to the present application;

[0063] Figure 8 yes Figure 7 A schematic structural diagram of an embodiment of 702 is shown;

[0064] Figure 9 A schematic structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0065] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of the application are for the purpose of describing specific embodiments only and are not intended to limit this application. The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0066] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0067] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0068] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is a medium for providing communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0069] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0070] Terminal devices 101, 102, and 103 can be various electronic devices with display screens and support web browsing, including but not limited to smartphones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV), laptop computers, desktop computers, etc.

[0071] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0072] It should be noted that the method for automatically detecting and processing abnormal information of vehicle parts provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the device for automatically detecting and processing abnormal information of vehicle parts is generally set in the server / terminal device.

[0073] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0074] Continue to refer Figure 2 , shows a flow chart of an embodiment of the method for automatically detecting and processing abnormal information of vehicle parts according to the present application. The method for automatically detecting and processing abnormal information of vehicle parts includes the following steps:

[0075] Step 201: Obtain a number of pieces of vehicle parts information from a big data platform in real time and construct an anomaly detection set.

[0076] In this embodiment, the big data platform includes quotation information of various auto parts manufacturers and quotation information of various auto parts operating platforms.

[0077] Step 202: Based on the preset vehicle parts anomaly classification model and the anomaly detection set, obtain the anomaly type corresponding to the anomaly detection set, and add the anomaly type to a preset vehicle parts anomaly list.

[0078] In this embodiment, before the step of obtaining the abnormality type corresponding to the abnormality detection set based on the preset vehicle parts abnormality classification model and the abnormality detection set, the method further includes:

[0079] Train the vehicle parts anomaly classification model through offline supervised learning;

[0080] Among them, the step of training the vehicle parts abnormality classification model through offline supervised learning specifically includes: pre-setting the types of abnormalities and obtaining a data set with a certain amount of abnormal data as a training set; constructing the same number of classifiers as the types of abnormalities, wherein each classifier only classifies its corresponding abnormality type, and the abnormality types corresponding to each classifier are different; inputting the training set into each classifier in turn to obtain classification results; based on the amount of abnormal data corresponding to each abnormal type, judging whether the classification result corresponding to each abnormal type reaches a preset threshold; if not, adjusting the classification condition of the classifier corresponding to the current abnormal type, inputting the training set into the adjusted classifier again to obtain classification results, until the classification result reaches the preset threshold, and the learning and training of the classifier corresponding to the current abnormal type is completed; until the learning and training of all classifiers are completed, all classifiers are integrated to generate the vehicle parts abnormality classification model.

[0081] In this embodiment, the setting of the abnormal type category is mainly to detect whether there is any abnormality in the quotation information of related vehicle parts in the car insurance claim business. The damage assessment platform performs risk control processing based on the automatic detection results to ensure that the car owners applying for claims are satisfied with the quotation of vehicle parts, thereby improving the trust of business users.

[0082] In this embodiment, the types of abnormalities may include: inverted prices of auto parts, missing prices, untimely price updates, prices exceeding the original factory prices of headquarters, missing user prices, parts-related institutions exceeding the collection location, regional deviations in price rankings, overdue updates of specific parts, inconsistent prices of left and right parts, inconsistent prices of different car series with the same code and brand, excessive adjustment trends compared to historical levels, frequent price adjustments, etc.

[0083] Through offline supervised learning, multiple classifiers are trained. Each classifier is responsible for detecting a type of anomaly. All trained classifiers are integrated into a vehicle parts anomaly classification model. This model can be used directly for subsequent detection of vehicle parts anomaly information. This ensures that one model can automatically detect multiple anomaly types, reducing the amount of manual detection and automating detection, making it more intelligent and convenient to use.

[0084] Continue to refer Figure 3 , Figure 3 This is the implementation Figure 2 The flowchart of a specific implementation of training the vehicle parts abnormality classification model before step 202 is shown, including the steps of:

[0085] Step 301: pre-set the abnormality type and obtain a data set with a certain amount of abnormal data as a training set;

[0086] Step 302: constructing the same number of classifiers as the number of the anomaly types, wherein each classifier classifies only the anomaly type corresponding to it, and the anomaly types corresponding to each classifier are different;

[0087] Step 303: input the training set into each classifier in sequence to obtain classification results;

[0088] Step 304: Based on the amount of abnormal data corresponding to each abnormal type, determine whether the classification result corresponding to each abnormal type reaches a preset threshold;

[0089] Step 305: If not, adjust the classification conditions of the classifier corresponding to the current abnormality type, input the training set into the adjusted classifier again, and obtain the classification results. When the classification results reach the preset threshold, the training of the classifier corresponding to the current abnormality type is completed.

[0090] Step 306: until all classifiers are trained, all classifiers are integrated to generate a vehicle parts abnormality classification model;

[0091] Step 307: If yes, then the learning and training of all classifiers are completed, and all the classifiers are integrated to generate a vehicle parts abnormality classification model.

[0092] In this embodiment, the step of obtaining the abnormality type corresponding to the abnormality detection set based on the preset vehicle parts abnormality classification model and the abnormality detection set specifically includes: entering the abnormality detection set into the vehicle parts abnormality classification model; based on the AdaBoost algorithm in the vehicle parts abnormality classification model, preliminarily determining the abnormality types corresponding to the abnormal vehicle parts information in the abnormality detection set; based on the Naive Bayes algorithm in the vehicle parts abnormality classification model and the preliminary results, obtaining the abnormality type corresponding to the abnormality detection set.

[0093] By combining the AdaBoost algorithm and the Naive Bayes algorithm in the vehicle parts anomaly classification model, the anomaly type corresponding to the anomaly detection set is obtained to ensure the detection accuracy of vehicle parts anomaly information.

[0094] Continue to refer Figure 4 , Figure 4 yes Figure 2 The flowchart of a specific implementation of step 202 shown includes the following steps:

[0095] Step 401: input the anomaly detection set into the vehicle parts anomaly classification model;

[0096] Step 402: Preliminarily determine the anomaly types corresponding to the abnormal vehicle parts information in the anomaly detection set based on the AdaBoost algorithm in the vehicle parts anomaly classification model;

[0097] Step 403: Based on the naive Bayes algorithm in the vehicle parts anomaly classification model and the preliminary result, obtain the anomaly type corresponding to the anomaly detection set.

[0098] In this embodiment, the step of preliminarily determining the abnormality types corresponding to the abnormal vehicle parts information in the abnormality detection set based on the AdaBoost algorithm in the vehicle parts abnormality classification model specifically includes: based on the AdaBoost algorithm: Obtain the abnormal prediction scores corresponding to each classifier in the vehicle parts abnormal classification model, where i represents the number of the sample in the abnormal detection set, α i Indicates the classification weight obtained by the current classifier when performing the i-th classification, G i (x) represents the classification function corresponding to the i-th classification performed by the current classifier, and n represents the number of samples in the anomaly detection set. Based on the preset anomaly classification score interval and the anomaly prediction score, the anomaly types corresponding to the abnormal vehicle parts information in the anomaly detection set are preliminarily determined.

[0099] The AdaBoost algorithm is used to preliminarily determine the anomaly types corresponding to the abnormal vehicle parts information in the anomaly detection set. Since there are multiple classifiers, multiple anomaly types and multiple vehicle parts information, an anomaly classification score interval is set for the detection result of each classifier. When performing anomaly detection on each vehicle parts information, it is only necessary to obtain the anomaly prediction score corresponding to the current vehicle parts information according to the AdaBoost algorithm, and then judge the corresponding anomaly classification score interval to determine the anomaly type of the current vehicle parts information. If the vehicle parts information has multiple anomaly types, due to the relative independence of the classifiers, it does not affect the anomaly detection by each classifier in turn, and multiple anomaly types are obtained. The AdaBoost algorithm and the classifiers in the vehicle parts anomaly classification model are used to ensure comprehensive and automated detection of multiple anomaly types for the elements in the anomaly detection set.

[0100] Continue to refer Figure 5 , Figure 5 yes Figure 4 The flowchart of a specific implementation of step 402 shown includes the following steps:

[0101] Step 501, based on the AdaBoost algorithm: Obtain the abnormal prediction scores corresponding to each classifier in the vehicle parts abnormal classification model, where i represents the number of the sample in the abnormal detection set, α i Indicates the classification weight obtained by the current classifier when performing the i-th classification, G i (x) represents the classification function corresponding to the i-th classification performed by the current classifier, and n represents the number of samples in the anomaly detection set;

[0102] Step 502 : Preliminarily determine the abnormality types corresponding to the abnormal vehicle parts information in the abnormality detection set based on the preset abnormality classification score interval and the abnormality prediction score.

[0103] In this embodiment, the step of obtaining the abnormality type corresponding to the abnormality detection set based on the naive Bayes algorithm in the vehicle parts abnormality classification model and the preliminary results specifically includes: counting the abnormality types corresponding to the abnormal vehicle parts information in the abnormality detection set; based on the statistical results, obtaining the proportion of vehicle parts information with the same abnormality type to the number of samples in the abnormality detection set; based on the preset naive Bayes algorithm: Get the conditional probability corresponding to different abnormal types, where P(A j ) represents the proportion value corresponding to the abnormal type numbered j, j represents the type number of the abnormal type, P(B) represents the proportion of abnormal data in the abnormal detection set, P(A j|B) represents the proportion of the data volume corresponding to the anomaly type numbered j to the total data volume of anomalies in the anomaly detection set; obtaining the conditional probabilities corresponding to the different anomaly types, comparing them, and selecting the anomaly type corresponding to the maximum conditional probability as the anomaly type of the anomaly detection set.

[0104] Through the Naive Bayes algorithm, the anomaly types determined after the preliminary detection of the anomaly detection set are selected, and the anomaly type with the maximum conditional probability is screened out as the anomaly type of the anomaly detection set. This makes it easier for the damage assessment platform in the later stage to directly find the car parts with the anomaly that have been released on the platform through the keywords corresponding to the anomaly type, making it easier for the damage assessment platform to automatically perform risk control judgments, which is more intelligent.

[0105] Continue to refer Figure 6 , Figure 6 yes Figure 4 The flowchart of a specific implementation of step 403 shown includes the following steps:

[0106] Step 601: Count the abnormal types corresponding to the abnormal vehicle parts information in the abnormal detection set;

[0107] Step 602: Based on the statistical results, obtain the proportion of vehicle parts information with the same abnormal type to the number of samples in the abnormality detection set;

[0108] Step 603, based on the preset Naive Bayes algorithm: Get the conditional probability corresponding to different abnormal types, where P(A j ) represents the proportion value corresponding to the abnormal type numbered j, j represents the type number of the abnormal type, P(B) represents the proportion of abnormal data in the abnormal detection set, P(A j |B) represents the ratio of the amount of data corresponding to the anomaly type numbered j to the total amount of data with anomalies in the anomaly detection set;

[0109] Step 604 : Obtain the conditional probabilities corresponding to the different anomaly types, compare them, and select the anomaly type corresponding to the maximum conditional probability as the anomaly type of the anomaly detection set.

[0110] Step 203: Determine whether the result in the vehicle parts abnormality list is a null value.

[0111] Step 204: If yes, then update the plurality of pieces of vehicle parts information obtained in real time from the big data platform to the preset damage platform.

[0112] In this embodiment, if the result in the vehicle parts abnormality list is a null value, it means that the elements in the abnormality detection set are all normal data, which are directly updated to the preset damage assessment platform to replace the original damage assessment information. The data is obtained in real time through the big data platform in step 201 to ensure the real-time and referenceability of the vehicle parts damage assessment information, ensure timely and transparent information acquisition, and improve the satisfaction of business users.

[0113] Step 205: If not, obtain the abnormality type from the vehicle parts abnormality list and send an abnormality warning to the damage assessment platform.

[0114] In this embodiment, after the step of obtaining the abnormality type from the vehicle parts abnormality list and sending an abnormality warning to the preset damage platform, the method further includes: sending the vehicle parts information to a manual channel for abnormality verification to obtain a verification result; judging whether the verification result is consistent with the abnormality type based on preset judgment conditions; if the verification result is consistent with the abnormality type, there is no need to perform feedback adjustment on the vehicle parts abnormality classification model; if the verification result is inconsistent with the abnormality type, feedback adjustment is performed on the vehicle parts abnormality classification model, wherein the conditions for the verification result to be inconsistent with the abnormality type include: a first condition, the verification result indicates that there is an abnormality in the vehicle parts information but the abnormality type is inconsistent with the abnormality type obtained from the vehicle parts abnormality list; a second condition, the verification result indicates that there is no abnormality in the vehicle parts information.

[0115] By sending the vehicle parts information to the manual channel for abnormality verification and comparing it with the automated abnormality detection results, on the one hand, the accuracy of abnormality type detection is guaranteed, and on the other hand, it is convenient for manual risk control to be carried out in a timely manner.

[0116] In this embodiment, the step of performing feedback adjustment on the vehicle parts abnormality classification model specifically includes: adjusting the algorithm based on a preset weight: Feedback adjustment is performed on each classifier in the vehicle parts abnormal classification model, where α i Indicates the classification weight obtained by the current classifier when performing the i-th classification, e i It represents the classification error rate corresponding to the i-th classification performed by the current classifier; feedback adjustment is completed until the number of classifications completed by each classifier reaches the corresponding preset classification number threshold or the classification error rate corresponding to each classifier is less than the corresponding preset classification error rate threshold.

[0117] Feedback adjustment is performed on the vehicle parts abnormality classification model through a weight adjustment algorithm, ensuring that the model learning and updating are continuously performed during use until specific conditions are met, at which time the model updating is stopped, thereby ensuring the accuracy of model detection.

[0118] Step 206: After receiving the abnormal warning, the damage assessment platform uses the abnormal type as a keyword to search for vehicle parts information containing the keyword that has been published by the damage assessment platform, and performs invalidation processing on the vehicle parts information.

[0119] In this embodiment, the step of performing invalidation processing on the vehicle parts information specifically includes: pre-setting an invalid state and an available state; and converting the state of the vehicle parts information containing the abnormal type that has been published on the damage assessment platform from an available state to an invalid state.

[0120] This application obtains an anomaly detection set; obtains the anomaly type corresponding to the anomaly detection set, and adds the anomaly type to a preset vehicle parts anomaly list; determines whether the result in the vehicle parts anomaly list is null; if so, updates the vehicle parts information to a preset damage assessment platform; if not, sends an anomaly warning to the damage assessment platform; uses the anomaly type as a keyword to search for vehicle parts information containing the keyword published by the damage assessment platform, and invalidates the vehicle parts information. This application fully automates the classification and collection of abnormal parts, reduces the time cost of manual screening by platform maintenance personnel, ensures user satisfaction, and is more intelligent.

[0121] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0122] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0123] In the embodiment of the present application, the classification model is trained and updated using machine learning in artificial intelligence technology to ensure the accuracy of the detection results of abnormal information of vehicle parts.

[0124] Further references Figure 7 , as a response to the above Figure 2 The present application provides an embodiment of a device for automatically detecting and processing abnormal information of vehicle parts. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0125] like Figure 7 As shown, the automatic detection and processing device 700 for abnormal vehicle parts information of this embodiment includes: a data acquisition module 701, an automatic detection module 702, a judgment module 703, a first processing module 704, a second processing module 705 and a third processing module 706.

[0126] The data collection module 701 is used to obtain a number of vehicle parts information from the big data platform in real time and build an anomaly detection set;

[0127] The automatic detection module 702 is configured to obtain an anomaly type corresponding to the anomaly detection set based on a preset vehicle parts anomaly classification model and the anomaly detection set, and add the anomaly type to a preset vehicle parts anomaly list;

[0128] The judgment module 703 is used to judge whether the result in the vehicle parts abnormality list is a null value;

[0129] The first processing module 704 is configured to update the plurality of pieces of vehicle parts information obtained in real time from the big data platform to a preset damage setting platform;

[0130] The second processing module 705 is configured to, if not, obtain the abnormality type from the vehicle parts abnormality list and send an abnormality warning to the damage assessment platform;

[0131] The third processing module 706 is used for the damage assessment platform to use the abnormality type as a keyword to search for vehicle parts information containing the keyword that has been published by the damage assessment platform after receiving the abnormality warning, and to perform invalidation processing on the vehicle parts information.

[0132] This application obtains an anomaly detection set; obtains the anomaly type corresponding to the anomaly detection set, and adds the anomaly type to a preset vehicle parts anomaly list; determines whether the result in the vehicle parts anomaly list is null; if so, updates the vehicle parts information to a preset damage assessment platform; if not, sends an anomaly warning to the damage assessment platform; uses the anomaly type as a keyword to search for vehicle parts information containing the keyword published by the damage assessment platform, and invalidates the vehicle parts information. This application fully automates the classification and collection of abnormal parts, reduces the time cost of manual screening by platform maintenance personnel, ensures user satisfaction, and is more intelligent.

[0133] Continue to refer Figure 8 , Figure 8 yes Figure 7 As shown in FIG702, a structural diagram of a specific embodiment, the automatic detection module 702 includes: a first algorithm submodule 7021, a second algorithm submodule 7022 and a feedback adjustment submodule 7023.

[0134] The first algorithm submodule 7021 is used to preliminarily determine the anomaly types corresponding to the abnormal vehicle parts information in the anomaly detection set based on the AdaBoost algorithm in the vehicle parts anomaly classification model. Specifically, it is used to preliminarily determine the anomaly types corresponding to the abnormal vehicle parts information in the anomaly detection set based on the AdaBoost algorithm: Obtain the abnormal prediction scores corresponding to each classifier in the vehicle parts abnormal classification model, where i represents the number of the sample in the abnormal detection set, α i Indicates the classification weight obtained by the current classifier when performing the i-th classification, G i (x) represents the classification function corresponding to the i-th classification performed by the current classifier, and n represents the number of samples in the anomaly detection set; and is also used to preliminarily determine the anomaly types corresponding to the abnormal vehicle parts information in the anomaly detection set based on the preset anomaly classification score interval and the anomaly prediction score.

[0135] The second algorithm submodule 7022 is configured to obtain an anomaly type corresponding to the anomaly detection set based on the naive Bayes algorithm in the vehicle parts anomaly classification model and the preliminary results. Specifically, the second algorithm submodule 7022 is configured to count the anomaly types corresponding to the vehicle parts information with anomalies in the anomaly detection set; further configured to obtain, based on the statistical results, the proportion of vehicle parts information with the same anomaly type to the number of samples in the anomaly detection set; and further configured to use the preset naive Bayes algorithm: Get the conditional probability corresponding to different abnormal types, where P(A j ) represents the proportion value corresponding to the abnormal type numbered j, j represents the type number of the abnormal type, P(B) represents the proportion of abnormal data in the abnormal detection set, P(A j |B) represents the proportion of the data volume corresponding to the anomaly type numbered j to the total data volume of anomalies in the anomaly detection set; is also used to obtain the conditional probabilities corresponding to the different anomaly types, compare them, and select the anomaly type corresponding to the maximum conditional probability as the anomaly type of the anomaly detection set.

[0136] Feedback adjustment submodule 7023 is used to adjust the algorithm based on preset weights: Feedback adjustment is performed on each classifier in the vehicle parts abnormal classification model, where α i Indicates the classification weight obtained by the current classifier when performing the i-th classification, e i It indicates the classification error rate corresponding to the i-th classification performed by the current classifier; it is also used to complete the feedback adjustment until the number of classifications completed by each classifier reaches the corresponding preset classification number threshold or the classification error rate corresponding to each classifier is less than the corresponding preset classification error rate threshold.

[0137] Through the first algorithm submodule and the second algorithm submodule, the anomaly type of the anomaly detection set is obtained, and then the feedback adjustment submodule is used to feedback and adjust each classifier in the vehicle parts anomaly classification model to achieve automatic learning and detection during use, ensuring the accuracy and intelligence of model detection.

[0138] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware via computer-readable instructions. The computer-readable instructions can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes in the above-described method embodiments. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0139] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0140] To solve the above technical problems, the present application also provides a computer device. Figure 9 , Figure 9 This is a basic structural block diagram of the computer device in this embodiment.

[0141] The computer device 9 includes a memory 91, a processor 92, and a network interface 93 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 9 with components 91-93, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0142] The computer device may be a desktop computer, notebook computer, PDA, cloud server, etc. The computer device may interact with the user via a keyboard, mouse, remote control, touchpad, or voice control device.

[0143] The memory 91 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic storage, magnetic disk, optical disk, etc. In some embodiments, the memory 91 can be an internal storage unit of the computer device 9, such as the hard disk or memory of the computer device 9. In other embodiments, the memory 91 can also be an external storage device of the computer device 9, such as a plug-in hard disk equipped on the computer device 9, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Of course, the memory 91 can also include both the internal storage unit of the computer device 9 and its external storage device. In this embodiment, the memory 91 is generally used to store the operating system and various application software installed on the computer device 9, such as computer-readable instructions for the method for automatically detecting and processing abnormal information of vehicle parts. In addition, the memory 91 can also be used to temporarily store various types of data that have been output or are to be output.

[0144] In some embodiments, the processor 92 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 92 is generally used to control the overall operation of the computer device 9. In this embodiment, the processor 92 is used to execute computer-readable instructions or process data stored in the memory 91, such as computer-readable instructions for executing the method for automatically detecting and processing abnormal vehicle parts information.

[0145] The network interface 93 may include a wireless network interface or a wired network interface. The network interface 93 is generally used to establish a communication connection between the computer device 9 and other electronic devices.

[0146] The computer device proposed in this embodiment belongs to the technical field of intelligent detection of abnormal information of auto parts. This application obtains an abnormality detection set; obtains the abnormality type corresponding to the abnormality detection set, and adds the abnormality type to a preset auto parts abnormality list; determines whether the result in the said auto parts abnormality list is a null value; if so, updates the auto parts information to the preset damage assessment platform; if not, sends an abnormality warning to the damage assessment platform; uses the abnormality type as a keyword to search for auto parts information containing the keyword that has been published by the damage assessment platform, and performs invalidation processing on the auto parts information. This application realizes the full automation of the classification and collection of abnormal parts, reduces the time cost of manual screening by platform maintenance personnel, ensures user satisfaction and is more intelligent.

[0147] The present application also provides another embodiment, namely, providing a computer-readable storage medium, which stores computer-readable instructions, and the computer-readable instructions can be executed by a processor to enable the processor to perform the steps of the above-mentioned method for automatically detecting and processing abnormal information of vehicle parts.

[0148] The computer-readable storage medium proposed in this embodiment belongs to the technical field of intelligent detection of abnormal information of vehicle parts. This application obtains an abnormality detection set; obtains the abnormality type corresponding to the abnormality detection set, and adds the abnormality type to a preset vehicle parts abnormality list; determines whether the result in the vehicle parts abnormality list is a null value; if so, updates the vehicle parts information to the preset damage assessment platform; if not, sends an abnormality warning to the damage assessment platform; uses the abnormality type as a keyword to search for vehicle parts information containing the keyword that has been published by the damage assessment platform, and performs invalidation processing on the vehicle parts information. This application realizes the full automation of the classification and collection of abnormal parts, reduces the time cost of manual screening by platform maintenance personnel, ensures user satisfaction and is more intelligent.

[0149] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0150] Obviously, the embodiments described above are only some of the embodiments of the present application, rather than all of the embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions described in the aforementioned specific embodiments, or to make equivalent replacements for some of the technical features therein. Any equivalent structure made using the contents of the present application specification and the accompanying drawings, directly or indirectly used in other related technical fields, is also within the scope of patent protection of the present application.

Claims

1. A method for automatically detecting and processing abnormal information of vehicle parts, characterized in that: The steps include: Obtain several pieces of vehicle parts information from the big data platform in real time and build an anomaly detection set; Based on a preset vehicle parts anomaly classification model and the anomaly detection set, obtaining an anomaly type corresponding to the anomaly detection set, and adding the anomaly type to a preset vehicle parts anomaly list; Determine whether the result in the vehicle parts abnormality list is a null value; If so, the vehicle parts information obtained in real time from the big data platform is updated to the preset damage setting platform; If not, obtain the abnormality type from the abnormal list of vehicle parts and send an abnormality warning to the damage assessment platform; Send the vehicle parts information to the manual channel for abnormality verification and obtain the verification result; Based on a preset judgment condition, it is determined whether the verification result is consistent with the abnormality type; if the verification result is inconsistent with the abnormality type, feedback adjustment is performed on the vehicle parts abnormality classification model, wherein the conditions for the verification result to be inconsistent with the abnormality type include: a first condition, the verification result indicates that the vehicle parts information has an abnormality but the abnormality type is inconsistent with the abnormality type obtained from the vehicle parts abnormality list; a second condition, the verification result indicates that the vehicle parts information does not have an abnormality; After receiving the abnormal warning, the damage assessment platform uses the abnormal type as a keyword to search for vehicle parts information containing the keyword that has been published by the damage assessment platform, and performs invalidation processing on the vehicle parts information.

2. The method for automatically detecting and processing abnormal information of vehicle parts according to claim 1, characterized in that: Before the step of obtaining the abnormality type corresponding to the abnormality detection set based on the preset vehicle parts abnormality classification model and the abnormality detection set, the method further includes: Predetermine the types of anomalies and obtain a data set with a certain amount of anomaly data as a training set; Constructing the same number of classifiers as the number of the anomaly types, wherein each classifier only classifies the anomaly type corresponding to it, and the anomaly types corresponding to each classifier are different; Inputting the training set into each classifier in turn to obtain classification results; Based on the amount of abnormal data corresponding to each abnormal type, determine whether the classification result corresponding to each abnormal type reaches a preset threshold; If not, adjust the classification conditions of the classifier corresponding to the current abnormality type, input the training set into the adjusted classifier again, and obtain the classification results until the classification results reach the preset threshold. The learning and training of the classifier corresponding to the current abnormality type is completed; After all classifiers have been trained, all classifiers are integrated to generate the vehicle parts abnormality classification model.

3. The method for automatically detecting and processing abnormal information of vehicle parts according to claim 2, characterized in that: The step of obtaining the abnormality type corresponding to the abnormality detection set based on the preset vehicle parts abnormality classification model and the abnormality detection set specifically includes: Entering the anomaly detection set into the vehicle parts anomaly classification model; Based on the AdaBoost algorithm in the vehicle parts anomaly classification model, preliminarily determine the anomaly types corresponding to the abnormal vehicle parts information in the anomaly detection set; Based on the naive Bayes algorithm and preliminary results in the vehicle parts anomaly classification model, the anomaly type corresponding to the anomaly detection set is obtained.

4. The method for automatically detecting and processing abnormal information of vehicle parts according to claim 3, characterized in that: The step of preliminarily determining the abnormality types corresponding to the abnormal vehicle parts information in the abnormality detection set based on the AdaBoost algorithm in the vehicle parts abnormality classification model specifically includes: Based on the AdaBoost algorithm: , obtain the abnormal prediction scores corresponding to each classifier in the vehicle parts abnormal classification model, where, represents the number of the sample in the anomaly detection set, Indicates that the current classifier performs the The classification weight obtained during the second classification, Indicates that the current classifier performs the The corresponding classification function for the sub-classification is, represents the number of samples in the anomaly detection set; Based on the preset abnormal classification score interval and the abnormal prediction score, the abnormal types corresponding to the abnormal vehicle parts information in the abnormal detection set are preliminarily determined.

5. The method for automatically detecting and processing abnormal information of vehicle parts according to claim 4, characterized in that: The step of obtaining the anomaly type corresponding to the anomaly detection set based on the naive Bayes algorithm in the vehicle parts anomaly classification model and the preliminary results specifically includes: Counting the abnormal types corresponding to the abnormal vehicle parts information in the abnormal detection set; Based on the statistical results, the proportion of vehicle parts information with the same abnormal type to the number of samples in the abnormality detection set is obtained; Based on the preset naive Bayes algorithm: , obtain the conditional probabilities corresponding to different anomaly types, where Indicates the ratio value corresponding to the abnormal type numbered j, where j represents the type number of the abnormal type. Indicates the proportion of abnormal data in the anomaly detection set, The ratio of the data volume corresponding to the anomaly type numbered j to the total data volume with anomalies in the anomaly detection set; The conditional probabilities corresponding to the different anomaly types are obtained, compared, and the anomaly type corresponding to the maximum conditional probability is selected as the anomaly type of the anomaly detection set.

6. The method for automatically detecting and processing abnormal information of vehicle parts according to claim 1, characterized in that: The step of performing feedback adjustment on the vehicle parts abnormality classification model specifically includes: Adjust the algorithm based on preset weights: , feedback adjustment is performed on each classifier in the vehicle parts abnormal classification model, wherein, Indicates that the current classifier performs the The classification weight obtained during the second classification, Indicates that the current classifier performs the The corresponding classification error rate during the secondary classification; Feedback adjustment is completed until the number of classifications completed by each classifier reaches the corresponding preset classification number threshold or the classification error rate corresponding to each classifier is less than the corresponding preset classification error rate threshold.

7. A device for automatically detecting and processing abnormal information of vehicle parts, characterized in that: include: The data collection module is used to obtain a number of vehicle parts information from the big data platform in real time and build an anomaly detection set; An automatic detection module, configured to obtain an anomaly type corresponding to the anomaly detection set based on the vehicle parts anomaly classification model and the anomaly detection set, and add the anomaly type to a preset vehicle parts anomaly list; A judgment module, used to judge whether the result in the vehicle parts abnormality list is a null value; The first processing module is configured to update the plurality of pieces of vehicle parts information obtained in real time from the big data platform to a preset damage setting platform if yes; A second processing module is configured to, if not, obtain the abnormality type from the vehicle parts abnormality list and send an abnormality warning to the damage assessment platform; Send the vehicle parts information to the manual channel for abnormality verification and obtain the verification result; Based on a preset judgment condition, it is determined whether the verification result is consistent with the abnormality type; if the verification result is inconsistent with the abnormality type, feedback adjustment is performed on the vehicle parts abnormality classification model, wherein the conditions for the verification result to be inconsistent with the abnormality type include: a first condition, the verification result indicates that the vehicle parts information has an abnormality but the abnormality type is inconsistent with the abnormality type obtained from the vehicle parts abnormality list; a second condition, the verification result indicates that the vehicle parts information does not have an abnormality; The third processing module is used for the damage assessment platform to use the abnormality type as a keyword to search for vehicle parts information containing the keyword that has been published by the damage assessment platform after receiving the abnormality warning, and to perform invalidation processing on the vehicle parts information.

8. A computer device comprising a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the method for automatically detecting and processing abnormal information of vehicle parts according to any one of claims 1 to 6 when executing the computer-readable instructions.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the method for automatically detecting and processing abnormal information of vehicle parts according to any one of claims 1 to 6.

Images