Analysis method, device, equipment and medium for damage correlation of vehicle parts

Abstract

The present application discloses a method, device, equipment and medium for analyzing the correlation of damage of vehicle spare parts, and the method includes: obtaining damage source data of multiple vehicles in historical time; performing field extraction, data cleaning and normalization processing on each of the damage source data in turn to obtain multiple damage standard data; using a correlation analysis model to perform a damage correlation analysis of spare parts on the multiple damage standard data according to the vehicle dimension to obtain at least one damage correlation rule of spare parts. Based on the formed damage correlation rules of spare parts, this application allows automobile manufacturers to optimize the structural design of related vehicle models, improve the rationality of vehicle design and the overall safety of vehicles; the insurance industry can rely on the formed damage correlation rules of spare parts to compare the damage lists of spare parts repaired or replaced by auto repair institutions, and promptly discover and prevent the risk of claims leakage due to excessive vehicle repairs; and this application has a wide range of applicable scenarios, diverse, and highly practical.

Description

Technical Field

[0001] The present application relates to the field of vehicle damage assessment and vehicle manufacturing technology, and specifically to a method, device, equipment and medium for analyzing the correlation of damage to vehicle parts and components. Background Art

[0002] In 2022, the number of cars in my country has exceeded 300 million, and there are approximately 90 million reports of vehicle accidents each year. Due to differences in structural design, material technology, etc., different types of vehicles have different parts damaged when an accident occurs.

[0003] The insurance industry often faces the risk of vehicle insurance claims leakage due to the lack of effective technical means to analyze the damage relationship between different parts and components when an accident occurs. Automobile manufacturers can only optimize and improve vehicle design through a limited number of collision tests.

[0004] Therefore, the insurance and automotive industries are in urgent need of an effective method to help solve related problems. Summary of the invention

[0005] In view of the above problems, the embodiments of the present application provide a method, device, equipment and medium for analyzing the damage correlation of vehicle parts to overcome or at least partially overcome the shortcomings of the prior art.

[0006] In a first aspect, an embodiment of the present application provides a method for analyzing the damage correlation of vehicle parts, including:

[0007] Obtain damage assessment source data for multiple vehicles over a historical period;

[0008] Perform field extraction, data cleaning, and normalization processing on each damage assessment source data in turn to obtain multiple damage assessment standard data;

[0009] A correlation analysis model is adopted to perform a correlation analysis on the damage of spare parts on the plurality of damage assessment specification data according to the vehicle dimension, so as to obtain at least one damage correlation rule of spare parts.

[0010] In a second aspect, an embodiment of the present application further provides a device for analyzing the damage correlation of vehicle parts, the device comprising:

[0011] An acquisition unit, used to acquire damage assessment source data of multiple vehicles within a historical period;

[0012] A preprocessing unit, used to perform field extraction, data cleaning, and normalization processing on each of the damage assessment source data in turn to obtain multiple damage assessment standard data;

[0013] The analysis unit is used to use a correlation analysis model to perform a spare parts damage correlation analysis on the multiple damage assessment specification data according to the vehicle dimension to obtain at least one spare parts damage correlation rule.

[0014] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor; and a memory arranged to store computer executable instructions, wherein when the executable instructions are executed, the processor executes the above-mentioned vehicle spare parts damage correlation analysis method.

[0015] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes the above-mentioned vehicle spare parts damage correlation analysis method.

[0016] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0017] This application first classifies historical accident data according to vehicle models, and then extracts the list of damaged spare parts in each accident for each vehicle model, and then uses the association analysis algorithm in big data analysis to analyze the probability of damage to other spare parts (or several spare parts) when a certain type (or several types) of spare parts are damaged in an accident of a specific vehicle model, and forms association rules for spare parts damage. Based on the formed association rules for damage to spare parts, automobile manufacturers can optimize the structural design of related vehicle models, improve the rationality of vehicle design and the overall safety of vehicles; the insurance industry can rely on the formed association rules for damage to spare parts, compare the damage assessment lists of spare parts repaired or replaced by auto repair institutions, and promptly discover and prevent the risk of claims leakage caused by excessive vehicle repairs; and this application has a wide range of applicable scenarios, diverse, and highly practical. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 A schematic diagram showing a flow chart of a method for analyzing damage correlation of vehicle parts according to an embodiment of the present application;

[0020] Figure 2 A schematic diagram of the structure of a risk control engine according to an embodiment of the present application is shown;

[0021] Figure 3 A schematic diagram of a damage assessment tree structure according to an embodiment of the present application is shown;

[0022] Figure 4 A schematic diagram showing the structure of a device for analyzing the damage correlation of vehicle parts according to an embodiment of the present application is shown;

[0023] Figure 5 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0025] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0026] In 2022, the number of vehicles in my country has exceeded 300 million, and there are about 90 million reports of vehicle accidents each year. Due to differences in structural design, material technology, etc., different types of vehicles have different damaged parts when a vehicle accident occurs. Due to the lack of effective technical means to analyze the damage relationship between different parts when an accident occurs, the insurance industry often faces the risk of vehicle insurance claims leakage, and automobile manufacturers can only optimize and improve vehicle design through a limited number of collision tests. Therefore, the insurance industry and the automobile industry are in urgent need of an effective method to help solve the pain points of related industries.

[0027] In this regard, a method for analyzing the damage correlation of vehicle parts and components is proposed in this application. This method can be implemented through a big data analysis platform. Figure 1 A schematic diagram of the structure of a big data analysis platform according to an embodiment of the present application is shown. Figure 1 It can be seen that the big data analysis platform 100 is deployed with an analysis device 110 for the damage correlation of vehicle parts that can realize the business logic of this application, and the big data analysis platform 100 can communicate with the national auto insurance information platform 200. Among them, the national auto insurance information platform, as the only real-time production transaction platform in the insurance industry, gathers all vehicle underwriting and claims business data of all insurance companies across the country, and has a good foundation for data analysis and application.

[0028] It should be noted that the vehicle parts damage correlation analysis method of the present application can be implemented through the above-mentioned big data analysis platform 100, but is not limited to this. Any system or architecture that can implement the business logic of the present application can be used.

[0029] Figure 2 A schematic diagram showing a flow chart of a method for analyzing the damage correlation of vehicle parts according to an embodiment of the present application is shown. Figure 2 It can be seen that the method can be applied to the big data analysis platform 100, and the present application at least includes steps S210 to S230:

[0030] Step S210: Obtain damage assessment source data for multiple vehicles within a historical period.

[0031] Specifically, the full amount of vehicle damage assessment data occurring in the history of auto insurance from the national auto insurance information platform 200 can be uploaded to the big data analysis platform 100 and recorded as damage assessment source data.

[0032] Step S220: Perform field extraction, data cleaning, and normalization processing on each damage assessment source data in turn to obtain multiple damage assessment standard data.

[0033] Then, a large amount of damage assessment source data is preprocessed to obtain standardized damage assessment specification data that can be input into the correlation analysis model.

[0034] Preprocessing includes field extraction, data cleaning, normalization, etc., which are performed in sequence. Specifically, in some embodiments,

[0035] Field extraction includes: extracting each vehicle damage assessment source data according to the preset fields and the extraction rules of each field, and obtaining multiple damage assessment field data, wherein the preset fields include: claim code, VIN code of the insured vehicle, case closing time, insured area, location of the accident, total amount of loss assessment, total amount of compensation, loss amount, accident classification, cause of the accident, name of replacement / repair parts, replacement or repair mark, number of replacement / repair parts, replacement / repair parts, OEM code, vehicle OE code, and parts price.

[0036] The specific extraction fields and the extraction rules (extraction instructions) of each field are shown in Table 1. The data obtained after field extraction is recorded as damage assessment field data and then enters the data cleaning processing stage.

[0037] Table 1:

[0038]

[0039]

[0040] As for data cleaning, in some embodiments of the present application, the damage assessment field data obtained after field extraction is subjected to at least one of missing data processing, duplicate data processing, abnormal data processing, redundant data processing, and noise data processing to filter out bad data and obtain damage assessment filtered data; wherein, the missing data processing includes: if the name of the replacement / repair part of a damage assessment field data is missing, then the damage assessment field data is deleted; the duplicate data processing includes: if there are multiple damage assessment field data with the same claim code, then the VIN codes of the insured vehicles under the multiple claim codes are compared, and for the insured vehicles with the same VIN codes, the damage assessment field data with the latest case closing time is retained; the redundant data processing includes: The processing includes: if there are multiple damage assessment field data with the same claim code and the VIN code of the vehicle involved in the accident, then compare the other fields under the multiple claim codes. For those with the same other fields, retain the damage assessment field data with the latest case closing time; the abnormal data processing includes: removing spaces and special symbols from the names of replacement / repair parts, and only retaining Chinese characters; removing spaces, special symbols, and Chinese characters from the vehicle OE code, and only retaining numbers and letters, and all letters are capitalized; removing special symbols and Chinese characters from the VIN code of the vehicle involved in the accident, and only retaining numbers and letters, and all letters are capitalized; the noise data processing includes: removing damage assessment field data of accident losses caused by accidental factors.

[0041] Cleaning of the extracted data mainly includes missing data processing, duplicate data processing, abnormal data processing, redundant data processing, noise data processing, etc. Some data processing methods are listed below:

[0042] Missing data processing: For example, if the accessory name data is missing, directly delete the entire data corresponding to the accessory.

[0043] Duplicate data processing: Use the claim code as the primary key to extract all VIN data under the claim code. If there is duplicate data, keep the record of the latest damage assessment date.

[0044] Redundant data processing: Use VIN code and claim code as the primary key, remove other redundant data, and keep the record of the latest damage assessment date.

[0045] Abnormal data processing: remove spaces and special symbols from spare parts names, and only keep Chinese characters; remove spaces, special symbols and Chinese characters from OE codes, and only keep numbers and letters, and all letters are changed to uppercase letters; remove special symbols and Chinese characters from VIN codes, and only keep numbers and letters, and all letters are changed to uppercase letters.

[0046] Noise data processing: remove accident loss data caused by incidental factors such as theft, robbery, and water wading.

[0047] Data cleaning is not limited to the above-mentioned cases, and can be set according to the extracted damage assessment field data.

[0048] Then, the damage assessment filter data obtained after data cleaning is subjected to standardized processing. This is because there are many different names for the same component in the industry. Standardized processing is to identify the same component with the same name to facilitate subsequent correlation analysis. Specifically, in some embodiments of the present application, the standardized processing includes: using a pre-established standardized name to convert the replacement / repair parts name of the damage assessment filter data obtained after data cleaning into a standardized name to obtain the damage assessment standard data.

[0049] The inventor of this application has defined 62 parts that are often damaged in vehicle accidents based on business experience, and formulated standardized names. The standardized names are used to normalize the damage assessment filtering data. The standardized names of commonly used parts are shown in Table 2 below:

[0050] Table 2:

[0051]

[0052]

[0053] After field extraction, data cleaning and normalization, the data obtained is relatively standardized and recorded as damage assessment standard data.

[0054] Step S230: using a correlation analysis model to perform a component damage correlation analysis on the plurality of damage assessment specification data according to the vehicle dimension, and obtaining at least one component damage correlation rule.

[0055] The above normalized data can be used as the input of the correlation analysis model and enter this step, that is, the data model analysis stage.

[0056] The data model analysis mainly includes three parts: data file segmentation, data conversion, and operation analysis using the FPGrowth algorithm. Specifically, in some embodiments of the present application, the correlation analysis model is used to perform a correlation analysis of the damage of spare parts on the multiple damage assessment specification data according to the vehicle model dimension to obtain at least one accessory damage association rule, including: arranging and segmenting the multiple damage assessment specification data into at least one data file according to the vehicle model dimension, wherein the data file contains multiple damage assessment analysis data; converting the format of the multiple damage assessment analysis data in each of the data files to obtain at least one data format file; and performing a correlation analysis on the multiple damage assessment analysis data in each of the data format files based on the FpGrowth algorithm to obtain at least one spare parts damage association rule.

[0057] First, data file segmentation

[0058] The normalized data is divided into different Excel files according to vehicle models. Each file contains 10 fields, including damage assessment number, vehicle attributes, VIN code, model name, repair shop type, accessory name, accessory OE number, accessory price type, accessory price, and damage assessment method. Table 3 is an example of a data file. Table 3 only gives two damage assessment analysis data. In fact, a data file contains many damage assessment analysis data, and the model names of multiple damage assessment analysis data in a data file are the same.

[0059] Table 3:

[0060]

[0061] Second, data conversion

[0062] The aforementioned 62 standard spare parts are used as field names for data conversion to form a data format file required by the FPGrowth algorithm, as shown in Table 4. Table 4 shows a portion of a data format file. After data conversion, the data in the obtained data format file is in the form shown in Table 4:

[0063] Table 4:

[0064]

[0065] Third, use the FPGrowth algorithm to conduct operation analysis

[0066] Association analysis algorithms in machine learning include Apriori, EM, FpGrowth, etc. Among them, the FpGrowth algorithm compresses data records by constructing a tree structure, so that mining frequent item sets only requires scanning data records twice, and the algorithm does not need to generate candidate sets, so it is more efficient. This application combines the FpGrowth algorithm with the actual scenario of this application to realize the association analysis between different parts.

[0067] Specifically, in some embodiments of the present application, based on the FpGrowth algorithm, a correlation analysis is performed on multiple damage analysis data in each of the data format files to obtain at least one spare part damage association rule, including: constructing a damage assessment tree structure of a vehicle model dimension according to the data format file; scanning the damage assessment tree structure to mine frequent item sets to obtain at least one spare part damage association rule under the vehicle model dimension, and the damage association rule includes: a preconditioner set, a postconditioner set, support, confidence, and lift.

[0068] For example, in 6 accidents involving different vehicles of the same vehicle model, the damaged parts in each accident are shown in Table 5. From Table 5, we can see that in 6 accidents, the headlight (right) appeared 5 times, the front bumper skin appeared 3 times, the front fog light (right) appeared 4 times, the front windshield appeared 3 times, the engine hood hinge (right) appeared 3 times, and the condenser appeared 3 times. Based on the above data, the damage tree structure is constructed, such as Figure 3 shown.

[0069] Table 5

[0070]

[0071] Then, the damage assessment tree structure is scanned to mine frequent item sets, and a damage association rule of at least one spare part under the vehicle model dimension is obtained. A damage association rule includes: a preconditioner item set, a postconditioner item set, support, confidence, and lift.

[0072] Among them, support is used to find frequent item sets, which indicates the proportion of the frequent item sets in the entire data samples, that is, the probability of a / a group of accessories appearing in all accidents.

[0073] Confidence: It is used to determine association rules and indicates the probability of another data appearing after one data appears, that is, the probability of one or a group of accessories being damaged at the same time in the current data set.

[0074] Lift: It is used to determine the probability of two data appearing at the same time, but at the same time, the probability of the two data appearing separately must be considered, indicating the correlation between the two data, that is, the correlation of a / a group of accessories being damaged in an accident.

[0075] Table 6 shows two obtained damage association rules, as shown in Table 6:

[0076]

[0077] From Table 6 above, we can get the following results:

[0078] For Rule 1: {"front windshield"}->{"condenser"}, in the set of spare parts for this accident, when the "front windshield" is damaged, the probability of the "condenser" being damaged is 94.48%. The credibility of this analysis result is 100%. When the "front windshield" is damaged, it can be predicted that the impact of the "front windshield" on the "condenser" is about 1.058. This result is greater than 1, which is a valid association rule.

[0079] For rule 2, that is, the association rule {"condenser", "radiator frame"}->{"rear bumper skin"}, when the "condenser" and "radiator frame" are damaged, the probability of the "rear bumper skin" being damaged is 94.48%, and the credibility of the analysis result is also 100%, but the lifting degree of this rule is 1. Therefore, there is no correlation between the damage of the "condenser" and "radiator frame" and the damage of the "rear bumper skin".

[0080] Based on the above method, using real accident data to form big data analysis results, multiple spare parts damage association rules can be obtained according to vehicle models, which has many practical uses.

[0081] For example, multiple spare parts damage association rules are aggregated into a vehicle spare parts association index database; when assessing the damage of a target vehicle, if the damage assessment result hits a damage association rule in the vehicle spare parts association index database, it is determined whether there are spare parts that are not associated in the damage assessment result. If so, a leakage warning is triggered.

[0082] Specifically, a "vehicle spare parts association index database" can be formed for the insurance industry according to vehicle models and deployed in an intelligent damage assessment system or a damage assessment system open to insurance companies. Each business case will be called in real time during the damage assessment process. If the business scenario of a certain vehicle model is the same as the analysis result, and non-related accessories appear in the auto repair shop's repair parts list, the corresponding association rules (anti-penetration rules) will be triggered to warn the insurance company that the business may involve over-repairs or even fraud risks, directly providing basic data support for the industry's auto insurance claims risk control.

[0083] In addition, automobile manufacturers can also refer to relevant analysis results to further optimize vehicle structure design.

[0084] Depend on Figure 2 It can be seen from the method shown that the present application first classifies historical accident data according to vehicle models, and then extracts the list of damaged spare parts in each accident for each vehicle model, and then uses the association analysis algorithm in big data analysis to analyze the probability of damage to other spare parts (or several spare parts) when a certain type (or several types) of spare parts are damaged in an accident of a specific vehicle model, thereby forming association rules for spare parts damage. Based on the formed association rules for damage to spare parts, automobile manufacturers can optimize the structural design of related vehicle models, improve the rationality of vehicle design and the overall safety of vehicles; the insurance industry can rely on the formed association rules for damage to spare parts, compare the damage assessment lists of spare parts repaired or replaced by auto repair institutions, and promptly discover and prevent the risk of claims leakage caused by excessive vehicle repairs; and the present application has a wide range of applicable scenarios, is diverse, and has strong practicality.

[0085] Figure 4 A schematic diagram of the structure of a device for analyzing the damage correlation of vehicle parts according to an embodiment of the present application is shown. Figure 4 It can be seen that the vehicle parts damage correlation analysis device 110 includes:

[0086] An acquisition unit 111 is used to acquire damage assessment source data of multiple vehicles in a historical period;

[0087] The preprocessing unit 112 is used to perform field extraction, data cleaning, and normalization processing on each of the damage assessment source data in turn to obtain multiple damage assessment standard data;

[0088] The analysis unit 113 is used to use a correlation analysis model to perform a spare parts damage correlation analysis on the multiple damage assessment specification data according to the vehicle dimension to obtain at least one spare parts damage correlation rule.

[0089] In some embodiments of the present application, in the above-mentioned device, the preprocessing unit 112 is used to extract each piece of the vehicle damage assessment source data according to the preset fields and the extraction rules of each field, and obtain multiple damage assessment field data, wherein the preset fields include: claim code, VIN code of the insured vehicle, case closing time, insured area, location of the accident, total amount of loss assessment, total amount of compensation, loss amount, accident classification, cause of the accident, name of replacement / repair parts, replacement or repair mark, number of replacement / repair parts, replacement / repair parts, OEM code, and vehicle OE code, and parts price.

[0090] In some embodiments of the present application, in the above-mentioned device, the pre-processing unit 112 is used to perform at least one of missing data processing, duplicate data processing, abnormal data processing, redundant data processing, and noise data processing on the damage assessment field data obtained after field extraction, so as to filter bad data and obtain damage assessment filtered data; wherein, the missing data processing includes: if the name of the replacement / repair part of a damage assessment field data is missing, then the damage assessment field data is deleted; the duplicate data processing includes: if there are multiple damage assessment field data with the same claim code, then the VIN codes of the vehicles in danger under the multiple claim codes are compared, and for the vehicles in danger with the same VIN codes, the damage assessment field data with the latest case closing time is retained; The redundant data processing includes: if there are multiple damage assessment field data with the same claim code and the VIN code of the vehicle involved in the accident, then compare the other fields under the multiple claim codes, and for those with the same other fields, retain the damage assessment field data with the latest case closing time; the abnormal data processing includes: removing spaces and special symbols from the names of replacement / repair parts, and only retaining Chinese characters; removing spaces, special symbols, and Chinese characters from the vehicle OE code, and only retaining numbers and letters, and all letters are capitalized; removing special symbols and Chinese characters from the VIN code of the vehicle involved in the accident, and only retaining numbers and letters, and all letters are capitalized; the noise data processing includes: removing damage assessment field data of accident losses caused by accidental factors.

[0091] In some embodiments of the present application, in the above-mentioned device, the preprocessing unit 112 is used to use pre-established standardized names to convert the names of replacement / repair parts of the damage assessment filtering data obtained after data cleaning into standardized names to obtain the damage assessment standard data.

[0092] In some embodiments of the present application, in the above-mentioned device, the analysis unit 113 is used to organize and split the multiple damage assessment specification data into at least one data file according to the vehicle model dimension, and the data file contains multiple damage assessment analysis data; convert the format of the multiple damage assessment analysis data in each of the data files to obtain at least one data format file; based on the FpGrowth algorithm, perform correlation analysis on the multiple damage assessment analysis data in each of the data format files to obtain at least one spare parts damage association rule.

[0093] In some embodiments of the present application, in the above-mentioned device, the analysis unit 113 is used to construct a damage assessment tree structure of a vehicle model dimension according to the data format file; scan the damage assessment tree structure, perform frequent item set mining, and obtain damage association rules of at least one spare part under the vehicle model dimension, wherein the damage association rules include: a preconditioner set, a postconditioner set, support, confidence, and lift.

[0094] In some embodiments of the present application, in the above-mentioned device, the analysis unit 113 is used to aggregate multiple spare parts damage association rules into a vehicle spare parts association index database; when assessing the damage of the target vehicle, if the damage assessment result hits a damage association rule in the vehicle spare parts association index database, it is determined whether there are spare parts that are not associated in the damage assessment result, and if so, a leakage warning is triggered.

[0095] It should be noted that the above-mentioned vehicle parts damage correlation analysis device can implement the above-mentioned vehicle parts damage correlation analysis method one by one, which will not be repeated one by one.

[0096] Figure 5 is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. Figure 5 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0097] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0098] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0099] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming an analysis device for the damage correlation of vehicle parts at the logical level. The processor executes the program stored in the memory and is specifically used to execute the above method.

[0100] The above application Figure 4The method performed by the analysis device for the damage correlation of vehicle parts disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above-mentioned vehicle parts damage correlation analysis method in combination with its hardware.

[0101] The electronic device may also perform Figure 4 The method of analyzing the correlation of damage of vehicle parts and components is implemented in the device for analyzing the correlation of damage of vehicle parts and components. Figure 4 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0102] The present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to execute Figure 4 The method executed by the vehicle spare parts damage correlation analysis device in the illustrated embodiment is specifically used to execute the aforementioned method.

[0103] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt 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 include computer-usable program code.

[0104] The present application 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 the present application. 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 generate 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.

[0105] 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.

[0106] 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 in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0107] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0108] 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.

[0109] 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 tape 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.

[0110] 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.

[0111] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on 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.

[0112] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for analyzing the damage correlation of vehicle parts, characterized in that: include: Obtain damage assessment source data for multiple vehicles over a historical period; Extract fields, clean data, and normalize them according to standardized names for each damage assessment source data in turn to obtain multiple damage assessment standard data; Adopting a correlation analysis model based on the FpGrowth algorithm, the plurality of damage assessment specification data are subjected to a damage correlation analysis of spare parts according to the vehicle dimension, and at least one damage association rule of spare parts is obtained; the damage association rule includes: a precondition set, a postcondition set, a support degree, a confidence degree, and a lift degree; Aggregate multiple spare parts damage association rules into a vehicle spare parts association index database; When assessing the damage of the target vehicle, if the damage assessment result hits a damage association rule in the vehicle spare parts association index database, it is determined whether there are spare parts that are not associated in the damage assessment result, and if so, a leakage warning is triggered; The damage assessment source data is sequentially subjected to field extraction, data cleaning, and normalization processing according to standardized names to obtain multiple damage assessment standard data, including: Perform at least one of missing data processing, duplicate data processing, abnormal data processing, redundant data processing, and noise data processing on the damage assessment field data obtained after field extraction, so as to filter out bad data and obtain damage assessment filtered data; Wherein, the missing data processing includes: if the replacement / repair part name of a damage assessment field data is missing, deleting the damage assessment field data; The duplicate data processing includes: if there are multiple damage assessment field data with the same claim code, then compare the VIN codes of the vehicles in the accident under the multiple claim codes, and for the vehicles in the accident with the same VIN codes, retain the damage assessment field data with the latest case closing time; The redundant data processing includes: if there are multiple damage assessment field data with the same claim code and the VIN code of the accident vehicle, compare the other fields under the multiple claim codes, and for those with the same other fields, retain the damage assessment field data with the latest case closing time; The abnormal data processing includes: removing spaces and special symbols from the names of replacement / repair parts, and only retaining Chinese characters; removing spaces, special symbols, and Chinese characters from the vehicle OE code, and only retaining numbers and letters, and capitalizing the letters; removing special symbols and Chinese characters from the VIN code of the accident vehicle, and only retaining numbers and letters, and capitalizing the letters; The noise data processing includes: removing the damage assessment field data of accident loss caused by accidental factors; The relevance analysis model based on the FpGrowth algorithm is used to perform a relevance analysis of spare parts damage on the plurality of damage assessment specification data according to the vehicle model dimension, and at least one spare parts damage association rule is obtained, including: According to the vehicle model dimension, the plurality of damage assessment specification data are sorted and divided into at least one data file, wherein the data file contains a plurality of damage assessment analysis data; Converting the format of the plurality of damage assessment analysis data in each of the data files to obtain at least one data format file; Based on the FpGrowth algorithm, a correlation analysis is performed on the multiple damage assessment analysis data in each of the data format files to obtain at least one spare parts damage association rule; Based on the FpGrowth algorithm, a correlation analysis is performed on the multiple damage assessment analysis data in each of the data format files to obtain at least one spare parts damage association rule, including: Construct a damage assessment tree structure of vehicle model dimension according to the data format file; The damage assessment tree structure is scanned to mine frequent item sets, and a damage association rule of at least one spare part under the vehicle model dimension is obtained.

2. The method according to claim 1, characterized in that The damage assessment source data is sequentially subjected to field extraction, data cleaning, and normalization processing according to standardized names to obtain multiple damage assessment standard data, including at least: According to the preset fields and the extraction rules of each field, the vehicle damage assessment source data is extracted to obtain multiple damage assessment field data, wherein the preset fields include: claim code, VIN code of the insured vehicle, case closing time, insured area, location of the accident, total amount of damage assessment, total amount of compensation, amount of loss, accident classification, cause of the accident, name of replacement / repair parts, replacement or repair mark, number of replacement / repair parts, replacement / repair parts, OEM code, vehicle OE code, and parts price.

3. The method according to claim 2, characterized in that The said sequentially extracting fields from each of the damage assessment source data, performing data cleaning, and normalizing processing according to standardized names to obtain a plurality of damage assessment standard data, further includes: By using pre-established standardized names, the names of replacement / repair parts of the damage assessment filtering data obtained after data cleaning are converted into standardized names to obtain the damage assessment standard data.

4. A device for analyzing the damage correlation of vehicle parts, characterized in that: The device comprises: An acquisition unit, used to acquire damage assessment source data of multiple vehicles in a historical period; A preprocessing unit is used to extract fields, clean data, and normalize each damage assessment source data in turn according to standardized names to obtain multiple damage assessment standard data; An analysis unit, configured to use a correlation analysis model based on an FpGrowth algorithm to perform a relevance analysis of spare parts damage on the plurality of damage assessment specification data according to a vehicle dimension, and obtain at least one damage association rule for spare parts; the damage association rule includes: a precondition set, a postcondition set, a support, a confidence, and a lift; The analysis unit is further used to aggregate the damage association rules of multiple spare parts into a vehicle spare parts association index database; when assessing the damage of a target vehicle, if the damage assessment result hits a damage association rule in the vehicle spare parts association index database, it is determined whether there are spare parts that do not have association in the damage assessment result, and if so, a leakage warning is triggered; A preprocessing unit, used to perform at least one of missing data processing, duplicate data processing, abnormal data processing, redundant data processing, and noise data processing on the damage assessment field data obtained after field extraction, so as to filter out bad data and obtain damage assessment filtered data; Wherein, the missing data processing includes: if the replacement / repair part name of a damage assessment field data is missing, deleting the damage assessment field data; The duplicate data processing includes: if there are multiple damage assessment field data with the same claim code, then compare the VIN codes of the vehicles involved in the accident under the multiple claim codes, and for the vehicles involved in the accident with the same VIN codes, retain the damage assessment field data with the latest case closing time; The redundant data processing includes: if there are multiple damage assessment field data with the same claim code and the VIN code of the accident vehicle, compare the other fields under the multiple claim codes, and if the other fields are the same, retain the damage assessment field data with the latest case closing time; The abnormal data processing includes: removing spaces and special symbols from the names of replacement / repair parts, and only retaining Chinese characters; removing spaces, special symbols, and Chinese characters from the vehicle OE code, and only retaining numbers and letters, and capitalizing the letters; Remove special symbols and Chinese characters from the VIN code of the accident vehicle, retain only numbers and letters, and capitalize the letters; The noise data processing includes: removing the damage assessment field data of accident loss caused by accidental factors; The analysis unit is further used to organize and divide the multiple damage assessment specification data into at least one data file according to the vehicle model dimension, wherein the data file contains multiple damage assessment analysis data; perform format conversion on the multiple damage assessment analysis data in each of the data files to obtain at least one data format file; perform correlation analysis on the multiple damage assessment analysis data in each of the data format files based on the FpGrowth algorithm to obtain at least one spare parts damage association rule; A damage assessment tree structure of a vehicle model dimension is constructed according to the data format file; the damage assessment tree structure is scanned to mine frequent item sets to obtain damage association rules of at least one spare part under the vehicle model dimension.

5. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions, wherein when the executable instructions are executed, the processor executes the method for analyzing the damage correlation of vehicle parts according to any one of claims 1 to 3.

6. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, enables the electronic device to execute the vehicle spare parts damage correlation analysis method according to any one of claims 1 to 3.

Images