Defect data processing method and system based on multi-server division of labor

Abstract

The present invention discloses a defect data processing method and system based on multi-server division of labor, the method comprising: obtaining multiple vehicle sensor data submitted by multiple vehicle detection systems and system information corresponding to each of the vehicle detection systems; grouping the multiple vehicle sensor data according to the system information and preset data efficiency grouping rules to obtain multiple vehicle data sets; determining the processing server corresponding to each of the vehicle data sets from multiple candidate servers; sending each of the vehicle data sets to the corresponding processing server for vehicle defect detection, and instructing the processing server to return the detection results to the corresponding vehicle detection system. It can be seen that the present invention can more reasonably and comprehensively schedule multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a defect data processing method and system based on multi-server division of labor. Background Art

[0002] With the development of data processing technology and the improvement of data processing equipment performance, more and more data processing intelligent technologies are being applied in the processing or testing of vehicles to improve the detection accuracy of vehicle defects, thus generating a large amount of vehicle defect detection data. In the prior art, when considering the processing of a large amount of vehicle defect detection data, most of them only use a single server or processing equipment to perform data analysis in accordance with the corresponding vehicle detection requirements, without considering the combination of multiple servers in the big data scenario to perform defect data processing. Therefore, the efficiency of data processing is not high, and the accuracy of vehicle defect detection is lacking. It can be seen that the prior art has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a defect data processing method and system based on multi-server division of labor, which can more reasonably and comprehensively schedule multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a defect data processing method based on multi-server division of labor, the method comprising:

[0005] Acquire a plurality of vehicle sensor data submitted by a plurality of vehicle detection systems and system information corresponding to each of the vehicle detection systems;

[0006] According to the system information and a preset data efficiency grouping rule, the plurality of vehicle sensor data are grouped to obtain a plurality of vehicle data sets;

[0007] Determine a processing server corresponding to each of the vehicle data sets from a plurality of candidate servers;

[0008] Each of the vehicle data sets is sent to the corresponding processing server for vehicle defect detection, and the processing server is instructed to return the detection result to the corresponding vehicle detection system.

[0009] As an optional embodiment, in the first aspect of the present invention, the system information includes system parameters and system history records; the system parameters include system location, system type and system equipment performance information; the system history records include system history data volume records and system history data integrity records.

[0010] As an optional implementation, in the first aspect of the present invention, the grouping of the plurality of vehicle sensor data to obtain a plurality of vehicle data sets according to the system information and a preset data efficiency grouping rule includes:

[0011] For each of the vehicle sensor data, calculating the system priority parameter corresponding to the vehicle sensor data according to the system history record of the vehicle detection system corresponding to the vehicle sensor data;

[0012] Determine the data priority parameter corresponding to the vehicle sensor data according to the data type of the vehicle sensor data and the correspondence between the preset data type and priority; the data type is image data, sound data, infrared ranging data, infrared imaging data, temperature and humidity data or light reflection three-dimensional model data;

[0013] defining a system similarity parameter between any two of the vehicle sensor data as the similarity between the system parameters of the vehicle detection systems corresponding to the two vehicle sensor data;

[0014] According to the system priority parameter, the data priority parameter and the system similarity parameter, the plurality of vehicle sensor data are grouped and iteratively calculated based on a dynamic programming algorithm to obtain a plurality of vehicle data sets.

[0015] As an optional implementation, in the first aspect of the present invention, the calculating the system priority parameter corresponding to the vehicle sensor data according to the system history record of the vehicle detection system corresponding to the vehicle sensor data includes:

[0016] Counting the weighted sum average of the data volumes of all data records in the system historical data volume record of the vehicle detection system corresponding to the vehicle sensor data, to obtain a system data volume parameter corresponding to the vehicle sensor data; wherein the weighted calculation weight corresponding to the data volume of each data record is proportional to the vehicle defect value corresponding to the corresponding data record; the vehicle defect value is used to characterize the degree of vehicle defect in the vehicle defect detection result corresponding to the vehicle sensor data corresponding to the data record;

[0017] The weighted average value of the data integrity of all data records in the system historical data integrity of the vehicle detection system corresponding to the vehicle sensor data is calculated to obtain the system data integrity parameter corresponding to the vehicle sensor data; wherein the weighted calculation weight corresponding to the data integrity of each data record is proportional to the defect prediction probability corresponding to the corresponding data record; the defect prediction probability is the confidence probability corresponding to the prediction result obtained when the vehicle sensor data corresponding to the data record is predicted by the corresponding vehicle defect prediction model;

[0018] A weighted average value of the system data volume parameter and the system data integrity parameter is calculated to obtain a system priority parameter corresponding to the vehicle sensor data.

[0019] As an optional implementation, in the first aspect of the present invention, the plurality of vehicle sensor data are grouped and iteratively calculated based on a dynamic programming algorithm according to the system priority parameter, the data priority parameter and the system similarity parameter to obtain a plurality of vehicle data sets, including:

[0020] Setting the objective function to maximize the number of vehicle sensor data in each vehicle data set and minimize the total number of all vehicle data sets;

[0021] Setting restrictions includes:

[0022] The system similarity parameter between any two vehicle sensor data in each vehicle data set is greater than a first parameter threshold;

[0023] The system similarity parameter between any of the vehicle sensor data respectively belonging to two different vehicle data sets is less than a second parameter threshold;

[0024] A difference between the system priority parameters of any two of the vehicle sensor data in each vehicle data set is less than a first difference threshold;

[0025] A difference between the data priority parameters of any two of the vehicle sensor data in each vehicle data set is less than a second difference threshold;

[0026] Based on a dynamic programming algorithm, the plurality of vehicle sensor data are iteratively calculated in groups according to the objective function and the constraint conditions until convergence, so as to obtain a plurality of vehicle data sets.

[0027] As an optional implementation, in the first aspect of the present invention, determining a processing server corresponding to each of the vehicle data sets from a plurality of candidate servers includes:

[0028] For each of the vehicle data sets, calculating a location distance parameter between a server location corresponding to each candidate server and a system location parameter corresponding to the vehicle data set;

[0029] Calculating data matching parameters between defect detection model parameters corresponding to each of the candidate servers and data type parameters corresponding to the vehicle data set;

[0030] Calculating a weighted sum of the location distance parameter and the data matching parameter corresponding to each of the candidate servers to obtain a server priority parameter corresponding to each of the candidate servers;

[0031] The candidate server with the highest server priority parameter is determined as the processing server corresponding to the vehicle data set.

[0032] As an optional implementation, in the first aspect of the present invention, the calculating of the location distance parameter between the server location corresponding to each candidate server and the system location parameter corresponding to the vehicle data set includes:

[0033] Determine the system position corresponding to the vehicle detection system corresponding to all the vehicle sensor data in the vehicle data set, and obtain multiple target system positions;

[0034] For each candidate server, calculating the location distance between the server location of the candidate server and each of the target system locations;

[0035] Calculate the weighted sum average of all the location distances to obtain the location distance parameter corresponding to the candidate server; wherein the weighted calculation weight corresponding to each location distance includes a first weight and a second weight; the first weight is proportional to the data transmission performance of the corresponding candidate server; the second weight is proportional to the data transmission performance of the corresponding vehicle detection system.

[0036] As an optional implementation, in the first aspect of the present invention, the step of calculating the data matching parameters between the defect detection model parameters corresponding to each of the candidate servers and the data type parameters corresponding to the vehicle data set includes:

[0037] Determine the data types corresponding to all the vehicle sensor data in the vehicle data set to obtain a target data type set;

[0038] For each of the candidate servers, obtaining training data records and historical prediction records of a prediction model used for vehicle defect detection in the candidate server;

[0039] Calculate the similarity between all data types in the training data record and the target data type set to obtain a data similarity parameter;

[0040] Calculate the average prediction accuracy of each data type in the target data type set in the historical prediction records to obtain a data prediction accuracy parameter;

[0041] The weighted average value of the data similarity parameter and the data prediction accuracy parameter is calculated to obtain the data matching parameter corresponding to the candidate server.

[0042] A second aspect of an embodiment of the present invention discloses a defect data processing system based on multi-server division of labor, the system comprising:

[0043] An acquisition module, used for acquiring a plurality of vehicle sensor data submitted by a plurality of vehicle detection systems and system information corresponding to each of the vehicle detection systems;

[0044] A grouping module, configured to group the plurality of vehicle sensor data to obtain a plurality of vehicle data sets according to the system information and a preset data efficiency grouping rule;

[0045] A determination module, used to determine a processing server corresponding to each of the vehicle data sets from a plurality of candidate servers;

[0046] The sending module is used to send each of the vehicle data sets to the corresponding processing server for vehicle defect detection, and instruct the processing server to return the detection result to the corresponding vehicle detection system.

[0047] As an optional embodiment, in the second aspect of the present invention, the system information includes system parameters and system history records; the system parameters include system location, system type and system equipment performance information; the system history records include system history data volume records and system history data integrity records.

[0048] As an optional implementation, in the second aspect of the present invention, the specific manner in which the grouping module groups the plurality of vehicle sensor data to obtain the plurality of vehicle data sets according to the system information and the preset data efficiency grouping rule includes:

[0049] For each of the vehicle sensor data, calculating the system priority parameter corresponding to the vehicle sensor data according to the system history record of the vehicle detection system corresponding to the vehicle sensor data;

[0050] Determine the data priority parameter corresponding to the vehicle sensor data according to the data type of the vehicle sensor data and the correspondence between the preset data type and priority; the data type is image data, sound data, infrared ranging data, infrared imaging data, temperature and humidity data or light reflection three-dimensional model data;

[0051] defining a system similarity parameter between any two of the vehicle sensor data as the similarity between the system parameters of the vehicle detection systems corresponding to the two vehicle sensor data;

[0052] According to the system priority parameter, the data priority parameter and the system similarity parameter, the plurality of vehicle sensor data are grouped and iteratively calculated based on a dynamic programming algorithm to obtain a plurality of vehicle data sets.

[0053] As an optional implementation, in the second aspect of the present invention, the specific manner in which the grouping module calculates the system priority parameter corresponding to the vehicle sensor data according to the system history record of the vehicle detection system corresponding to the vehicle sensor data includes:

[0054] Counting the weighted sum average of the data volumes of all data records in the system historical data volume record of the vehicle detection system corresponding to the vehicle sensor data, to obtain a system data volume parameter corresponding to the vehicle sensor data; wherein the weighted calculation weight corresponding to the data volume of each data record is proportional to the vehicle defect value corresponding to the corresponding data record; the vehicle defect value is used to characterize the degree of vehicle defect in the vehicle defect detection result corresponding to the vehicle sensor data corresponding to the data record;

[0055] The weighted average value of the data integrity of all data records in the system historical data integrity of the vehicle detection system corresponding to the vehicle sensor data is calculated to obtain the system data integrity parameter corresponding to the vehicle sensor data; wherein the weighted calculation weight corresponding to the data integrity of each data record is proportional to the defect prediction probability corresponding to the corresponding data record; the defect prediction probability is the confidence probability corresponding to the prediction result obtained when the vehicle sensor data corresponding to the data record is predicted by the corresponding vehicle defect prediction model;

[0056] A weighted average value of the system data volume parameter and the system data integrity parameter is calculated to obtain a system priority parameter corresponding to the vehicle sensor data.

[0057] As an optional implementation, in the second aspect of the present invention, the grouping module performs grouping iterative calculations on the multiple vehicle sensor data based on the dynamic programming algorithm according to the system priority parameter, the data priority parameter and the system similarity parameter to obtain a specific method of multiple vehicle data sets, including:

[0058] Setting the objective function to maximize the number of vehicle sensor data in each vehicle data set and minimize the total number of all vehicle data sets;

[0059] Setting restrictions includes:

[0060] The system similarity parameter between any two vehicle sensor data in each vehicle data set is greater than a first parameter threshold;

[0061] The system similarity parameter between any of the vehicle sensor data respectively belonging to two different vehicle data sets is less than a second parameter threshold;

[0062] A difference between the system priority parameters of any two of the vehicle sensor data in each vehicle data set is less than a first difference threshold;

[0063] A difference between the data priority parameters of any two of the vehicle sensor data in each vehicle data set is less than a second difference threshold;

[0064] Based on a dynamic programming algorithm, the plurality of vehicle sensor data are iteratively calculated in groups according to the objective function and the constraint conditions until convergence, so as to obtain a plurality of vehicle data sets.

[0065] As an optional implementation, in the second aspect of the present invention, the specific manner in which the determination module determines the processing server corresponding to each of the vehicle data sets from a plurality of candidate servers includes:

[0066] For each of the vehicle data sets, calculating a location distance parameter between a server location corresponding to each candidate server and a system location parameter corresponding to the vehicle data set;

[0067] Calculating data matching parameters between defect detection model parameters corresponding to each of the candidate servers and data type parameters corresponding to the vehicle data set;

[0068] Calculating a weighted sum of the location distance parameter and the data matching parameter corresponding to each of the candidate servers to obtain a server priority parameter corresponding to each of the candidate servers;

[0069] The candidate server with the highest server priority parameter is determined as the processing server corresponding to the vehicle data set.

[0070] As an optional implementation, in the second aspect of the present invention, the specific manner in which the determination module calculates the location distance parameter between the server location corresponding to each candidate server and the system location parameter corresponding to the vehicle data set includes:

[0071] Determine the system position corresponding to the vehicle detection system corresponding to all the vehicle sensor data in the vehicle data set, and obtain multiple target system positions;

[0072] For each candidate server, calculating the location distance between the server location of the candidate server and each of the target system locations;

[0073] Calculate the weighted sum average of all the location distances to obtain the location distance parameter corresponding to the candidate server; wherein the weighted calculation weight corresponding to each location distance includes a first weight and a second weight; the first weight is proportional to the data transmission performance of the corresponding candidate server; the second weight is proportional to the data transmission performance of the corresponding vehicle detection system.

[0074] As an optional implementation, in the second aspect of the present invention, the specific manner in which the determination module calculates the data matching parameters between the defect detection model parameters corresponding to each of the candidate servers and the data type parameters corresponding to the vehicle data set includes:

[0075] Determine the data types corresponding to all the vehicle sensor data in the vehicle data set to obtain a target data type set;

[0076] For each of the candidate servers, obtaining training data records and historical prediction records of a prediction model used for vehicle defect detection in the candidate server;

[0077] Calculate the similarity between all data types in the training data record and the target data type set to obtain a data similarity parameter;

[0078] Calculate the average prediction accuracy of each data type in the target data type set in the historical prediction records to obtain a data prediction accuracy parameter;

[0079] The weighted average value of the data similarity parameter and the data prediction accuracy parameter is calculated to obtain the data matching parameter corresponding to the candidate server.

[0080] The third aspect of the present invention discloses another defect data processing system based on multi-server division of labor, the system comprising:

[0081] A memory storing executable program code;

[0082] a processor coupled to the memory;

[0083] The processor calls the executable program code stored in the memory to execute part or all of the steps in the defect data processing method based on multi-server division of labor disclosed in the first aspect of the present invention.

[0084] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute part or all of the steps in the defect data processing method based on multi-server division of labor disclosed in the first aspect of the present invention.

[0085] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0086] The present invention can group multiple vehicle sensor data submitted by multiple vehicle detection systems according to system information and preset data efficiency grouping rules to obtain multiple vehicle data sets, and then determine the processing server corresponding to each vehicle data set and send it for processing and return the detection results to the vehicle detection system, so as to more reasonably and comprehensively schedule multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0088] Figure 1 It is a flow chart of a defect data processing method based on multi-server division of labor disclosed in an embodiment of the present invention.

[0089] Figure 2 It is a structural schematic diagram of a defect data processing system based on multi-server division of labor disclosed in an embodiment of the present invention.

[0090] Figure 3 It is a structural schematic diagram of another defect data processing system based on multi-server division of labor disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0091] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0092] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0093] 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 invention. The appearance of the phrase in various places 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.

[0094] The present invention discloses a defect data processing method and system based on multi-server division of labor, which can group multiple vehicle sensor data submitted by multiple vehicle detection systems according to system information and preset data efficiency grouping rules to obtain multiple vehicle data sets, and then determine the processing server corresponding to each vehicle data set and send it for processing and return the detection results to the vehicle detection system, so that multiple servers can be more reasonably and comprehensively dispatched to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety. The following are detailed descriptions.

[0095] Embodiment 1

[0096] See also Figure 1 , Figure 1 This is a flow chart of a defect data processing method based on multi-server division of labor disclosed in an embodiment of the present invention. Figure 1 The defect data processing method based on multi-server division of labor described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the defect data processing method based on multi-server division of labor may include the following operations:

[0097] 101. Acquire multiple vehicle sensor data submitted by multiple vehicle detection systems and system information corresponding to each vehicle detection system.

[0098] 102. Group multiple vehicle sensor data according to system information and preset data efficiency grouping rules to obtain multiple vehicle data sets.

[0099] 103. Determine a processing server corresponding to each vehicle data set from multiple candidate servers.

[0100] 104. Send each vehicle data set to a corresponding processing server for vehicle defect detection, and instruct the processing server to return the detection result to the corresponding vehicle detection system.

[0101] It can be seen that the above-mentioned embodiment of the invention can group multiple vehicle sensor data submitted by multiple vehicle detection systems according to system information and preset data efficiency grouping rules to obtain multiple vehicle data sets, and then determine the processing server corresponding to each vehicle data set and send it for processing and return the detection results to the vehicle detection system, so as to more reasonably and comprehensively schedule multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety.

[0102] As an optional embodiment, in the above steps, the system information includes system parameters and system history records; the system parameters include system location, system type and system equipment performance information; the system history records include system history data volume records and system history data integrity records.

[0103] It can be seen that through the above-mentioned optional embodiments, the system information content of the vehicle detection system is limited, which can fully characterize the overall operating characteristics and operating conditions of the vehicle detection system, and is subsequently used to accurately group vehicle sensor data, assist in more reasonable and comprehensive scheduling of multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety.

[0104] As an optional embodiment, in the above steps, according to the system information and the preset data efficiency grouping rule, the plurality of vehicle sensor data are grouped to obtain a plurality of vehicle data sets, including:

[0105] For each vehicle sensor data, calculating a system priority parameter corresponding to the vehicle sensor data according to a system history record of the vehicle detection system corresponding to the vehicle sensor data;

[0106] Determine the data priority parameter corresponding to the vehicle sensor data according to the data type of the vehicle sensor data and the correspondence between the preset data type and priority; optionally, the data type is image data, sound data, infrared ranging data, infrared imaging data, temperature and humidity data or light reflection three-dimensional model data;

[0107] The system similarity parameter between any two vehicle sensor data is defined as the similarity between the system parameters of the vehicle detection systems corresponding to the two vehicle sensor data;

[0108] According to the system priority parameter, the data priority parameter and the system similarity parameter, the multiple vehicle sensor data are grouped and iteratively calculated based on the dynamic programming algorithm to obtain multiple vehicle data sets.

[0109] It can be seen that through the above-mentioned optional embodiments, the system priority parameters, data priority parameters and system similarities corresponding to the vehicle sensor data can be calculated respectively, and accurate data grouping can be achieved based on the dynamic programming algorithm to facilitate subsequent server determination and parallel computing, and assist in more reasonable and comprehensive scheduling of multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety.

[0110] As an optional embodiment, in the above step, calculating the system priority parameter corresponding to the vehicle sensor data according to the system history record of the vehicle detection system corresponding to the vehicle sensor data includes:

[0111] Count the weighted sum average of the data volumes of all data records in the system historical data volume record of the vehicle detection system corresponding to the vehicle sensor data to obtain the system data volume parameter corresponding to the vehicle sensor data; optionally, the weighted calculation weight corresponding to the data volume of each data record is proportional to the vehicle defect value corresponding to the corresponding data record; the vehicle defect value is used to characterize the degree of vehicle defect in the vehicle defect detection result corresponding to the vehicle sensor data corresponding to the data record;

[0112] The weighted average value of the data integrity of all data records in the system historical data integrity of the vehicle detection system corresponding to the vehicle sensor data is calculated to obtain the system data integrity parameter corresponding to the vehicle sensor data; optionally, the weighted calculation weight corresponding to the data integrity of each data record is proportional to the defect prediction probability corresponding to the corresponding data record; the defect prediction probability is the confidence probability corresponding to the prediction result obtained when the vehicle sensor data corresponding to the data record is predicted by the corresponding vehicle defect prediction model;

[0113] The weighted average value of the system data volume parameter and the system data integrity parameter is calculated to obtain the system priority parameter corresponding to the vehicle sensor data.

[0114] It can be seen that through the above-mentioned optional embodiments, it is possible to analyze and consider the average data volume and data integrity in the historical records of the detection system corresponding to the vehicle sensor data to obtain accurate system priority parameters for the vehicle sensor data, so as to facilitate the subsequent accurate data grouping and server determination and parallel computing, and assist in more reasonable and comprehensive scheduling of multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety.

[0115] As an optional embodiment, in the above steps, according to the system priority parameter, the data priority parameter and the system similarity parameter, a plurality of vehicle sensor data are grouped and iteratively calculated based on a dynamic programming algorithm to obtain a plurality of vehicle data sets, including:

[0116] The objective function is set to maximize the number of vehicle sensor data in each vehicle data set and minimize the total number of all vehicle data sets;

[0117] Setting restrictions includes:

[0118] A system similarity parameter between any two vehicle sensor data in each vehicle data set is greater than a first parameter threshold;

[0119] A system similarity parameter between any vehicle sensor data respectively belonging to two different vehicle data sets is less than a second parameter threshold;

[0120] A difference between system priority parameters of any two vehicle sensor data in each vehicle data set is less than a first difference threshold;

[0121] A difference between data priority parameters of any two vehicle sensor data in each vehicle data set is less than a second difference threshold;

[0122] Based on the dynamic programming algorithm, multiple vehicle sensor data are grouped and iteratively calculated according to the objective function and constraints until convergence, thereby obtaining multiple vehicle data sets.

[0123] It can be seen that through the above-mentioned optional embodiments, it is possible to set the objective functions and constraints corresponding to the system priority parameters, data priority parameters and system similarities corresponding to the vehicle sensor data, and realize accurate data grouping based on the dynamic programming algorithm, so as to facilitate subsequent server determination and parallel computing, and assist in realizing more reasonable and comprehensive scheduling of multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety.

[0124] As an optional embodiment, in the above step, determining a processing server corresponding to each vehicle data set from a plurality of candidate servers includes:

[0125] For each vehicle data set, calculating a location distance parameter between a server location corresponding to each candidate server and a system location parameter corresponding to the vehicle data set;

[0126] Calculating data matching parameters between defect detection model parameters corresponding to each candidate server and data type parameters corresponding to the vehicle data set;

[0127] Calculate the weighted sum of the location distance parameter and the data matching parameter corresponding to each candidate server to obtain the server priority parameter corresponding to each candidate server;

[0128] The candidate server with the highest server priority parameter is determined as the processing server corresponding to the vehicle data set.

[0129] It can be seen that through the above-mentioned optional embodiments, it is possible to calculate the system position proximity and data matching degree between the candidate server and the vehicle data set to screen out more suitable servers for data calculation, thereby assisting in more reasonable and comprehensive scheduling of multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety.

[0130] As an optional embodiment, in the above step, calculating the location distance parameter between the server location corresponding to each candidate server and the system location parameter corresponding to the vehicle data set includes:

[0131] Determine the system position corresponding to the vehicle detection system corresponding to all vehicle sensor data in the vehicle data set, and obtain multiple target system positions;

[0132] For each candidate server, calculating a location distance between a server location of the candidate server and a location of each target system;

[0133] Calculate the weighted sum average of all location distances to obtain the location distance parameter corresponding to the candidate server; optionally, the weighted calculation weight corresponding to each location distance includes a first weight and a second weight; the first weight is proportional to the data transmission performance of the corresponding candidate server; the second weight is proportional to the data transmission performance of the corresponding vehicle detection system.

[0134] It can be seen that through the above-mentioned optional embodiments, it is possible to accurately determine the location distance parameters corresponding to the candidate servers by performing weighted calculation on the distance between the candidate servers and the vehicle detection system locations corresponding to all vehicle sensor data in the vehicle data set, and considering the data transmission performance of the server and the vehicle detection system as the adjustment weight, so as to facilitate the subsequent screening of more suitable servers for data calculation and improve the transmission efficiency of returning the results to the vehicle detection system after the server calculation is completed, and assist in realizing more reasonable and comprehensive scheduling of multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety.

[0135] As an optional embodiment, in the above step, calculating the data matching parameters between the defect detection model parameters corresponding to each candidate server and the data type parameters corresponding to the vehicle data set includes:

[0136] Determine the data types corresponding to all vehicle sensor data in the vehicle data set to obtain a target data type set;

[0137] For each candidate server, obtaining training data records and historical prediction records of a prediction model used for vehicle defect detection in the candidate server;

[0138] Calculate the similarity between all data types in the training data records and the target data type set to obtain a data similarity parameter;

[0139] Calculate the average prediction accuracy of each data type in the target data type set in the historical prediction records to obtain the data prediction accuracy parameter;

[0140] The weighted average of the data similarity parameter and the data prediction accuracy parameter is calculated to obtain the data matching parameter corresponding to the candidate server.

[0141] It can be seen that through the above-mentioned optional embodiments, the data matching parameters corresponding to the candidate server can be accurately determined by performing weighted calculation on the similarity and historical prediction accuracy between the historical records of the candidate server's prediction model and the data types corresponding to all vehicle sensor data in the vehicle data set, so as to facilitate the subsequent screening of more suitable servers for data calculation, and assist in achieving more reasonable and comprehensive scheduling of multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety.

[0142] Embodiment 2

[0143] See also Figure 2 , Figure 2 Schematic diagram of a defect data processing system based on multi-server division of labor disclosed in an embodiment of the present invention. Figure 2 The defect data processing system based on multi-server division of labor described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the defect data processing system based on multi-server division of labor may include:

[0144] The acquisition module 201 is used to acquire a plurality of vehicle sensing data submitted by a plurality of vehicle detection systems and system information corresponding to each vehicle detection system.

[0145] The grouping module 202 is used to group the multiple vehicle sensor data to obtain multiple vehicle data sets according to the system information and the preset data efficiency grouping rules.

[0146] The determination module 203 is used to determine the processing server corresponding to each vehicle data set from multiple candidate servers.

[0147] The sending module 204 is used to send each vehicle data set to a corresponding processing server for vehicle defect detection, and instruct the processing server to return the detection result to the corresponding vehicle detection system.

[0148] It can be seen that the above-mentioned embodiment of the invention can group multiple vehicle sensor data submitted by multiple vehicle detection systems according to system information and preset data efficiency grouping rules to obtain multiple vehicle data sets, and then determine the processing server corresponding to each vehicle data set and send it for processing and return the detection results to the vehicle detection system, so as to more reasonably and comprehensively schedule multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety.

[0149] As an optional embodiment, the system information includes system parameters and system history records; the system parameters include system location, system type and system equipment performance information; the system history records include system history data volume records and system history data integrity records.

[0150] It can be seen that through the above-mentioned optional embodiments, the system information content of the vehicle detection system is limited, which can fully characterize the overall operating characteristics and operating conditions of the vehicle detection system, and is subsequently used to accurately group vehicle sensor data, assist in more reasonable and comprehensive scheduling of multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety.

[0151] As an optional embodiment, the specific manner in which the grouping module groups the multiple vehicle sensor data to obtain the multiple vehicle data sets according to the system information and the preset data efficiency grouping rule includes:

[0152] For each vehicle sensor data, calculating a system priority parameter corresponding to the vehicle sensor data according to a system history record of the vehicle detection system corresponding to the vehicle sensor data;

[0153] Determine the data priority parameter corresponding to the vehicle sensor data according to the data type of the vehicle sensor data and the correspondence between the preset data type and priority; optionally, the data type is image data, sound data, infrared ranging data, infrared imaging data, temperature and humidity data or light reflection three-dimensional model data;

[0154] The system similarity parameter between any two vehicle sensor data is defined as the similarity between the system parameters of the vehicle detection systems corresponding to the two vehicle sensor data;

[0155] According to the system priority parameter, the data priority parameter and the system similarity parameter, the multiple vehicle sensor data are grouped and iteratively calculated based on the dynamic programming algorithm to obtain multiple vehicle data sets.

[0156] It can be seen that through the above-mentioned optional embodiments, the system priority parameters, data priority parameters and system similarities corresponding to the vehicle sensor data can be calculated respectively, and accurate data grouping can be achieved based on the dynamic programming algorithm to facilitate subsequent server determination and parallel computing, and assist in more reasonable and comprehensive scheduling of multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety.

[0157] As an optional embodiment, the specific manner in which the grouping module calculates the system priority parameter corresponding to the vehicle sensor data according to the system history record of the vehicle detection system corresponding to the vehicle sensor data includes:

[0158] Count the weighted sum average of the data volumes of all data records in the system historical data volume record of the vehicle detection system corresponding to the vehicle sensor data to obtain the system data volume parameter corresponding to the vehicle sensor data; optionally, the weighted calculation weight corresponding to the data volume of each data record is proportional to the vehicle defect value corresponding to the corresponding data record; the vehicle defect value is used to characterize the degree of vehicle defect in the vehicle defect detection result corresponding to the vehicle sensor data corresponding to the data record;

[0159] The weighted average value of the data integrity of all data records in the system historical data integrity of the vehicle detection system corresponding to the vehicle sensor data is calculated to obtain the system data integrity parameter corresponding to the vehicle sensor data; optionally, the weighted calculation weight corresponding to the data integrity of each data record is proportional to the defect prediction probability corresponding to the corresponding data record; the defect prediction probability is the confidence probability corresponding to the prediction result obtained when the vehicle sensor data corresponding to the data record is predicted by the corresponding vehicle defect prediction model;

[0160] The weighted average value of the system data volume parameter and the system data integrity parameter is calculated to obtain the system priority parameter corresponding to the vehicle sensor data.

[0161] It can be seen that through the above-mentioned optional embodiments, it is possible to analyze and consider the average data volume and data integrity in the historical records of the detection system corresponding to the vehicle sensor data to obtain accurate system priority parameters for the vehicle sensor data, so as to facilitate the subsequent accurate data grouping and server determination and parallel computing, and assist in more reasonable and comprehensive scheduling of multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety.

[0162] As an optional embodiment, the grouping module performs grouping and iterative calculation on multiple vehicle sensor data based on a dynamic programming algorithm according to the system priority parameter, the data priority parameter and the system similarity parameter to obtain a specific method of multiple vehicle data sets, including:

[0163] The objective function is set to maximize the number of vehicle sensor data in each vehicle data set and minimize the total number of all vehicle data sets;

[0164] Setting restrictions includes:

[0165] A system similarity parameter between any two vehicle sensor data in each vehicle data set is greater than a first parameter threshold;

[0166] A system similarity parameter between any vehicle sensor data respectively belonging to two different vehicle data sets is less than a second parameter threshold;

[0167] A difference between system priority parameters of any two vehicle sensor data in each vehicle data set is less than a first difference threshold;

[0168] A difference between data priority parameters of any two vehicle sensor data in each vehicle data set is less than a second difference threshold;

[0169] Based on the dynamic programming algorithm, multiple vehicle sensor data are grouped and iteratively calculated according to the objective function and constraints until convergence, thereby obtaining multiple vehicle data sets.

[0170] It can be seen that through the above-mentioned optional embodiments, it is possible to set the objective functions and constraints corresponding to the system priority parameters, data priority parameters and system similarities corresponding to the vehicle sensor data, and realize accurate data grouping based on the dynamic programming algorithm, so as to facilitate subsequent server determination and parallel computing, and assist in realizing more reasonable and comprehensive scheduling of multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety.

[0171] As an optional embodiment, the specific manner in which the determination module determines the processing server corresponding to each vehicle data set from a plurality of candidate servers includes:

[0172] For each vehicle data set, calculating a location distance parameter between a server location corresponding to each candidate server and a system location parameter corresponding to the vehicle data set;

[0173] Calculating data matching parameters between defect detection model parameters corresponding to each candidate server and data type parameters corresponding to the vehicle data set;

[0174] Calculate the weighted sum of the location distance parameter and the data matching parameter corresponding to each candidate server to obtain the server priority parameter corresponding to each candidate server;

[0175] The candidate server with the highest server priority parameter is determined as the processing server corresponding to the vehicle data set.

[0176] It can be seen that through the above-mentioned optional embodiments, it is possible to calculate the system position proximity and data matching degree between the candidate server and the vehicle data set to screen out more suitable servers for data calculation, thereby assisting in more reasonable and comprehensive scheduling of multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety.

[0177] As an optional embodiment, the specific manner in which the determination module calculates the location distance parameter between the server location corresponding to each candidate server and the system location parameter corresponding to the vehicle data set includes:

[0178] Determine the system position corresponding to the vehicle detection system corresponding to all vehicle sensor data in the vehicle data set, and obtain multiple target system positions;

[0179] For each candidate server, calculating a location distance between a server location of the candidate server and a location of each target system;

[0180] Calculate the weighted sum average of all location distances to obtain the location distance parameter corresponding to the candidate server; optionally, the weighted calculation weight corresponding to each location distance includes a first weight and a second weight; the first weight is proportional to the data transmission performance of the corresponding candidate server; the second weight is proportional to the data transmission performance of the corresponding vehicle detection system.

[0181] It can be seen that through the above-mentioned optional embodiments, it is possible to accurately determine the location distance parameters corresponding to the candidate servers by performing weighted calculation on the distance between the candidate servers and the vehicle detection system locations corresponding to all vehicle sensor data in the vehicle data set, and considering the data transmission performance of the server and the vehicle detection system as the adjustment weight, so as to facilitate the subsequent screening of more suitable servers for data calculation and improve the transmission efficiency of returning the results to the vehicle detection system after the server calculation is completed, and assist in realizing more reasonable and comprehensive scheduling of multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety.

[0182] As an optional embodiment, the specific manner in which the determination module calculates the data matching parameters between the defect detection model parameters corresponding to each candidate server and the data type parameters corresponding to the vehicle data set includes:

[0183] Determine the data types corresponding to all vehicle sensor data in the vehicle data set to obtain a target data type set;

[0184] For each candidate server, obtaining training data records and historical prediction records of a prediction model used for vehicle defect detection in the candidate server;

[0185] Calculate the similarity between all data types in the training data records and the target data type set to obtain a data similarity parameter;

[0186] Calculate the average prediction accuracy of each data type in the target data type set in the historical prediction records to obtain the data prediction accuracy parameter;

[0187] The weighted average of the data similarity parameter and the data prediction accuracy parameter is calculated to obtain the data matching parameter corresponding to the candidate server.

[0188] It can be seen that through the above-mentioned optional embodiments, the data matching parameters corresponding to the candidate server can be accurately determined by performing weighted calculation on the similarity and historical prediction accuracy between the historical records of the candidate server's prediction model and the data types corresponding to all vehicle sensor data in the vehicle data set, so as to facilitate the subsequent screening of more suitable servers for data calculation, and assist in achieving more reasonable and comprehensive scheduling of multiple servers to realize defect detection of vehicle sensor data in big data scenarios, improve vehicle detection efficiency and detection accuracy, and improve vehicle safety.

[0189] Embodiment 3

[0190] See also Figure 3 , Figure 3 This is another defect data processing system based on multi-server division of labor disclosed in an embodiment of the present invention. Figure 3 The defect data processing system based on multi-server division of labor is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the defect data processing system based on multi-server division of labor may include:

[0191] A memory 301 storing executable program codes;

[0192] a processor 302 coupled to the memory 301;

[0193] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the defect data processing method based on multi-server division of labor described in the first embodiment.

[0194] Embodiment 4

[0195] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the defect data processing method based on multi-server division of labor described in the first embodiment.

[0196] Embodiment 5

[0197] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the defect data processing method based on multi-server division of labor described in Example 1.

[0198] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0199] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0200] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0201] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0202] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0203] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0204] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0205] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0206] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0207] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0208] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0209] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0210] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0211] Finally, it should be noted that the defect data processing method and system based on multi-server division of labor disclosed in the embodiment of the present invention only discloses the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that it is still possible to modify the technical solutions recorded in the aforementioned embodiments, or to make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A defect data processing method based on multi-server division of labor, characterized in that: The method comprises: Acquire a plurality of vehicle sensor data submitted by a plurality of vehicle detection systems and system information corresponding to each of the vehicle detection systems; According to the system information and the preset data efficiency grouping rule, the plurality of vehicle sensor data are grouped to obtain a plurality of vehicle data sets, including: For each of the vehicle sensor data, according to the system history record of the vehicle detection system corresponding to the vehicle sensor data, the system priority parameter corresponding to the vehicle sensor data is calculated, including: Counting the weighted sum average of the data volumes of all data records in the system historical data volume record of the vehicle detection system corresponding to the vehicle sensor data, to obtain the system data volume parameter corresponding to the vehicle sensor data; wherein the weighted calculation weight corresponding to the data volume of each data record is proportional to the vehicle defect value corresponding to the corresponding data record; the vehicle defect value is used to characterize the degree of vehicle defect in the vehicle defect detection result corresponding to the vehicle sensor data corresponding to the data record; The weighted average value of the data integrity of all data records in the system historical data integrity of the vehicle detection system corresponding to the vehicle sensor data is calculated to obtain the system data integrity parameter corresponding to the vehicle sensor data; wherein the weighted calculation weight corresponding to the data integrity of each data record is proportional to the defect prediction probability corresponding to the corresponding data record; the defect prediction probability is the confidence probability corresponding to the prediction result obtained when the vehicle sensor data corresponding to the data record is predicted by the corresponding vehicle defect prediction model; Calculating a weighted average value of the system data volume parameter and the system data integrity parameter to obtain a system priority parameter corresponding to the vehicle sensor data; Determine a processing server corresponding to each of the vehicle data sets from a plurality of candidate servers; Each of the vehicle data sets is sent to the corresponding processing server for vehicle defect detection, and the processing server is instructed to return the detection result to the corresponding vehicle detection system.

2. The defect data processing method based on multi-server division of labor according to claim 1 is characterized in that: The system information includes system parameters and system history records; the system parameters include system location, system type and system equipment performance information; the system history records include system history data volume records and system history data integrity records.

3. The defect data processing method based on multi-server division of labor according to claim 2 is characterized in that: The step of grouping the plurality of vehicle sensor data according to the system information and a preset data efficiency grouping rule to obtain a plurality of vehicle data sets includes: Determine the data priority parameter corresponding to the vehicle sensor data according to the data type of the vehicle sensor data and the correspondence between the preset data type and priority; the data type is image data, sound data, infrared ranging data, infrared imaging data, temperature and humidity data or light reflection three-dimensional model data; defining a system similarity parameter between any two of the vehicle sensor data as the similarity between the system parameters of the vehicle detection systems corresponding to the two vehicle sensor data; According to the system priority parameter, the data priority parameter and the system similarity parameter, the plurality of vehicle sensor data are grouped and iteratively calculated based on a dynamic programming algorithm to obtain a plurality of vehicle data sets.

4. The defect data processing method based on multi-server division of labor according to claim 3 is characterized in that: The method further comprises performing grouping and iterative calculation on the plurality of vehicle sensor data based on the system priority parameter, the data priority parameter and the system similarity parameter based on a dynamic programming algorithm to obtain a plurality of vehicle data sets, including: Setting the objective function to maximize the number of vehicle sensor data in each vehicle data set and minimize the total number of all vehicle data sets; Setting restrictions includes: The system similarity parameter between any two vehicle sensor data in each vehicle data set is greater than a first parameter threshold; The system similarity parameter between any of the vehicle sensor data respectively belonging to two different vehicle data sets is less than a second parameter threshold; A difference between the system priority parameters of any two of the vehicle sensor data in each vehicle data set is less than a first difference threshold; A difference between the data priority parameters of any two of the vehicle sensor data in each vehicle data set is less than a second difference threshold; Based on a dynamic programming algorithm, the plurality of vehicle sensor data are iteratively calculated in groups according to the objective function and the constraint conditions until convergence, so as to obtain a plurality of vehicle data sets.

5. The defect data processing method based on multi-server division of labor according to claim 1 is characterized in that: The step of determining a processing server corresponding to each of the vehicle data sets from a plurality of candidate servers includes: For each of the vehicle data sets, calculating a location distance parameter between a server location corresponding to each candidate server and a system location parameter corresponding to the vehicle data set; Calculating data matching parameters between defect detection model parameters corresponding to each of the candidate servers and data type parameters corresponding to the vehicle data set; Calculating a weighted sum of the location distance parameter and the data matching parameter corresponding to each of the candidate servers to obtain a server priority parameter corresponding to each of the candidate servers; The candidate server with the highest server priority parameter is determined as the processing server corresponding to the vehicle data set.

6. The defect data processing method based on multi-server division of labor according to claim 5 is characterized in that: The calculating of the location distance parameter between the server location corresponding to each candidate server and the system location parameter corresponding to the vehicle data set includes: Determine the system position corresponding to the vehicle detection system corresponding to all the vehicle sensor data in the vehicle data set, and obtain multiple target system positions; For each candidate server, calculating the location distance between the server location of the candidate server and each of the target system locations; Calculate the weighted sum average of all the location distances to obtain the location distance parameter corresponding to the candidate server; wherein the weighted calculation weight corresponding to each location distance includes a first weight and a second weight; the first weight is proportional to the data transmission performance of the corresponding candidate server; the second weight is proportional to the data transmission performance of the corresponding vehicle detection system.

7. The defect data processing method based on multi-server division of labor according to claim 5 is characterized in that: The calculating of data matching parameters between the defect detection model parameters corresponding to each of the candidate servers and the data type parameters corresponding to the vehicle data set includes: Determine the data types corresponding to all the vehicle sensor data in the vehicle data set to obtain a target data type set; For each of the candidate servers, obtaining training data records and historical prediction records of a prediction model used for vehicle defect detection in the candidate server; Calculate the similarity between all data types in the training data record and the target data type set to obtain a data similarity parameter; Calculate the average prediction accuracy of each data type in the target data type set in the historical prediction records to obtain a data prediction accuracy parameter; The weighted average value of the data similarity parameter and the data prediction accuracy parameter is calculated to obtain the data matching parameter corresponding to the candidate server.

8. A defect data processing system based on multi-server division of labor, characterized in that: The system comprises: An acquisition module, used for acquiring a plurality of vehicle sensor data submitted by a plurality of vehicle detection systems and system information corresponding to each of the vehicle detection systems; A grouping module, used to group the plurality of vehicle sensor data to obtain a plurality of vehicle data sets according to the system information and a preset data efficiency grouping rule, including: For each of the vehicle sensor data, according to the system history record of the vehicle detection system corresponding to the vehicle sensor data, the system priority parameter corresponding to the vehicle sensor data is calculated, including: Counting the weighted sum average of the data volumes of all data records in the system historical data volume record of the vehicle detection system corresponding to the vehicle sensor data, to obtain the system data volume parameter corresponding to the vehicle sensor data; wherein the weighted calculation weight corresponding to the data volume of each data record is proportional to the vehicle defect value corresponding to the corresponding data record; the vehicle defect value is used to characterize the degree of vehicle defect in the vehicle defect detection result corresponding to the vehicle sensor data corresponding to the data record; The weighted average value of the data integrity of all data records in the system historical data integrity of the vehicle detection system corresponding to the vehicle sensor data is calculated to obtain the system data integrity parameter corresponding to the vehicle sensor data; wherein the weighted calculation weight corresponding to the data integrity of each data record is proportional to the defect prediction probability corresponding to the corresponding data record; the defect prediction probability is the confidence probability corresponding to the prediction result obtained when the vehicle sensor data corresponding to the data record is predicted by the corresponding vehicle defect prediction model; Calculating a weighted average value of the system data volume parameter and the system data integrity parameter to obtain a system priority parameter corresponding to the vehicle sensor data; A determination module, used to determine a processing server corresponding to each of the vehicle data sets from a plurality of candidate servers; The sending module is used to send each of the vehicle data sets to the corresponding processing server for vehicle defect detection, and instruct the processing server to return the detection result to the corresponding vehicle detection system.

9. A defect data processing system based on multi-server division of labor, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the defect data processing method based on multi-server division of labor as described in any one of claims 1-7.

Images