WO2022100455A1 - 车辆全损检测方法、装置、终端设备及存储介质 - Google Patents

车辆全损检测方法、装置、终端设备及存储介质 Download PDF

Info

Publication number
WO2022100455A1
WO2022100455A1 PCT/CN2021/127259 CN2021127259W WO2022100455A1 WO 2022100455 A1 WO2022100455 A1 WO 2022100455A1 CN 2021127259 W CN2021127259 W CN 2021127259W WO 2022100455 A1 WO2022100455 A1 WO 2022100455A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
accessory
loss
danger
weight
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2021/127259
Other languages
English (en)
French (fr)
Inventor
张逸
方华
赵志伟
黄榀
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
OneConnect Smart Technology Co Ltd
Original Assignee
OneConnect Smart Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by OneConnect Smart Technology Co Ltd filed Critical OneConnect Smart Technology Co Ltd
Publication of WO2022100455A1 publication Critical patent/WO2022100455A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08—Insurance
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/22—Indexing; Data structures therefor; Storage structures
    • G06F16/2282—Tablespace storage structures; Management thereof
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/08—Detecting or categorising vehicles

Definitions

  • the present application relates to the field of artificial intelligence, and in particular, to a vehicle total loss detection method, device, terminal device and storage medium.
  • the inventor realized that, in the existing vehicle total loss detection process, it is based on the business experience of the personnel to determine whether the vehicle in danger has reached the total loss state, which leads to the influence factors of personnel subjectivity in the vehicle total loss detection. Reduced the accuracy of vehicle total loss detection.
  • the embodiments of the present application provide a vehicle total loss detection method, device, terminal device, and storage medium, so as to solve the problem that in the process of vehicle total loss detection in the prior art, the vehicle in danger is detected according to the business experience of the loss assessor. Whether the total loss state is reached, the problem of low accuracy of vehicle total loss detection is caused.
  • a first aspect of the embodiments of the present application provides a vehicle total loss detection method, including:
  • the probability threshold If the total loss probability of the vehicle in danger is greater than the probability threshold, it is determined that the vehicle in danger is in a state of total loss.
  • a second aspect of the embodiments of the present application provides a vehicle total loss detection device, including:
  • a damage information acquisition unit configured to acquire vehicle information of the vehicle in danger, and acquire information on the damage of accessories of the vehicle in danger according to the vehicle information;
  • a loss evidence weight calculation unit configured to calculate the corresponding damage quantity of the accident vehicle in different accessory groups according to the accessory damage information, and calculate the loss evidence weight of the accident vehicle according to the corresponding damage quantity in the different accessory groups. , the loss evidence weight is used to characterize the entire vehicle loss degree of the accident vehicle;
  • a total loss probability calculation unit configured to calculate the loss weight threshold of the vehicle in danger according to the vehicle information, and calculate the total loss probability of the vehicle in danger according to the loss evidence weight and the loss weight threshold;
  • a total loss determination unit configured to determine that the vehicle in danger is in a state of total loss if the probability of total loss of the vehicle in danger is greater than a probability threshold.
  • a third aspect of the embodiments of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, when the processor executes the computer program accomplish:
  • the probability threshold If the total loss probability of the vehicle in danger is greater than the probability threshold, it is determined that the vehicle in danger is in a state of total loss.
  • a fourth aspect of the embodiments of the present application provides a storage medium, where the storage medium stores a computer program, and the computer program is executed by a processor to implement:
  • the probability threshold If the total loss probability of the vehicle in danger is greater than the probability threshold, it is determined that the vehicle in danger is in a state of total loss.
  • the embodiment of the present application has the beneficial effect that the damage information of the accessories of the vehicle in danger is obtained according to the vehicle information, and the corresponding damage quantity of the vehicle in different accessory groups is calculated according to the damage information of the accessories, which can effectively calculate To the corresponding damage quantities in different accessory groups, the loss evidence weight of the vehicle in danger is calculated according to the corresponding damage quantities in different accessory groups.
  • the degree of vehicle loss of the vehicle in danger can be effectively obtained, and the total loss probability of the vehicle in danger can be calculated according to the weight of the loss evidence and the loss weight threshold.
  • the vehicle in danger is determined to be in a total loss state, thereby preventing the influence of business experience or subjective factors on the determination of total loss state, improving the accuracy of vehicle total loss detection, and eliminating the need for vehicle detection. Demolition and damage determination improve the detection efficiency of vehicle total loss detection.
  • Fig. 1 is the realization flow chart of a kind of vehicle total loss detection method provided by the embodiment of the present application;
  • FIG. 2 is an implementation flowchart of a vehicle total loss detection method provided by another embodiment of the present application.
  • FIG. 3 is a structural block diagram of a vehicle total loss detection device provided by an embodiment of the present application.
  • FIG. 4 is a structural block diagram of a terminal device provided by an embodiment of the present application.
  • the vehicle total loss detection method involved in the embodiments of the present application may be executed by a control device or terminal (hereinafter referred to as a "mobile terminal").
  • FIG. 1 shows an implementation flowchart of a vehicle total loss detection method provided by an embodiment of the present application, including:
  • Step S10 acquiring vehicle information of the vehicle in danger, and acquiring damage information on accessories of the vehicle in danger according to the vehicle information.
  • the vehicle information includes captured pictures corresponding to different vehicle accessories on the vehicle in danger or a text description of the degree of damage.
  • the vehicle information includes captured pictures corresponding to different vehicle accessories
  • by performing image analysis on the captured pictures corresponding to the vehicle accessories In order to determine whether the vehicle accessories corresponding to the photographed pictures are damaged accessories, the image analysis is used to calculate the damage degree of the corresponding vehicle accessories according to the photographed pictures. If the calculated damage degree is greater than the damage threshold, it is determined that the vehicle accessories corresponding to the damage degree are Damaged accessories.
  • the accessory damage information stores photos corresponding to the damaged accessories on the vehicle in danger.
  • the accessory damage information may include photos corresponding to the damaged door panels and the damaged front bumper on the vehicle.
  • Step S20 Calculate the damage quantity corresponding to the accident vehicle in different accessory groups according to the accessory damage information, and calculate the loss evidence weight of the accident vehicle according to the corresponding damage quantity in the different accessory groups.
  • the loss evidence weight is used to represent the entire vehicle loss degree of the accident vehicle.
  • corresponding quantity thresholds are set for different accessory groups, and weights are calculated based on the quantity thresholds and the damage quantity in the corresponding accessory groups, so as to obtain the loss sub-weights corresponding to different accessory groups, and based on the different accessories
  • the loss sub-weight corresponding to the group is obtained to obtain the loss evidence weight of the vehicle in danger.
  • calculating, according to the accessory damage information, the corresponding damage quantities of the vehicle in danger in different accessory groups including:
  • the accessory identifier of the damaged accessory in the accessory damage information respectively and query the corresponding accessory group according to the accessory identifier of the damaged accessory, wherein, in this embodiment, an accessory group look-up table is pre-stored, and the accessory group look-up table
  • the corresponding relationship between different accessory identifiers and corresponding accessory groups is stored in the , and the accessory identifiers and accessory groups are stored in a one-to-one or one-to-many manner.
  • the accessory group includes an interior accessory group and an exterior accessory group. Therefore, by matching the accessory identifiers of different damaged accessories in the accessory damage information with the accessory group query table, respectively, the accessory groups corresponding to different damaged accessories are obtained.
  • the matching result between the accessory ID of the damaged accessory a1 and the accessory group query table is that the accessory group A is damaged.
  • the matching result between the accessory ID of the accessory a2 and the accessory group look-up table is accessory group B. If the matching result between the accessory ID of the damaged accessory a3 and the accessory group look-up table is accessory group A, the damaged accessories a1 and a3 will be added.
  • To the accessory group A add the damaged accessory a2 to the accessory group B. At this time, the damaged quantity corresponding to the accessory group A is 2, and the damaged quantity corresponding to the accessory group B is 1.
  • calculating the weight of the evidence of loss of the vehicle in danger according to the corresponding damage quantities in the different accessory groups includes:
  • calculation formula used to calculate the loss sub-weight corresponding to the accessory group according to the quantity threshold and the damage quantity in the accessory group is:
  • thrd i is the quantity threshold corresponding to the i-th accessory group
  • thrd i up is the upper limit value of the weight set for the i-th accessory group
  • g is the damage quantity in the i-th accessory group
  • W i (g) is the loss sub-weight corresponding to the i-th accessory group.
  • Step S30 Calculate the loss weight threshold of the vehicle in danger according to the vehicle information, and calculate the total loss probability of the vehicle in danger according to the loss evidence weight and the loss weight threshold;
  • the loss evidence weight is used to represent the current loss degree of the vehicle in danger
  • the loss weight threshold is used to represent the corresponding loss weight when the accident vehicle is in a state of total loss
  • calculating the loss weight threshold of the vehicle in danger according to the vehicle information includes:
  • a vehicle age classification query table is pre-stored in this embodiment, and the vehicle age classification query The table stores the correspondence between different vehicle age groups and the corresponding vehicle age classifications. Therefore, by matching the vehicle age of the accident vehicle with the vehicle age classification query table, the vehicle age classification corresponding to the accident vehicle can be obtained;
  • a value preservation coefficient lookup table is pre-stored, and the value preservation coefficient The lookup table stores the correspondence between different vehicle age classifications and the corresponding value preservation coefficients. Therefore, by matching the vehicle age classification of the accident vehicle with the value preservation coefficient lookup table, the corresponding value preservation coefficient of the accident vehicle can be obtained. The coefficient is used to characterize the degree of preservation of the value of the vehicle in danger.
  • calculating the total loss probability of the vehicle in danger according to the loss evidence weight and the loss weight threshold includes: calculating the loss evidence weight and the loss weight threshold according to an exponential life function. Perform exponential operation to obtain the total loss probability of the vehicle in danger.
  • Step S40 if the total loss probability of the vehicle in danger is greater than a probability threshold, it is determined that the vehicle in danger is in a state of total loss.
  • the probability threshold can be set according to requirements, for example, the probability threshold can be set to 78%, 87% or 95%, etc.
  • the vehicle in danger will be fully
  • the total loss mark can be used to mark the accident vehicle in the form of text, voice or image, so as to prompt the corresponding user or the loss assessor to determine that the accident vehicle is in a total loss state.
  • the total loss probability of the accident vehicle is less than or equal to the probability threshold, it is determined that the accident vehicle is not in a total loss state, and no total loss compensation is required for the accident vehicle.
  • the damage quantity corresponding to the different accessory groups can be effectively calculated.
  • the weight of the loss evidence of the vehicle in danger is calculated according to the corresponding damage quantities in different parts groups. Since the weight of the evidence of loss is used to represent the degree of loss of the vehicle in danger, the weight of the evidence of loss can effectively obtain the degree of loss of the vehicle in danger.
  • the total loss probability of the vehicle in danger is calculated according to the loss evidence weight and the loss weight threshold. Based on the total loss probability, it can effectively determine whether the corresponding vehicle is in a state of total loss.
  • the vehicle in danger can be determined. It is in a total loss state, thereby preventing the influence of business experience or subjective factors on the determination of total loss state, improving the accuracy of vehicle total loss detection, and eliminating the need for disassembly and damage determination of the accident vehicle, which improves the accuracy of vehicle total loss detection. detection efficiency.
  • FIG. 2 is a flowchart of an implementation of a vehicle total loss detection method provided by another embodiment of the present application.
  • the vehicle total loss detection method provided in this embodiment is a further refinement of step S10 in the embodiment corresponding to Fig. 1, including:
  • Step S11 acquiring the photographed pictures corresponding to different vehicle accessories in the vehicle information, and querying the corresponding standard pictures according to the accessory identifiers of the vehicle accessories.
  • Step S12 respectively calculating the image similarity between the captured pictures corresponding to different vehicle accessories and the standard pictures.
  • the standard pixel matrix and the shooting pixel matrix are obtained by respectively obtaining the standard picture corresponding to the same vehicle accessory and the matrix of the pixels in the shot picture, and the distance between the standard pixel matrix and the shooting pixel matrix is calculated according to the Euclidean distance formula, so as to obtain the The image similarity between the captured image and the standard image, the greater the image similarity between the captured image and the standard image, the lower the damage degree of the vehicle accessories.
  • Step S13 if the image similarity between the captured picture corresponding to the vehicle accessory and the standard image is less than a similarity threshold, mark the vehicle accessory as a damaged accessory.
  • the similarity threshold can be set according to requirements. For example, in this step, the similarity threshold can be set to 10%, 5%, or 3%, etc., and the similarity threshold is used to determine whether the vehicle accessories corresponding to the image similarity are Damaged accessories.
  • the image similarity between the photographed image corresponding to the vehicle accessory and the standard image is less than the similarity threshold, that is, the difference between the current state of the vehicle accessory and the non-damaged state is greater than the threshold difference. Therefore, It is determined that the current damage degree of the vehicle accessory is relatively large, and the vehicle accessory is marked as a damaged accessory.
  • Step S14 acquiring the photographed picture corresponding to the damaged accessory, and obtaining the accessory damage information.
  • the accuracy of the calculation of the similarity of the images corresponding to different vehicle accessories is effectively improved.
  • the image similarity of different vehicle accessories can effectively determine whether the vehicle accessories are damaged accessories, and by obtaining the photographed pictures corresponding to different damaged accessories, the damage information of the accessories corresponding to the accident vehicle can be obtained.
  • the total loss probability of the vehicle in danger is calculated based on the loss evidence weight and the loss weight threshold. Specifically, the total loss probability of the accident vehicle is calculated from the loss evidence weight and the loss weight threshold.
  • Uploading the total loss probability of the accident vehicle to the blockchain can ensure its safety and fairness and transparency to users.
  • the user equipment can download the total loss probability of the vehicle in danger from the blockchain, so as to check whether the total loss probability of the vehicle in danger has been tampered with.
  • the blockchain referred to in this example is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.
  • Blockchain essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block.
  • the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.
  • FIG. 3 is a structural block diagram of a vehicle total loss detection apparatus 100 provided by an embodiment of the present application.
  • each unit included in the vehicle total loss detection apparatus 100 is used to execute each step in the embodiment corresponding to FIG. 1 and FIG. 2 .
  • FIG. 1 , FIG. 2 and the related descriptions in the embodiments corresponding to FIG. 1 and FIG. 2 For convenience of explanation, only the parts related to this embodiment are shown.
  • the vehicle total loss detection device 100 includes: a damage information acquisition unit 10 , a loss evidence weight calculation unit 11 , a total loss probability calculation unit 12 and a total loss determination unit 13 , wherein:
  • the damage information acquisition unit 10 is configured to acquire vehicle information of the vehicle in danger, and acquire information on the damage of accessories of the vehicle in danger according to the vehicle information.
  • the damage information obtaining unit 10 is further configured to: obtain the photographed pictures corresponding to different vehicle accessories in the vehicle information, and query the corresponding standard pictures according to the accessory identifiers of the vehicle accessories;
  • the loss evidence weight calculation unit 11 is configured to calculate the corresponding damage quantity of the accident vehicle in different accessory groups according to the accessory damage information, and calculate the loss evidence of the accident vehicle according to the corresponding damage quantity in the different accessory groups. weight, the weight of the loss evidence is used to represent the whole vehicle loss degree of the vehicle in danger.
  • the loss evidence weight calculation unit 11 is further configured to: separately obtain the accessory identifiers of the damaged accessories in the accessory damage information, and query the corresponding accessory group according to the accessory identifiers of the damaged accessories;
  • the different damaged accessories are added to the corresponding queried accessory group, and the number of the damaged accessories in the different accessories is obtained respectively, so as to obtain the damaged quantity corresponding to the different accessory groups.
  • the loss evidence weight calculation unit 11 is further configured to: respectively obtain the quantity thresholds corresponding to the different accessory groups, and calculate the loss factor corresponding to the accessory group according to the quantity threshold and the damage quantity in the accessory group. Weights;
  • calculation formula used to calculate the loss sub-weight corresponding to the accessory group according to the quantity threshold and the damage quantity in the accessory group is:
  • thrd i is the quantity threshold corresponding to the i-th accessory group
  • thrd i up is the upper limit value of the weight set for the i-th accessory group
  • g is the damage quantity in the i-th accessory group
  • W i (g) is the loss sub-weight corresponding to the i-th accessory group.
  • the total loss probability calculation unit 12 is configured to calculate the loss weight threshold of the accident vehicle according to the vehicle information, and calculate the total loss probability of the accident vehicle according to the loss evidence weight and the loss weight threshold.
  • the total loss probability calculation unit 12 is further configured to: obtain the vehicle age of the accident vehicle in the vehicle information, and determine the vehicle age classification of the accident vehicle according to the vehicle age;
  • the total loss determination unit 13 is configured to determine that the accident vehicle is in a total loss state if the total loss probability of the accident vehicle is greater than a probability threshold.
  • the total loss determination unit 13 is further configured to: perform an exponential operation on the loss evidence weight and the loss weight threshold according to an exponential life function, so as to obtain the total loss probability of the out-of-hazard vehicle.
  • the corresponding damage quantity in the different accessory groups can be effectively calculated.
  • the weight of the loss evidence of the vehicle in danger is calculated according to the corresponding damage quantities in different parts groups. Since the weight of the evidence of loss is used to represent the degree of loss of the vehicle in danger, the weight of the evidence of loss can effectively obtain the degree of loss of the vehicle in danger.
  • the total loss probability of the vehicle in danger is calculated according to the loss evidence weight and the loss weight threshold. Based on the total loss probability, it can effectively determine whether the corresponding vehicle is in a state of total loss.
  • the vehicle in danger can be determined. It is in a total loss state, thereby preventing the influence of business experience or subjective factors on the determination of total loss state, improving the accuracy of vehicle total loss detection, and eliminating the need for disassembly and damage determination of the accident vehicle, which improves the accuracy of vehicle total loss detection. detection efficiency.
  • FIG. 4 is a structural block diagram of a terminal device 2 provided by another embodiment of the present application.
  • the terminal device 2 of this embodiment includes: a processor 20 , a memory 21 , and a computer program 22 stored in the memory 21 and executable on the processor 20 , such as a vehicle total loss detection method program of.
  • the processor 20 executes the computer program 22
  • the steps in each of the above-mentioned embodiments of the vehicle total loss detection method are implemented, for example, S10 to S40 shown in FIG. 1 , or S11 to S14 shown in FIG. 2 .
  • the processor 20 executes the computer program 22
  • the functions of the units in the embodiment corresponding to FIG. 3 are implemented, for example, the functions of the units 10 to 13 shown in FIG. 3 , please refer to the corresponding implementation in FIG. 4 for details. The relevant descriptions in the examples will not be repeated here.
  • the computer program 22 may be divided into one or more units, and the one or more units are stored in the memory 21 and executed by the processor 20 to complete the present application.
  • the one or more units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 22 in the terminal device 2 .
  • the computer program 22 can be divided into a damage information acquisition unit 10, a loss evidence weight calculation unit 11, a total loss probability calculation unit 12, and a total loss determination unit 13, and the specific functions of each unit are as described above.
  • the terminal device may include, but is not limited to, the processor 20 and the memory 21 .
  • FIG. 4 is only an example of the terminal device 2, and does not constitute a limitation on the terminal device 2, and may include more or less components than the one shown, or combine some components, or different components
  • the terminal device may further include an input and output device, a network access device, a bus, and the like.
  • the so-called processor 20 may be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the memory 21 may be an internal storage unit of the terminal device 2 , such as a hard disk or a memory of the terminal device 2 .
  • the memory 21 can also be an external storage device of the terminal device 2, such as a plug-in hard disk equipped on the terminal device 2, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, Flash Card, etc.
  • the memory 21 may also include both an internal storage unit of the terminal device 2 and an external storage device.
  • the memory 21 is used to store the computer program and other programs and data required by the terminal device.
  • the memory 21 can also be used to temporarily store data that has been output or will be output.
  • Embodiments of the present application further provide a storage medium, where a computer program is stored in the storage medium, and when the computer program is executed by a processor, implements each step of the vehicle total loss detection method provided by any of the above solutions, and the storage medium may As a computer-readable storage medium, the computer-readable storage medium may be non-volatile or volatile.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Databases & Information Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Technology Law (AREA)
  • General Business, Economics & Management (AREA)
  • Library & Information Science (AREA)
  • Quality & Reliability (AREA)
  • Software Systems (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
  • Traffic Control Systems (AREA)

Abstract

本申请适用于人工智能技术领域，提供了一种车辆全损检测方法、装置、终端设备及存储介质，该方法包括：根据出险车辆的车辆信息获取配件损坏信息；根据配件损坏信息计算不同配件组中对应的损坏数量，根据不同配件组中对应的损坏数量计算损失证据权重；根据车辆信息计算损失权重阈值，根据损失证据权重和损失权重阈值计算全损概率；若损概率大于概率阈值，则判定出险车辆为全损状态。本申请通过根据损失证据权重和损失权重阈值计算出险车辆的全损概率，基于全损概率能有效的判断对应出险车辆是否处于全损状态，即，进而防止了由于业务经验或人员主观因素对全损状态认定的影响，提高了车辆全损检测的准确性。此外，本申请还涉及区块链技术。

Description

车辆全损检测方法、装置、终端设备及存储介质
本申请要求于2020年11月13日提交中国专利局、申请号为202011265076.9，发明名称为“车辆全损检测方法、装置、终端设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及人工智能领域，尤其涉及一种车辆全损检测方法、装置、终端设备及存储介质。
背景技术
在车辆定损领域，出险车辆是否达到全损是一个非常有争议的问题，这关系到保险公司，投保人、修理厂等多方利益。一方面，对于维修费用高于车辆实际价值的车辆，保险公司希望推定全损，减少保险公司的损失；另一方面，投保人希望维护自身利益，获取更多补偿；此外，修理厂希望不拆解出险车辆，直接回收改装，获取不菲的收益。由于车辆的残值拆解、不拆解价值差异巨大，在不拆解车辆的情况下，如何准确、快速判断车辆是否达到全损标准是保险行业面临的一个亟需解决的问题。
技术问题
综上，发明人意识到，现有的车辆全损检测过程中，均是依据定损人员的业务经验检测出险车辆是否达到全损状态，进而导致车辆全损检测存在人员主观性的影响因素，降低了车辆全损检测的准确性。
技术解决方案
有鉴于此，本申请实施例提供了一种车辆全损检测方法、装置、终端设备及存储介质，以解决现有技术的车辆全损检测过程中，由于依据定损人员的业务经验检测出险车辆是否达到全损状态，所导致的车辆全损检测准确性低下的问题。
本申请实施例的第一方面提供了一种车辆全损检测方法，包括：
获取出险车辆的车辆信息，并根据所述车辆信息获取所述出险车辆的配件损坏信息；
根据所述配件损坏信息计算所述出险车辆在不同配件组中对应的损坏数量，并根据不同所述配件组中对应的损坏数量计算所述出险车辆的损失证据权重，所述损失证据权重用于表征所述出险车辆的整车损失程度；
根据所述车辆信息计算所述出险车辆的损失权重阈值，并根据所述损失证据权重和所述损失权重阈值计算所述出险车辆的全损概率；
若所述出险车辆的全损概率大于概率阈值，则判定所述出险车辆为全损状态。
本申请实施例的第二方面提供了一种车辆全损检测装置，包括：
损坏信息获取单元，用于获取出险车辆的车辆信息，并根据所述车辆信息获取所述出险车辆的配件损坏信息；
损失证据权重计算单元，用于根据所述配件损坏信息计算所述出险车辆在不同配件组中对应的损坏数量，并根据不同所述配件组中对应的损坏数量计算所述出险车辆的损失证据权重，所述损失证据权重用于表征所述出险车辆的整车损失程度；
全损概率计算单元，用于根据所述车辆信息计算所述出险车辆的损失权重阈值，并根据所述损失证据权重和所述损失权重阈值计算所述出险车辆的全损概率；
全损判定单元，用于若所述出险车辆的全损概率大于概率阈值，则判定所述出险车辆为全损状态。
本申请实施例的第三方面提供了一种终端设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现：
获取出险车辆的车辆信息，并根据所述车辆信息获取所述出险车辆的配件损坏信 息；
根据所述配件损坏信息计算所述出险车辆在不同配件组中对应的损坏数量，并根据不同所述配件组中对应的损坏数量计算所述出险车辆的损失证据权重，所述损失证据权重用于表征所述出险车辆的整车损失程度；
根据所述车辆信息计算所述出险车辆的损失权重阈值，并根据所述损失证据权重和所述损失权重阈值计算所述出险车辆的全损概率；
若所述出险车辆的全损概率大于概率阈值，则判定所述出险车辆为全损状态。
本申请实施例的第四方面提供了一种存储介质，所述存储介质存储有计算机程序，所述计算机程序被处理器执行时实现：
获取出险车辆的车辆信息，并根据所述车辆信息获取所述出险车辆的配件损坏信息；
根据所述配件损坏信息计算所述出险车辆在不同配件组中对应的损坏数量，并根据不同所述配件组中对应的损坏数量计算所述出险车辆的损失证据权重，所述损失证据权重用于表征所述出险车辆的整车损失程度；
根据所述车辆信息计算所述出险车辆的损失权重阈值，并根据所述损失证据权重和所述损失权重阈值计算所述出险车辆的全损概率；
若所述出险车辆的全损概率大于概率阈值，则判定所述出险车辆为全损状态。
有益效果
本申请实施例与现有技术相比存在的有益效果是：通过根据车辆信息获取出险车辆的配件损坏信息，并根据配件损坏信息计算出险车辆在不同配件组中对应的损坏数量，能有效的计算到不同配件组中对应的损坏数量，通过根据不同配件组中对应的损坏数量计算出险车辆的损失证据权重，由于损失证据权重用于表征出险车辆的整车损失程度，因此，基于损失证据权重能有效得到出险车辆的整车损失程度，通过根据损失证据权重和损失权重阈值计算出险车辆的全损概率，基于全损概率能有效的判断对应出险车辆是否处于全损状态，即，若出险车辆的全损概率大于概率阈值，则判定出险车辆为全损状态，进而防止了由于业务经验或人员主观因素对全损状态认定的影响，提高了车辆全损检测的准确性，且无需进行出险车辆的拆卸定损，提高了车辆全损检测的检测效率。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的一种车辆全损检测方法的实现流程图；
图2是本申请另一实施例提供的一种车辆全损检测方法的实现流程图；
图3是本申请实施例提供的一种车辆全损检测装置的结构框图；
图4是本申请实施例提供的一种终端设备的结构框图。
本发明的实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
本申请实施例所涉及的车辆全损检测方法，可以由控制设备或终端(以下称“移动终端”)执行。
请参阅图1，图1示出了本申请实施例提供的一种车辆全损检测方法的实现流程图，包括：
步骤S10，获取出险车辆的车辆信息，并根据所述车辆信息获取所述出险车辆的配 件损坏信息。
其中，该车辆信息包括出险车辆上不同车辆配件对应的拍摄图片或损坏程度的文字描述，当该车辆信息包括不同车辆配件对应的拍摄图片时，通过对该车辆配件对应的拍摄图片进行图片分析，以判断该拍摄图片对应的车辆配件是否为损坏配件，该图片分析用于根据拍摄图片计算对应车辆配件的损坏程度，若计算得到的损坏程度大于损坏阈值，则判定该损坏程度对应的车辆配件是损坏配件。
具体的，该步骤中，该配件损坏信息中存储有对应出险车辆上损坏配件对应的拍摄图片，例如，该配件损坏信息可以包括出险车辆上损坏车门板和损坏前保险杠对应的拍摄图片。
步骤S20，根据所述配件损坏信息计算所述出险车辆在不同配件组中对应的损坏数量，并根据不同所述配件组中对应的损坏数量计算所述出险车辆的损失证据权重。
其中，通过根据配件损坏信息计算出险车辆在不同配件组中对应的损坏数量，有效的提高了出险车辆的损失证据权重计算的准确性，该损失证据权重用于表征出险车辆的整车损失程度。
该步骤中，当该出险车辆中不同配件组对应的损坏数量越大时，则计算得到的出险车辆的损失证据权重越大，出险车辆的损失证据权重越大，则该出险车辆的整车损失程度越大。
具体的，该步骤中，针对不同的配件组设置有对应的数量阈值，通过基于数量阈值和对应配件组中的损坏数量进行权重计算，以得到不同配件组对应的损失子权重，并基于不同配件组对应的损失子权重，以得到该出险车辆的损失证据权重。
可选的，该步骤中，所述根据所述配件损坏信息计算所述出险车辆在不同配件组中对应的损坏数量，包括：
分别获取所述配件损坏信息中损坏配件的配件标识，并根据所述损坏配件的配件标识查询对应的所述配件组，其中，本实施例中预存储有配件组查询表，该配件组查询表中存储有不同配件标识与对应配件组之间的对应关系，且该配件标识与配件组之间采用一对一或一对多的方式进行存储，该配件组包括内饰配件组、外饰配件组、动力配件组或行驶配件组等，因此，通过分别将配件损坏信息中不同损坏配件的配件标识与配件组查询表进行匹配，得到不同损坏配件对应的配件组。
将不同所述损坏配件添加至对应查询到的所述配件组中，并分别获取不同所述配件中所述损坏配件的数量，得到不同所述配件组对应的损坏数量，其中，通过将不同损坏配件添加至对应查询到的配件组中，有效的提高了不同配件中损坏配件数量计算的准确性，例如，损坏配件a1的配件标识与配件组查询表之间的匹配结果是配件组A，损坏配件a2的配件标识与配件组查询表之间的匹配结果是配件组B，损坏配件a3的配件标识与配件组查询表之间的匹配结果是配件组A时，则将损坏配件a1和a3添加至配件组A中，将损坏配件a2添加至配件组B中，此时，配件组A对应的损坏数量为2个，配件组B对应的损坏数量为1个。
可选的，该步骤中，所述根据不同所述配件组中对应的损坏数量计算所述出险车辆的损失证据权重，包括：
分别获取不同所述配件组对应的数量阈值，并根据所述数量阈值和所述配件组中的损坏数量计算对应所述配件组的损失子权重，其中，该损失子权重用于表征对应配件组的损坏程度；
计算不同所述配件组之间的损失子权重的和，得到所述损失证据权重。
进一步地，所述根据所述数量阈值和所述配件组中的损坏数量计算对应所述配件组的损失子权重所采用的计算公式为：
Figure PCTCN2021127259-appb-000001
其中，thrd i是第i个所述配件组对应的数量阈值，thrd i up针对第i个所述配件组设置的权重上限值，g是第i个所述配件组中的损坏数量，W i(g)是第i个所述配件组对应的损失子权重。
步骤S30，根据所述车辆信息计算所述出险车辆的损失权重阈值，并根据所述损失证据权重和所述损失权重阈值计算所述出险车辆的全损概率；
其中，由于该损失证据权重用于表征出险车辆当前的损失程度，该损失权重阈值用于表征该出险车辆处于全损状态时对应的损失权重，因此，通过根据损失证据权重和损失权重阈值能有效的计算到出险车辆的全损概率，该全损概率是出险车辆处于全损状态的概率值。
可选的，该步骤中，所述根据所述车辆信息计算所述出险车辆的损失权重阈值，包括：
获取所述车辆信息中所述出险车辆的车辆年龄，并根据所述车辆年龄确定所述出险车辆的车龄分类，其中，本实施例中预存储有车龄分类查询表，该车龄分类查询表中存储有不同车龄段与对应车龄分类之间的对应关系，因此，通过将该出险车辆的车辆年龄与车龄分类查询表进行匹配，以得到该出险车辆对应的车龄分类；
根据确定到的所述车龄分类计算所述出险车辆的保值系数，并根据所述保值系数进行回归计算，得到所述损失权重阈值，本实施例中预存储有保值系数查询表，该保值系数查询表中存储有不同车龄分类与对应保值系数之间的对应关系，因此，通过将该出险车辆的车龄分类与保值系数查询表进行匹配，以得到该出险车辆对应的保值系数，该保值系数用于表征该出险车辆的价值的保值程度。
可选的，该步骤中，所述根据所述损失证据权重和所述损失权重阈值计算所述出险车辆的全损概率，包括：根据指数寿命函数对所述损失证据权重和所述损失权重阈值进行指数运算，得到所述出险车辆的全损概率。
步骤S40，若所述出险车辆的全损概率大于概率阈值，则判定所述出险车辆为全损状态。
其中，该概率阈值可以根据需求进行设置，例如，该概率阈值可以设置为78％、87％或95％等，该步骤中，若判定到出险车辆为全损状态，则对该出险车辆进行全损标记，该全损标记可以采用文字、语音或图像的方式对该出险车辆进行标记，以提示对应的用户或定损人员该出险车辆判定为全损状态。
可选的，该步骤中，若出险车辆的全损概率小于或等于概率阈值，则判定该出险车辆不为全损状态，针对该出险车辆不需要进行全损理赔。
本实施例中，通过根据车辆信息获取出险车辆的配件损坏信息，并根据配件损坏信息计算出险车辆在不同配件组中对应的损坏数量，能有效的计算到不同配件组中对应的损坏数量，通过根据不同配件组中对应的损坏数量计算出险车辆的损失证据权重，由于损失证据权重用于表征出险车辆的整车损失程度，因此，基于损失证据权重能有效得到出险车辆的整车损失程度，通过根据损失证据权重和损失权重阈值计算出险车辆的全损概率，基于全损概率能有效的判断对应出险车辆是否处于全损状态，即，若出险车辆的全损概率大于概率阈值，则判定出险车辆为全损状态，进而防止了由于业务经验或人员主观因素对全损状态认定的影响，提高了车辆全损检测的准确性，且无需进行出险车辆的拆卸定损，提高了车辆全损检测的检测效率。
请参阅图2，图2是本申请另一实施例提供的一种车辆全损检测方法的实现流程图。相对于图1对应的实施例，本实施例提供的车辆全损检测方法是对图1对应的实施例 中步骤S10的进一步细化，包括：
步骤S11，获取所述车辆信息中不同车辆配件对应的拍摄图片，并根据所述车辆配件的配件标识查询对应的标准图片。
其中，通过将该车辆信息中存储不同车辆配件与对应拍摄图片之间的对应关系，因此，通过将不同该车辆配件的配件标识与车辆信息中存储的配件标识进行匹配，以得到不同车辆配件对应的标准图片，该标准图片是对应车辆配件处于未损坏状态时的图片。
步骤S12，分别计算不同所述车辆配件对应的所述拍摄图片与所述标准图片之间的图像相似度。
其中，通过分别获取同一车辆配件对应的标准图片和拍摄图片中像素点的矩阵，得到标准像素矩阵和拍摄像素矩阵，根据欧式距离公式计算标准像素矩阵和拍摄像素矩阵之间的距离，以得到该拍摄图片与标准图片之间的图像相似度，若拍摄图片与标准图片之间的图像相似度越大，则该车辆配件的损坏程度越低。
步骤S13，若所述车辆配件对应的所述拍摄图片与所述标准图片之间的图像相似度小于相似度阈值，则将所述车辆配件标记为损坏配件。
其中，该相似度阈值可以根据需求进行设置，例如，该步骤中该相似度阈值可以设置为10％、5％或3％等，该相似度阈值用于判断图像相似度对应的车辆配件是否为损坏配件。
具体的，该步骤中，若车辆配件对应的拍摄图片与标准图片之间的图像相似度小于相似度阈值，即该车辆配件的当前状态与未处于损坏状态之间的差异大于阈值差异，因此，判定该车辆配件当前损坏程度较大，将该车辆配件标记为损坏配件。
步骤S14，获取所述损坏配件对应的所述拍摄图片，得到所述配件损坏信息。
本实施例中，通过获取车辆信息中不同车辆配件对应的拍摄图片，并根据车辆配件的配件标识查询对应的标准图片，有效的提高了不同车辆配件对应图像相似度计算的准确性，基于计算到的不同车辆配件的图像相似度，能有效的判断该车辆配件是否是损坏配件，通过获取不同损坏配件对应的拍摄图片，以得到出险车辆对应的配件损坏信息。
在本申请的所有实施例中，基于损失证据权重和损失权重阈值计算得到出险车辆的全损概率，具体来说，出险车辆的全损概率由损失证据权重和损失权重阈值计算得到。将出险车辆的全损概率上传至区块链可保证其安全性和对用户的公正透明性。用户设备可以从区块链中下载得到该出险车辆的全损概率，以便查证出险车辆的全损概率是否被篡改。本示例所指区块链是分布式数据存储、点对点传输、共识机制、加密算法等计算机技术的新型应用模式。区块链(Blockchain)，本质上是一个去中心化的数据库，是一串使用密码学方法相关联产生的数据块，每一个数据块中包含了一批次网络交易的信息，用于验证其信息的有效性(防伪)和生成下一个区块。区块链可以包括区块链底层平台、平台产品服务层以及应用服务层等。
请参阅图3，图3是本申请实施例提供的一种车辆全损检测装置100的结构框图。本实施例中该车辆全损检测装置100包括的各单元用于执行图1、图2对应的实施例中的各步骤。具体请参阅图1、图2以及图1、图2所对应的实施例中的相关描述。为了便于说明，仅示出了与本实施例相关的部分。参见图3，车辆全损检测装置100包括：损坏信息获取单元10、损失证据权重计算单元11、全损概率计算单元12和全损判定单元13，其中：
损坏信息获取单元10，用于获取出险车辆的车辆信息，并根据所述车辆信息获取所述出险车辆的配件损坏信息。
其中，损坏信息获取单元10还用于：获取所述车辆信息中不同车辆配件对应的拍摄图片，并根据所述车辆配件的配件标识查询对应的标准图片；
分别计算不同所述车辆配件对应的所述拍摄图片与所述标准图片之间的图像相似度；
若所述车辆配件对应的所述拍摄图片与所述标准图片之间的图像相似度小于相似度阈值，则将所述车辆配件标记为损坏配件；
获取所述损坏配件对应的所述拍摄图片，得到所述配件损坏信息。
损失证据权重计算单元11，用于根据所述配件损坏信息计算所述出险车辆在不同配件组中对应的损坏数量，并根据不同所述配件组中对应的损坏数量计算所述出险车辆的损失证据权重，所述损失证据权重用于表征所述出险车辆的整车损失程度。
其中，损失证据权重计算单元11还用于：分别获取所述配件损坏信息中损坏配件的配件标识，并根据所述损坏配件的配件标识查询对应的所述配件组；
将不同所述损坏配件添加至对应查询到的所述配件组中，并分别获取不同所述配件中所述损坏配件的数量，得到不同所述配件组对应的损坏数量。
可选的，损失证据权重计算单元11还用于：分别获取不同所述配件组对应的数量阈值，并根据所述数量阈值和所述配件组中的损坏数量计算对应所述配件组的损失子权重；
计算不同所述配件组之间的损失子权重的和，得到所述损失证据权重。
进一步地，所述根据所述数量阈值和所述配件组中的损坏数量计算对应所述配件组的损失子权重所采用的计算公式为：
Figure PCTCN2021127259-appb-000002
其中，thrd i是第i个所述配件组对应的数量阈值，thrd i up针对第i个所述配件组设置的权重上限值，g是第i个所述配件组中的损坏数量，W i(g)是第i个所述配件组对应的损失子权重。
全损概率计算单元12，用于根据所述车辆信息计算所述出险车辆的损失权重阈值，并根据所述损失证据权重和所述损失权重阈值计算所述出险车辆的全损概率。
其中，全损概率计算单元12还用于：获取所述车辆信息中所述出险车辆的车辆年龄，并根据所述车辆年龄确定所述出险车辆的车龄分类；
根据确定到的所述车龄分类计算所述出险车辆的保值系数，并根据所述保值系数进行回归计算，得到所述损失权重阈值。
全损判定单元13，用于若所述出险车辆的全损概率大于概率阈值，则判定所述出险车辆为全损状态。
其中，全损判定单元13还用于：根据指数寿命函数对所述损失证据权重和所述损失权重阈值进行指数运算，得到所述出险车辆的全损概率。
以上可以看出，通过根据车辆信息获取出险车辆的配件损坏信息，并根据配件损坏信息计算出险车辆在不同配件组中对应的损坏数量，能有效的计算到不同配件组中对应的损坏数量，通过根据不同配件组中对应的损坏数量计算出险车辆的损失证据权重，由于损失证据权重用于表征出险车辆的整车损失程度，因此，基于损失证据权重能有效得到出险车辆的整车损失程度，通过根据损失证据权重和损失权重阈值计算出险车辆的全损概率，基于全损概率能有效的判断对应出险车辆是否处于全损状态，即，若出险车辆的全损概率大于概率阈值，则判定出险车辆为全损状态，进而防止了由于业务经验或人员主观因素对全损状态认定的影响，提高了车辆全损检测的准确性，且无需进行出险车辆的拆卸定损，提高了车辆全损检测的检测效率。
图4是本申请另一实施例提供的一种终端设备2的结构框图。如图4所示，该实施例的终端设备2包括：处理器20、存储器21以及存储在所述存储器21中并可在所 述处理器20上运行的计算机程序22，例如车辆全损检测方法的程序。处理器20执行所述计算机程序22时实现上述各个车辆全损检测方法各实施例中的步骤，例如图1所示的S10至S40，或者图2所示的S11至S14。或者，所述处理器20执行所述计算机程序22时实现上述图3对应的实施例中各单元的功能，例如，图3所示的单元10至13的功能，具体请参阅图4对应的实施例中的相关描述，此处不赘述。
示例性的，所述计算机程序22可以被分割成一个或多个单元，所述一个或者多个单元被存储在所述存储器21中，并由所述处理器20执行，以完成本申请。所述一个或多个单元可以是能够完成特定功能的一系列计算机程序指令段，该指令段用于描述所述计算机程序22在所述终端设备2中的执行过程。例如，所述计算机程序22可以被分割成损坏信息获取单元10、损失证据权重计算单元11、全损概率计算单元12和全损判定单元13，各单元具体功能如上所述。
所述终端设备可包括，但不仅限于，处理器20、存储器21。本领域技术人员可以理解，图4仅仅是终端设备2的示例，并不构成对终端设备2的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件，例如所述终端设备还可以包括输入输出设备、网络接入设备、总线等。
所称处理器20可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
所述存储器21可以是所述终端设备2的内部存储单元，例如终端设备2的硬盘或内存。所述存储器21也可以是所述终端设备2的外部存储设备，例如所述终端设备2上配备的插接式硬盘，智能存储卡(Smart Media Card，SMC)，安全数字(Secure Digital，SD)卡，闪存卡(Flash Card)等。进一步地，所述存储器21还可以既包括所述终端设备2的内部存储单元也包括外部存储设备。所述存储器21用于存储所述计算机程序以及所述终端设备所需的其他程序和数据。所述存储器21还可以用于暂时地存储已经输出或者将要输出的数据。
本申请实施例还提供了一种存储介质，所述存储介质存储有计算机程序，所述计算机程序被处理器执行时实现上述任一方案提供的车辆全损检测方法的各步骤，该存储介质可以为计算机可读存储介质，所述计算机可读存储介质可以是非易失性，也可以是易失性。
以上所述实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围，均应包含在本申请的保护范围之内。

Claims (20)

  1. 一种车辆全损检测方法，其中，包括：
    获取出险车辆的车辆信息，并根据所述车辆信息获取所述出险车辆的配件损坏信息；
    根据所述配件损坏信息计算所述出险车辆在不同配件组中对应的损坏数量，并根据不同所述配件组中对应的损坏数量计算所述出险车辆的损失证据权重，所述损失证据权重用于表征所述出险车辆的整车损失程度；
    根据所述车辆信息计算所述出险车辆的损失权重阈值，并根据所述损失证据权重和所述损失权重阈值计算所述出险车辆的全损概率；
    若所述出险车辆的全损概率大于概率阈值，则判定所述出险车辆为全损状态。
  2. 根据权利要求1所述的车辆全损检测方法，其中，所述根据所述配件损坏信息计算所述出险车辆在不同配件组中对应的损坏数量，包括：
    分别获取所述配件损坏信息中损坏配件的配件标识，并根据所述损坏配件的配件标识查询对应的所述配件组；
    将不同所述损坏配件添加至对应查询到的所述配件组中，并分别获取不同所述配件中所述损坏配件的数量，得到不同所述配件组对应的损坏数量。
  3. 根据权利要求1所述的车辆全损检测方法，其中，所述根据不同所述配件组中对应的损坏数量计算所述出险车辆的损失证据权重，包括：
    分别获取不同所述配件组对应的数量阈值，并根据所述数量阈值和所述配件组中的损坏数量计算对应所述配件组的损失子权重；
    计算不同所述配件组之间的损失子权重的和，得到所述损失证据权重。
  4. 根据权利要求3所述的车辆全损检测方法，其中，所述根据所述数量阈值和所述配件组中的损坏数量计算对应所述配件组的损失子权重所采用的计算公式为：
    Figure PCTCN2021127259-appb-100001
    其中，thrd i是第i个所述配件组对应的数量阈值，thrd i up针对第i个所述配件组设置的权重上限值，g是第i个所述配件组中的损坏数量，W i(g)是第i个所述配件组对应的损失子权重。
  5. 根据权利要求1所述的车辆全损检测方法，其中，所述根据所述车辆信息计算所述出险车辆的损失权重阈值，包括：
    获取所述车辆信息中所述出险车辆的车辆年龄，并根据所述车辆年龄确定所述出险车辆的车龄分类；
    根据确定到的所述车龄分类计算所述出险车辆的保值系数，并根据所述保值系数进行回归计算，得到所述损失权重阈值。
  6. 根据权利要求1所述的车辆全损检测方法，其中，所述根据所述车辆信息获取所述出险车辆的配件损坏信息，包括：
    获取所述车辆信息中不同车辆配件对应的拍摄图片，并根据所述车辆配件的配件标识查询对应的标准图片；
    分别计算不同所述车辆配件对应的所述拍摄图片与所述标准图片之间的图像相似度；
    若所述车辆配件对应的所述拍摄图片与所述标准图片之间的图像相似度小于相似度阈值，则将所述车辆配件标记为损坏配件；
    获取所述损坏配件对应的所述拍摄图片，得到所述配件损坏信息。
  7. 根据权利要求1所述的车辆全损检测方法，其中，所述根据所述损失证据权重和 所述损失权重阈值计算所述出险车辆的全损概率，包括：
    根据指数寿命函数对所述损失证据权重和所述损失权重阈值进行指数运算，得到所述出险车辆的全损概率。
  8. 一种车辆全损检测装置，其中，包括：
    损坏信息获取单元，用于获取出险车辆的车辆信息，并根据所述车辆信息获取所述出险车辆的配件损坏信息；
    损失证据权重计算单元，用于根据所述配件损坏信息计算所述出险车辆在不同配件组中对应的损坏数量，并根据不同所述配件组中对应的损坏数量计算所述出险车辆的损失证据权重，所述损失证据权重用于表征所述出险车辆的整车损失程度；
    全损概率计算单元，用于根据所述车辆信息计算所述出险车辆的损失权重阈值，并根据所述损失证据权重和所述损失权重阈值计算所述出险车辆的全损概率；
    全损判定单元，用于若所述出险车辆的全损概率大于概率阈值，则判定所述出险车辆为全损状态。
  9. 一种终端设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，其中，所述处理器执行所述计算机程序时实现：
    获取出险车辆的车辆信息，并根据所述车辆信息获取所述出险车辆的配件损坏信息；
    根据所述配件损坏信息计算所述出险车辆在不同配件组中对应的损坏数量，并根据不同所述配件组中对应的损坏数量计算所述出险车辆的损失证据权重，所述损失证据权重用于表征所述出险车辆的整车损失程度；
    根据所述车辆信息计算所述出险车辆的损失权重阈值，并根据所述损失证据权重和所述损失权重阈值计算所述出险车辆的全损概率；
    若所述出险车辆的全损概率大于概率阈值，则判定所述出险车辆为全损状态。
  10. 根据权利要求9所述的终端设备，其中，所述根据所述配件损坏信息计算所述出险车辆在不同配件组中对应的损坏数量，包括：
    分别获取所述配件损坏信息中损坏配件的配件标识，并根据所述损坏配件的配件标识查询对应的所述配件组；
    将不同所述损坏配件添加至对应查询到的所述配件组中，并分别获取不同所述配件中所述损坏配件的数量，得到不同所述配件组对应的损坏数量。
  11. 根据权利要求9所述的终端设备，其中，所述根据不同所述配件组中对应的损坏数量计算所述出险车辆的损失证据权重，包括：
    分别获取不同所述配件组对应的数量阈值，并根据所述数量阈值和所述配件组中的损坏数量计算对应所述配件组的损失子权重；
    计算不同所述配件组之间的损失子权重的和，得到所述损失证据权重。
  12. 根据权利要求11所述的终端设备，其中，所述根据所述数量阈值和所述配件组中的损坏数量计算对应所述配件组的损失子权重所采用的计算公式为：
    Figure PCTCN2021127259-appb-100002
    其中，thrd i是第i个所述配件组对应的数量阈值，thrd i up针对第i个所述配件组设置的权重上限值，g是第i个所述配件组中的损坏数量，W i(g)是第i个所述配件组对应的损失子权重。
  13. 根据权利要求9所述的终端设备，其中，所述根据所述车辆信息计算所述出险车辆的损失权重阈值，包括：
    获取所述车辆信息中所述出险车辆的车辆年龄，并根据所述车辆年龄确定所述出 险车辆的车龄分类；
    根据确定到的所述车龄分类计算所述出险车辆的保值系数，并根据所述保值系数进行回归计算，得到所述损失权重阈值。
  14. 根据权利要求9所述的终端设备，其中，所述根据所述车辆信息获取所述出险车辆的配件损坏信息，包括：
    获取所述车辆信息中不同车辆配件对应的拍摄图片，并根据所述车辆配件的配件标识查询对应的标准图片；
    分别计算不同所述车辆配件对应的所述拍摄图片与所述标准图片之间的图像相似度；
    若所述车辆配件对应的所述拍摄图片与所述标准图片之间的图像相似度小于相似度阈值，则将所述车辆配件标记为损坏配件；
    获取所述损坏配件对应的所述拍摄图片，得到所述配件损坏信息。
  15. 一种存储介质，所述存储介质存储有计算机程序，其中，所述计算机程序被处理器执行时实现：
    获取出险车辆的车辆信息，并根据所述车辆信息获取所述出险车辆的配件损坏信息；
    根据所述配件损坏信息计算所述出险车辆在不同配件组中对应的损坏数量，并根据不同所述配件组中对应的损坏数量计算所述出险车辆的损失证据权重，所述损失证据权重用于表征所述出险车辆的整车损失程度；
    根据所述车辆信息计算所述出险车辆的损失权重阈值，并根据所述损失证据权重和所述损失权重阈值计算所述出险车辆的全损概率；
    若所述出险车辆的全损概率大于概率阈值，则判定所述出险车辆为全损状态。
  16. 根据权利要求15所述的存储介质，其中，所述根据所述配件损坏信息计算所述出险车辆在不同配件组中对应的损坏数量，包括：
    分别获取所述配件损坏信息中损坏配件的配件标识，并根据所述损坏配件的配件标识查询对应的所述配件组；
    将不同所述损坏配件添加至对应查询到的所述配件组中，并分别获取不同所述配件中所述损坏配件的数量，得到不同所述配件组对应的损坏数量。
  17. 根据权利要求15所述的存储介质，其中，所述根据不同所述配件组中对应的损坏数量计算所述出险车辆的损失证据权重，包括：
    分别获取不同所述配件组对应的数量阈值，并根据所述数量阈值和所述配件组中的损坏数量计算对应所述配件组的损失子权重；
    计算不同所述配件组之间的损失子权重的和，得到所述损失证据权重。
  18. 根据权利要求17所述的存储介质，其中，所述根据所述数量阈值和所述配件组中的损坏数量计算对应所述配件组的损失子权重所采用的计算公式为：
    Figure PCTCN2021127259-appb-100003
    其中，thrd i是第i个所述配件组对应的数量阈值，thrd i up针对第i个所述配件组设置的权重上限值，g是第i个所述配件组中的损坏数量，W i(g)是第i个所述配件组对应的损失子权重。
  19. 根据权利要求15所述的存储介质，其中，所述根据所述车辆信息计算所述出险车辆的损失权重阈值，包括：
    获取所述车辆信息中所述出险车辆的车辆年龄，并根据所述车辆年龄确定所述出险车辆的车龄分类；
    根据确定到的所述车龄分类计算所述出险车辆的保值系数，并根据所述保值系数进行回归计算，得到所述损失权重阈值。
  20. 根据权利要求15所述的存储介质，其中，所述根据所述车辆信息获取所述出险车辆的配件损坏信息，包括：
    获取所述车辆信息中不同车辆配件对应的拍摄图片，并根据所述车辆配件的配件标识查询对应的标准图片；
    分别计算不同所述车辆配件对应的所述拍摄图片与所述标准图片之间的图像相似度；
    若所述车辆配件对应的所述拍摄图片与所述标准图片之间的图像相似度小于相似度阈值，则将所述车辆配件标记为损坏配件；
    获取所述损坏配件对应的所述拍摄图片，得到所述配件损坏信息。
PCT/CN2021/127259 2020-11-13 2021-10-29 车辆全损检测方法、装置、终端设备及存储介质 Ceased WO2022100455A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011265076.9A CN112085612B (zh) 2020-11-13 2020-11-13 车辆全损检测方法、装置、终端设备及存储介质
CN202011265076.9 2020-11-13

Publications (1)

Publication Number Publication Date
WO2022100455A1 true WO2022100455A1 (zh) 2022-05-19

Family

ID=73731081

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/127259 Ceased WO2022100455A1 (zh) 2020-11-13 2021-10-29 车辆全损检测方法、装置、终端设备及存储介质

Country Status (2)

Country Link
CN (1) CN112085612B (zh)
WO (1) WO2022100455A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112085612B (zh) * 2020-11-13 2021-03-16 深圳壹账通智能科技有限公司 车辆全损检测方法、装置、终端设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170159803A1 (en) * 2015-12-03 2017-06-08 Allison Transmission, Inc. System and method to control the operation of a transmission using engine patterns
CN109146834A (zh) * 2017-06-13 2019-01-04 上海擎感智能科技有限公司 车辆定损方法及装置、计算机可读存储介质、终端
CN111507484A (zh) * 2019-01-31 2020-08-07 北京嘀嘀无限科技发展有限公司 一种提示方法、装置、电子设备和存储介质
CN111784522A (zh) * 2020-05-29 2020-10-16 中国平安财产保险股份有限公司 车辆全损判断方法、装置、计算机设备和可读存储介质
CN112085612A (zh) * 2020-11-13 2020-12-15 深圳壹账通智能科技有限公司 车辆全损检测方法、装置、终端设备及存储介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107403424B (zh) * 2017-04-11 2020-09-18 阿里巴巴集团控股有限公司 一种基于图像的车辆定损方法、装置及电子设备
CN109443301B (zh) * 2018-09-25 2021-09-10 平安科技（深圳）有限公司 一种车辆定损方法、计算机可读存储介质及服务器
CN110084708A (zh) * 2019-04-15 2019-08-02 华侨大学 一种基于物联网和区块链技术的保险管理平台和理赔方法
CN110796487A (zh) * 2019-10-18 2020-02-14 上海钧正网络科技有限公司 数量预测方法、装置、计算机设备和存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170159803A1 (en) * 2015-12-03 2017-06-08 Allison Transmission, Inc. System and method to control the operation of a transmission using engine patterns
CN109146834A (zh) * 2017-06-13 2019-01-04 上海擎感智能科技有限公司 车辆定损方法及装置、计算机可读存储介质、终端
CN111507484A (zh) * 2019-01-31 2020-08-07 北京嘀嘀无限科技发展有限公司 一种提示方法、装置、电子设备和存储介质
CN111784522A (zh) * 2020-05-29 2020-10-16 中国平安财产保险股份有限公司 车辆全损判断方法、装置、计算机设备和可读存储介质
CN112085612A (zh) * 2020-11-13 2020-12-15 深圳壹账通智能科技有限公司 车辆全损检测方法、装置、终端设备及存储介质

Also Published As

Publication number Publication date
CN112085612B (zh) 2021-03-16
CN112085612A (zh) 2020-12-15

Similar Documents

Publication Publication Date Title
WO2021057848A1 (zh) 网络的训练方法、图像处理方法、网络、终端设备及介质
US20120155765A1 (en) Image quality assessment
US8515164B2 (en) Non-product image identification
CN109166156B (zh) 一种摄像头标定图像的生成方法、移动终端及存储介质
CN110569864A (zh) 基于gan网络的车损图像生成方法和装置
WO2021189855A1 (zh) 基于ct序列的图像识别方法、装置、电子设备及介质
US20190392201A1 (en) Method of image-based relationship analysis and system thereof
CN112070250A (zh) 车辆定损方法、装置、终端设备及存储介质
CN112862703B (zh) 基于移动拍照的图像校正方法、装置、电子设备及介质
CN108197638A (zh) 对待评估样本进行分类的方法及装置
WO2020143165A1 (zh) 一种翻拍图像的识别方法、系统及终端设备
CN111368128B (zh) 目标图片的识别方法、装置和计算机可读存储介质
WO2019136915A1 (zh) 定损理赔方法、服务器及计算机可读存储介质
US20150023599A1 (en) Optical Match Character Classification
CN115841459A (zh) 图像清晰度分值的确定方法及装置、介质、设备
WO2022100455A1 (zh) 车辆全损检测方法、装置、终端设备及存储介质
CN112348799B (zh) 车辆定损方法、装置、终端设备及存储介质
CN115984786B (zh) 车辆损伤检测方法及装置、终端、存储介质
TWI824550B (zh) 畸變圖像生成方法、電子設備及計算機可讀存儲媒體
WO2022100028A1 (zh) 接口流量异常检测方法、装置、终端设备及存储介质
CN111046899B (zh) 身份证真伪识别方法、装置、设备及存储介质
CN108197626A (zh) 信息识别方法、系统及计算机可读存储介质
CN107908613A (zh) 图片显示方法和装置
CN116363421A (zh) 图像的特征分类方法、装置、电子设备及介质
CN113254787B (zh) 事件分析方法、装置、计算机设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21890982

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 18.08.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21890982

Country of ref document: EP

Kind code of ref document: A1