CN111507854A

CN111507854A - Vehicle damage assessment method, device, medium and electronic equipment based on historical claims

Info

Publication number: CN111507854A
Application number: CN202010600384.6A
Authority: CN
Inventors: 苏孝强; 刘海龙; 张恒
Original assignee: Aibao Technology Co ltd
Current assignee: Aibao Technology Co ltd
Priority date: 2020-06-29
Filing date: 2020-06-29
Publication date: 2020-08-07

Abstract

The invention provides a vehicle damage assessment method, device, medium and electronic equipment based on historical claims, and relates to the field of vehicle insurance claims. The method comprises the following steps: acquiring a loss assessment image and accident information of a case to be processed; obtaining first damage data of a case to be processed according to the damage assessment image; calling historical claim settlement data corresponding to at least one historical case with similarity higher than a preset value with the first damage data in a preset database based on the first damage data, wherein the historical claim settlement data comprises second damage data and historical claim case data; and carrying out claim settlement on the case to be processed according to the historical claim settlement data. The technology of the invention can find the problem without professional loss assessment knowledge, thereby improving the efficiency and saving the labor and time cost.

Description

Vehicle damage assessment method, device, medium and electronic equipment based on historical claims

Technical Field

The embodiment of the invention relates to the field of electronic information, in particular to a vehicle damage assessment method, device, medium and electronic equipment based on historical claims.

Background

After a traffic accident occurs, it is often necessary to wait for a claimant of an insurance company to go to a field for processing, and to obtain a claim basis by taking a picture or the like. With the recent increase in the amount of motor vehicle retention, the number of traffic accidents per year has been high. And the processing of vehicle claims settlement and damage service often needs to rely on the manpower field processing of professional insurance staff, and is high in cost, long in waiting period and low in processing efficiency.

The damage assessment result of the manual damage assessment is completely obtained by identifying damage assessment personnel, has larger subjectivity and sidedness, is easy to have the deviation of the damage assessment result, and cannot objectively and accurately reflect the damage condition of the vehicle. At present, a large amount of historical claim data is accumulated by insurance companies, and most of the historical claim data is the result of manual damage assessment, and a clean sample can be obtained by a machine and a manual cleaning mode and used for correcting the result of the machine damage assessment.

In the prior art, some technical schemes exist for automatically analyzing and obtaining claims by using traffic accident scene images. However, the prior art still has some problems:

in the prior art, the damage condition of a preset vehicle damage part is determined only according to a damage assessment image in a case to be processed, and a corresponding loss list and a corresponding compensation scheme are provided. Because the restriction of current technology, traffic accident and the high complexity of loss assessment rule, it is great that some loss assessment data and the claim data that analyze out automatically and actual conditions come in and go out to appear that are difficult to avoid, and this kind of condition often needs the manual review of loss assessment personnel to just can discover, and the treatment effeciency is lower to comparatively consume manpower resources.

Disclosure of Invention

In order to solve at least one problem in the background art, the invention provides a vehicle damage assessment method, a device, a medium and an electronic device based on historical claims, which can determine the claim data of a case to be processed by comparing the damage assessment data corresponding to at least one historical case with the historical claim data.

According to one aspect of the invention, a vehicle damage assessment method based on historical claims comprises: acquiring a loss assessment image and accident information of a case to be processed; obtaining first damage data of the case to be processed according to the damage assessment image and the accident information; calling historical claim settlement data corresponding to at least one historical case with similarity higher than a preset value with the first damage data in a preset database based on the first damage data, wherein the historical claim settlement data comprises second damage data and historical claim data; and carrying out claim settlement on the case to be processed according to the historical claim settlement data.

Further optionally, the first impairment data and the second impairment data include at least one piece of sub data, and the sub data includes: at least one of damage assessment image data, image feature data extracted from the damage assessment image, a damaged part of the vehicle determined based on the damage assessment image, and a damage type and/or damage degree identified based on the damaged part of the vehicle; and/or at least one of vehicle information corresponding to the case to be processed, place information of the case to be processed, accident type information of the case to be processed and weather information of the case to be processed when the accident occurs.

Further optionally, the invoking of historical claim data corresponding to at least one historical case in a predetermined database, where similarity of the first damage data is higher than a preset value, based on the first damage data includes: respectively calculating the sub-similarity of the sub-data corresponding to the case to be processed and the sub-data corresponding to each historical case in the preset database; calculating and determining the similarity between the historical claim data corresponding to the historical case and the first damage data of the case to be processed based on the sub-similarity; judging whether the similarity is greater than a preset value or not; and when the similarity is larger than a preset value, calling second damage assessment data and historical claim settlement data corresponding to the historical claim settlement data of the historical case.

Further optionally, the processing the case to be processed according to the historical claim data includes: selecting the historical case with the highest similarity from the historical cases with the similarity larger than a preset value; and taking the historical claim data of the historical case with the highest similarity as the reference data of the claim of the case to be processed.

Further optionally, the processing the claim to be processed case according to the historical claim settlement data further includes: selecting a plurality of historical cases from the historical cases with the similarity greater than a preset value; and taking the average value of the historical claim data of the plurality of historical cases as the reference data of the case claim to be processed.

Further optionally, the taking the average of the claim data of the plurality of historical cases as the reference data of the pending case claim includes: selecting corresponding historical claim settlement data from one or more different historical cases according to the categories of the historical cases; and comprehensively selecting historical claim data of the historical cases of various types, and taking the historical claim data corresponding to the historical claim data as reference data of the claim of the case to be processed.

Further optionally, the processing the claim to be processed case according to the historical claim settlement data further includes: and verifying the reference data by using the historical claim settlement data.

Further optionally, the acquiring the damage assessment image of the case to be processed includes: displaying first prompt information to obtain a loss assessment image, wherein the first prompt information is used for representing the requirement content corresponding to the loss assessment image; judging whether the obtained loss assessment image accords with a shooting reference value or not, and if so, judging that the obtained loss assessment image is the loss assessment image of the case to be processed; and if not, displaying second prompt information and re-acquiring the loss assessment image, wherein the second prompt information is used for indicating the content which needs to be adjusted for acquiring the loss assessment image.

Further optionally, before the first damage data of the case to be processed is obtained according to the damage assessment image and the accident information, the method further includes: identifying the area of a damaged area and the area of an undamaged area in the damage assessment image; calculating the ratio of the area of the damaged area to the area of the undamaged area in the damage assessment image and the number of the damaged areas; judging whether the ratio of the area of the damaged area to the area of the undamaged area in the damage assessment image reaches a preset threshold value and/or judging whether the number of the damaged areas in the damage assessment image reaches the threshold value; if the ratio of the area of the damaged area to the area of the undamaged area in the damage assessment image reaches a preset threshold value or the number of the damaged areas in the damage assessment image reaches a threshold value, the damage assessment image is a medium image, and first damage data of the case to be processed are obtained according to the medium image and the accident information; if the ratio of the area of the damaged area to the area of the undamaged area in the damage assessment image does not reach a preset threshold value and the number of the damaged areas in the damage assessment image does not reach the threshold value, the damage assessment image is a close-range image, and first damage data of the case to be processed are obtained according to the close-range image and the accident information.

According to another aspect of the present invention, a vehicle damage assessment apparatus based on a historical claim, comprises: the acquisition module is used for acquiring the damage assessment image and the accident information of the case to be processed; the calculation module is used for obtaining first damage data of the case to be processed according to the damage assessment image and the accident information; the calling module is used for calling historical claim settlement data corresponding to at least one historical case with similarity higher than a preset value with the first damage data in a preset database based on the first damage data, and the historical claim settlement data comprise second damage assessment data and historical claim data; and the claim case module is used for carrying out claim settlement on the case to be processed according to the historical claim settlement data.

Further optionally, the obtaining module further includes: the first prompt information display submodule is used for displaying first prompt information and acquiring a loss assessment image, and the first prompt information is used for representing the required content corresponding to the loss assessment image; the loss assessment image submodule is used for judging whether the obtained loss assessment image accords with a shooting reference value or not, and if so, judging that the obtained loss assessment image is the loss assessment image of the case to be processed; and the sub-module for displaying second prompt information is used for re-acquiring the loss assessment image if the second prompt information is not displayed, and the second prompt information is used for indicating the content of the loss assessment image which needs to be adjusted.

Further optionally, the apparatus further comprises: the damage assessment image module is used for identifying the area of a damaged area and the area of an undamaged area in the damage assessment image; a damaged region calculation module for calculating a ratio of an area of the damaged region to an area of the undamaged region in the damage assessment image and a number of the damaged regions; a damaged region judging module, configured to judge whether a ratio of an area of a damaged region to an area of an undamaged region in the damage assessment image reaches a preset threshold and/or judge whether the number of damaged regions in the damage assessment image reaches a threshold; if the ratio of the area of the damaged area to the area of the undamaged area in the damage assessment image reaches a preset threshold value and/or the number of the damaged areas in the damage assessment image reaches a threshold value, the damage assessment image is a medium image, and first damage data of the case to be processed are obtained according to the medium image and the accident information; and if the ratio of the area of the damaged area to the area of the undamaged area in the damage assessment image reaches a preset threshold value and/or the number of the damaged areas in the damage assessment image does not reach the threshold value, the damage assessment image is a close-range image, and first damage data of the case to be processed are obtained according to the close-range image and the accident information.

Further optionally, the invoking module further includes: a sub-similarity calculation submodule, configured to calculate sub-similarities between the sub-data corresponding to the to-be-processed case and the sub-data corresponding to each historical case in the predetermined database, respectively; a similarity operator module for determining a similarity between the historical case and the first damage data of the case to be processed based on the sub-similarity calculation; the judgment submodule is used for judging whether the similarity is greater than a preset value; and the calling submodule is used for calling second damage assessment data and historical claim settlement data corresponding to the historical claim settlement data of the historical case when the similarity is larger than a preset value.

Further optionally, the claim module comprises: the highest similarity submodule is used for selecting the historical case with the highest similarity from the historical cases with the similarity larger than a preset value; and taking the historical claim data of the historical case with the highest similarity as the reference data of the claim of the case to be processed. The highest similarity sub-module further comprises: the category selection unit is used for selecting corresponding historical claim data from one or more different historical cases according to the categories of the historical cases; the comprehensive unit is used for comprehensively selecting historical claim data of the historical cases of various types and taking the historical claim data corresponding to the historical claim data as reference data of the case claim to be processed; and the verification unit is used for verifying the reference data by utilizing the historical claim settlement data.

Further optionally, the claim module comprises: the average similarity submodule is used for selecting a plurality of historical cases from the historical cases with the similarity larger than a preset value; and taking the average value of the historical claim data of the plurality of historical cases as the reference data of the case claim to be processed. The category selection unit is used for selecting corresponding historical claim data from one or more different historical cases according to the categories of the historical cases; and the comprehensive unit is used for synthesizing the historical claim data of the selected historical cases in various categories, and taking the historical claim data corresponding to the historical claim data as the reference data of the case claim to be processed. A verification unit for verifying the reference data by using the historical claim data.

According to another aspect of the invention, an electronic device comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the historical claims-based vehicle damage assessment method.

According to another aspect of the invention, a non-transitory storage medium stores computer instructions for causing a computer to perform the historical claims-based vehicle damage assessment method.

The invention has the beneficial effects that:

1. according to the invention, through similarity comparison with the historical cases, the claim data in the historical cases is extracted as reference for damage assessment, so that the risk of error identification is reduced, and the identification accuracy is improved.

2. Aiming at the condition that the damage assessment data and the claim data which are automatically analyzed in the prior art have larger entrance and exit with the actual condition, the invention provides the historical case claim data with the highest similarity and the average value of the historical case claim data with the similarity higher than the threshold as reference data, thereby further improving the case processing efficiency and reducing the investment of human resources.

Drawings

FIG. 1 is a flow chart of a vehicle damage assessment method based on historical claims in an embodiment of the invention;

FIG. 2 is a flow chart illustrating another historical claims-based vehicle damage assessment method in accordance with an embodiment of the present invention;

fig. 3, fig. 4, fig. 5, and fig. 6 respectively show a flowchart of an implementation manner of step 201, step 206, step 207 manner one, and step 207 manner two in embodiment 2 of the present invention;

fig. 7 is a functional structure diagram of a vehicle damage assessment device based on a historical claim.

Detailed Description

The content of the invention will now be discussed with reference to a number of exemplary embodiments. It is to be understood that these examples are discussed only to enable those of ordinary skill in the art to better understand and thus implement the teachings of the present invention, and are not meant to imply any limitations on the scope of the invention.

As used herein, the term "include" and its variants are to be read as open-ended terms meaning "including, but not limited to. The term "based on" is to be read as "based, at least in part, on". The terms "one embodiment" and "an embodiment" are to be read as "at least one embodiment". The term "another embodiment" is to be read as "at least one other embodiment".

Example 1:

as shown in fig. 1, an embodiment of the present invention provides a vehicle damage assessment method based on historical claims, which includes:

101. acquiring a loss assessment image and accident information of a case to be processed;

as an exemplary embodiment, the damage-assessment image includes, for example, a medium-view image and/or a near-view image. The intermediate view image may be obtained by, for example, driving the image capturing device to capture an image, or by selecting a stored image in the storage device according to a user's selection operation. The intermediate view image is an intermediate view image that can reflect the damaged part, for example, an image that can see the entire view of the accident vehicle, for example, an image of the vehicle taken at a first predetermined distance (e.g., 3 meters) from the vehicle.

The close-up image is a close-up image that can clearly reflect the damaged part, for example, a clear picture that can see at least part of the damaged part, such as an image of the vehicle taken at a second predetermined distance (0.5 m or 1 m or other distance) from the vehicle. The close-range image may be obtained by driving the image capturing device to capture an image, or by selecting a stored image in the storage device according to a user's selection operation, for example.

The first and second predetermined distances may be set, for example, empirically or determined experimentally, and will not be described in detail herein.

102. Obtaining first damage data of the case to be processed according to the damage assessment image and the accident information;

103. calling historical claim settlement data corresponding to at least one historical case with similarity higher than a preset value with the first damage data in a preset database based on the first damage data, wherein the historical claim settlement data comprises second damage data and historical claim case data;

in this embodiment, the claim data of the historical case with the highest similarity may be called as the reference data in the predetermined database, or the average value of the historical claim data of a plurality of historical cases with similarity higher than the threshold value may be called as the reference data in the predetermined database.

104. And carrying out claim settlement on the case to be processed according to the historical claim settlement data.

The beneficial effect of this embodiment lies in:

1. through carrying out the similarity comparison with historical case, and then extract the claim data in the historical case and make the reference for the damage assessment, reduced the risk that the misrecognition appears, promoted the rate of accuracy of discernment.

Example 2

As shown in fig. 2, an embodiment of the present invention provides a vehicle damage assessment method based on historical claims, which includes:

201. acquiring a loss assessment image and accident information of a case to be processed;

in some embodiments, as shown in fig. 3, step 201 may be implemented by, but is not limited to, the following processes:

2011. displaying first prompt information to obtain a loss assessment image, wherein the first prompt information is used for representing the required content corresponding to the obtained loss assessment image;

2012. judging whether the acquired loss assessment image meets a shooting reference value or not, and if so, executing a step 2013; if not, go to step 2014;

2013. judging that the obtained loss assessment image is a loss assessment image of a case to be processed;

2014. and displaying second prompt information, and re-acquiring the loss assessment image, wherein the second prompt information is used for indicating the content of the loss assessment image which needs to be adjusted.

202. Identifying the area of a damaged area and the area of an undamaged area in the damage assessment image;

203. calculating the ratio of the area of the damaged area to the area of the undamaged area in the image and the number of the damaged areas;

204. judging whether the ratio of the area of the damaged area to the area of the undamaged area in the damage assessment image reaches a preset threshold value and/or judging whether the number of the damaged areas in the damage assessment image reaches the threshold value; in this embodiment, the preferable determination method is: if yes, that is, the ratio of the area of the damaged region to the area of the undamaged region in the damage assessment image reaches a preset threshold, or the number of the damaged regions in the damage assessment image reaches a threshold, then step 2041 is executed; if not, that is, the ratio of the area of the damaged area to the area of the undamaged area in the damage assessment image reaches the preset threshold or the number of damaged areas in the damage assessment image does not reach the threshold, then step 2042 is executed;

2041. determining that the damage assessment image is a medium image, and obtaining first damage assessment data of the case to be processed according to the medium image and accident information;

2042. and determining the damage assessment image as a close-range image, and obtaining first damage data of the case to be processed according to the close-range image and accident information.

In this embodiment, the method for distinguishing the intermediate view image from the close-up view image includes the following steps: a guiding process is carried out during the acquisition, for example, a user is prompted to acquire a medium/close view image on a screen, and the user correspondingly acquires the medium/close view image according to the qualified image acquired by the prompt; whether the image is qualified or not is judged according to various aspects, such as definition, quality, angle and the like of the image.

When judging whether the loss assessment image extracted from the video is a medium-view image, judging whether the loss assessment image is the medium-view image by the following method: identifying the area of the damaged area and the area of the undamaged area in the image; calculating the ratio of the area of the damaged area to the area of the undamaged area in the image; determining whether the ratio of the area of the damaged area to the area of the undamaged area in the image reaches a preset threshold value; and when the preset threshold value is reached, the image is regarded as a medium scene image.

Or, the medium-view image and the close-view image may be distinguished according to the number of damaged areas in the damage assessment image, and the specific steps include: identifying damaged regions and undamaged regions in the image according to a boundary detection algorithm; if there are multiple damaged areas (for example, two or more damaged areas) in the damaged image, the damaged image is considered to belong to the medium scene image.

In this way, all the loss assessment images (which may be according to the medium/near view categories or the identified vehicle parts, respectively) acquired after the accident are compared with the cases in the historical data, for example, the comparison may be performed through the following steps: extracting the characteristics of all loss assessment images acquired after the accident; performing feature matching according to the extracted features and the images of all cases in the historical cases; it is contemplated herein to compare only historical cases of the same or similar vehicle models.

205. Obtaining first damage data of the case to be processed according to the damage assessment image and the accident information;

and obtaining first damage data of the case to be processed according to the damage assessment image and the accident information. The first impairment data and the second impairment data may comprise at least one seed data, which may comprise one or more of: loss assessment image data of a case to be processed; image characteristic data extracted from the loss assessment image of the case to be processed; determining a damaged part of a vehicle in a case based on a damage assessment image of the case to be processed; and determining the damage type and/or damage degree of each vehicle damaged part in the case based on the damage assessment image of the case to be processed.

For example, the damaged part of the vehicle in the case is determined based on the damage assessment image of the case to be processed: determining at least one complete damaged area in a mesoscopic image in the damage assessment image, identifying vehicle damaged parts corresponding to the at least one complete damaged area respectively and combining the same identification results so as to determine at least one vehicle damaged part in the mesoscopic image according to the combined result.

In addition, the at least one piece of sub data may further optionally include one or more of the following: relevant vehicle information of the case to be processed; location information of cases to be processed; accident type information of cases to be processed; and weather information when an accident of a case to be treated occurs.

The relevant vehicle information includes, for example, a model, a brand, and/or a model of the relevant vehicle; the location information includes the location and/or accident site of the relevant vehicle of the case.

206. Calling historical claim settlement data corresponding to at least one historical case with similarity higher than a preset value with the first damage data in a preset database based on the first damage data, wherein the historical claim settlement data comprises second damage data and historical claim case data;

in some embodiments, as shown in fig. 4, step 206 may be implemented by, but is not limited to, the following process:

2061. respectively calculating the sub-similarity of the sub-data corresponding to the case to be processed and the sub-data corresponding to each historical case in a preset database;

2062. calculating and determining the similarity between the first damage data of the historical case and the historical claim data of the case to be processed based on the sub-similarity;

2063. judging whether the similarity is greater than a preset value; if yes, historical claim data corresponding to the historical case are called, and the historical claim data comprise second damage assessment data and historical claim data.

207. And carrying out claim settlement on the case to be processed according to the historical claim settlement data.

In this embodiment, there are multiple optional ways to claim cases to be processed according to historical claim settlement data, two of which are as follows:

in some embodiments, as shown in fig. 5, step 207 may be implemented by, but is not limited to, the following process:

the first method is as follows:

a2071, selecting corresponding historical claim settlement data from one or more different historical cases according to the types of the historical cases;

a2072, selecting a history case with the highest similarity from the history cases with the similarity larger than a preset value;

a2073, taking the historical claim data of the historical case with the highest similarity as the reference data of the claim of the case to be processed;

and A2074, verifying the reference data by using the historical claim settlement data.

In some embodiments, as shown in fig. 6, step 207 may be implemented by, but is not limited to, the following process:

the second method comprises the following steps:

b2071, selecting corresponding historical claim settlement data from one or more different historical cases according to the types of the historical cases;

b2072, selecting a plurality of historical cases from the historical cases with the similarity greater than the preset value, and comprehensively selecting historical claim settlement data corresponding to the historical cases of various types;

b2073, taking the average value of the historical claim data of the plurality of historical claim data as the reference data of the case claim to be processed;

and B2074, verifying the reference data by using the historical claim settlement data.

It should be noted that, in this embodiment, the way of claim settlement for the case to be processed according to the historical claim settlement data may be the first way, the second way, or both the first way and the second way. More accurate historical claim settlement data can be obtained through the method.

In order to more accurately process the case to be processed, the reference data of the claim of the case to be processed needs to be checked by using the historical case, the historical claim data is compared with all historical cases, and when the maximum value of the similarity is smaller than a certain threshold value, the probability that the damage assessment result appears in history is low, and the case is marked as a suspected damage assessment error case.

In order to process the case to be processed more accurately, the reference data of the case to be processed claim needs to be verified by using the historical case, and the historical case needs to be cleaned before the verification step is started.

A large number of historical cases are accumulated by insurance companies, but the data quality of a part of cases is not high, and particularly, the cases of misjudgment, excessive judgment, missed judgment and the like exist in manual damage assessment results. These cases should be defined as abnormal cases and excluded from the history. Therefore, the historical case needs to be cleaned and processed, abnormal data is removed, and a clean historical case library is obtained for subsequent comparison. The method for determining the abnormal case can be as follows:

1) manual screening mode: each case is marked manually one by one, and abnormal cases are marked as abnormal. But requires a lot of manual experience and a lot of manpower.

2) And (3) sending the result of the artificial marking into a machine learning model, for example, selecting algorithms such as ST L decomposition, CART tree, ARIMA, exponential smoothing, neural network L STM and the like, training an abnormal case detection model, continuously verifying the accuracy of the model by using new data and ensuring that the iterative result of the model is continuously optimized.

The beneficial effect of this embodiment lies in:

Example 3

The embodiment of the invention provides a vehicle damage assessment method based on historical claims, which comprises the following steps: acquiring a loss assessment image of a case to be processed to obtain loss assessment data of the case to be processed according to the loss assessment image; selecting at least one historical case which is most similar to the case to be processed from a predetermined database as a matched case of the case to be processed based on the similarity between the damage data of each historical case and the damage data of the case to be processed in the predetermined database, wherein the predetermined database comprises the damage data and the historical claim data of a plurality of historical cases; and carrying out claim settlement processing on the case to be processed according to the historical claim data of the matched case of the case to be processed.

An exemplary processing flow of the vehicle damage assessment method based on historical claims according to the embodiment of the disclosure may include the following steps:

301. and acquiring the damage assessment image and accident information of the case to be processed.

As an example, the step of acquiring the damage assessment image and accident information of the case to be processed comprises an image acquisition stage and an image classification stage;

302. And obtaining first damage data of the case to be processed according to the damage assessment image and the accident information.

The first impairment data and the second impairment data may comprise at least one seed data, which may comprise one or more of: loss assessment images corresponding to cases; image characteristic data extracted from the loss assessment image of the corresponding case; determining a vehicle damaged part in a case based on a damage assessment image of the corresponding case; and determining the damage type and/or damage degree of each vehicle damaged part in the case based on the damage assessment image of the corresponding case.

For example, the damaged part of the vehicle in the case is determined based on the damage assessment image of the corresponding case: determining at least one complete damaged area in a mesoscopic image in the damage assessment image, identifying vehicle damaged parts corresponding to the at least one complete damaged area respectively and combining the same identification results so as to determine at least one vehicle damaged part in the mesoscopic image according to the combined result.

In addition, the at least one piece of sub data may further optionally include one or more of the following: relevant vehicle information corresponding to the case; location information corresponding to the case; accident type information corresponding to the case; and weather information corresponding to the case when the accident occurs.

The relevant vehicle information includes, for example, a model, a brand, and/or a model of the relevant vehicle; the location information includes the location of the relevant vehicle and/or accident site of the case

303. And calling historical claim settlement data corresponding to at least one historical case with similarity higher than a preset value with the first damage data in a preset database based on the first damage data, wherein the historical claim settlement data comprises second damage data and historical claim case data.

As an exemplary embodiment, calculating the sub-similarity of the sub-data corresponding to the case to be processed and the sub-data corresponding to each historical case in the predetermined database respectively; calculating and determining the similarity between the history case and the case to be processed based on the sub-similarity; judging whether the similarity is greater than a preset value; and when the similarity is greater than a preset value, calling second damage assessment data and historical claim settlement data corresponding to the historical case.

304. And processing the claim case to be processed according to the historical claim data.

Specifically, the process of claim settlement of the case to be processed according to the historical claim data comprises the following steps: and selecting the historical case with the highest similarity from the historical cases with the similarity larger than the preset value, and taking the claim data of the historical case with the highest similarity as the reference data of the claim of the case to be processed. Illustratively, one case which is most similar to the case to be processed is selected from the matched cases of the cases to be processed, and the historical claim data of the case is used as the reference claim data of the case to be processed. In this way, the current case is processed using the claim data of the case that is most similar to the current case (i.e., the case to be processed).

In order to improve the accuracy of claims of cases to be processed, as an exemplary embodiment, the claims of the cases to be processed according to the historical claim data may also be claim data referring to a plurality of historical cases, specifically, a plurality of historical cases are selected from the historical cases with similarity greater than a preset value; and taking the average value of the claim data of the plurality of historical cases as the reference data of the claim of the case to be processed. For example, an average of a plurality (e.g., 10, 5, etc.) of historical claim data of matching cases is used as the reference claim data of the current case.

In addition, in some cases, the types of the claim data of the current case and the matched case may not be completely the same, for example, the current case requires A, B two types of claim data, the matched case may include A, B, C three types of data or more, or a part of the matched case may include a and the other part includes B, so that different claim data may be selected from different historical cases, and after different claim data are integrated, reference claim data is obtained, specifically, corresponding historical claim data is selected from different one or more historical cases according to the type of the claim data; comprehensively selecting various types of historical claim data as reference data of the case claim to be processed. For each item of claim data required by the case to be processed, selecting one or more cases with the claim data from the at least partially matched cases, so as to obtain the claim data of the case to be processed according to the claim data of the one or more cases; and forming reference claim data of the case to be processed by utilizing the obtained claim data of each case to be processed. As an example, obtaining the claim data of the case to be processed from the claim data of the one or more cases includes, for example: and taking the average value of the claim data of the one or more cases as the claim data of the case to be processed.

Comparing the historical claim data with all historical cases, and when the maximum similarity is smaller than a certain threshold, the historical claim data is lower in probability of appearing in history, and the case is marked as a suspected damage-assessment error case.

As an example, the step of acquiring the damage assessment image of the case to be processed comprises an image acquisition stage and an image classification stage; in the image acquisition stage, receiving or acquiring a plurality of images acquired aiming at a vehicle related to a case to be processed; in the image classification stage, a medium view image and a near view image of the case-related vehicle to be processed are determined among the plurality of images received or acquired in the image acquisition stage.

As an example, the image acquisition phase comprises, for example: the method comprises the steps of obtaining a medium-view image and a near-view image of a vehicle related to a case to be processed by driving an image acquisition device to acquire images or acquiring videos, or selecting corresponding frames in a stored image or a stored video in a storage device according to selection operation of a user to be used as the medium-view image and the near-view image of the vehicle related to the case to be processed.

As an example, the image acquisition phase comprises, for example: a medium image acquisition sub-stage, which is suitable for acquiring a medium image of a vehicle related to the case to be processed; and a close-range image acquisition sub-stage, which is suitable for acquiring a close-range image of a vehicle related to the case to be processed.

As an example, the medium image acquisition sub-phase comprises, for example: judging whether the acquired medium view image of the vehicle related to the case to be processed meets the loss assessment requirement: if the loss assessment requirement is met, executing the processing of the close-range image acquisition sub-stage; otherwise, the medium image of the vehicle related to the case to be processed is obtained again until the medium image meets the loss assessment requirement.

For example, if the medium image is complete, the medium image is judged to meet the loss assessment requirement; or if the medium image is complete and the definition of the medium image is higher than or equal to the first preset threshold, judging that the medium image meets the loss assessment requirement.

The first preset threshold may be set according to an empirical value, or determined by an experimental method, for example, and will not be described herein.

As an example, whether the medium view image is complete may be determined as follows: identifying damaged areas and undamaged areas in the medium scene image; calculating the ratio of the area of all damaged areas to the first area of all undamaged areas in the medium scene image; and if the ratio of the first areas is smaller than or equal to a second preset threshold value, judging that the medium scene image is complete.

The second predetermined threshold may be set according to an empirical value, or determined by an experimental method, for example, and will not be described herein.

For example, when the foreground image satisfies any one or more of the following conditions, the foreground image is judged to be complete: the number of damaged areas in the medium scene image is more than 1; the medium image comprises at least one complete damaged area; each damaged area included by the medium scene image is complete; and all the outer sides of the edges of the vehicle area in the middle view image are environment image areas.

As an example, whether the damaged area in the medium view image is complete may be determined, for example, as follows: for each of partial or all damaged areas in the medium view image, judging whether the area outside the edge of the damaged area is an undamaged area: if yes, judging that the damaged area is complete; otherwise, the damaged area is determined to be incomplete.

As an example, whether the damaged area in the medium view image is complete may be determined, for example, as follows: for each of a part or all of the damaged area in the intermediate view image, determining whether an edge of the damaged area at least partially coincides with an image boundary of the intermediate view image: if yes, judging that the damaged area is incomplete; otherwise, the damaged area is judged to be complete.

As an example, the close-up image acquisition sub-phase comprises, for example: judging whether the acquired close-range image of the vehicle related to the case to be processed meets the loss assessment requirement: if the loss assessment requirement is met, processing in an image classification stage is executed; otherwise, the close-range image of the vehicle related to the case to be processed is obtained again until the close-range image meets the loss assessment requirement.

As an example, the determining whether the acquired close-range image of the vehicle related to the case to be processed meets the damage assessment requirement includes: aiming at each acquired close-range image of the vehicle related to the case to be processed, based on at least one damaged part of the vehicle related to the case to be processed, determining the damaged part of the vehicle corresponding to the close-range image: if the damaged part of the vehicle corresponding to the close-range image does not exist in the damaged part of the at least one vehicle, determining that the close-range image does not meet the damage assessment requirement.

As an example, the determining whether the acquired close-range image of the vehicle related to the case to be processed meets the damage assessment requirement includes: and if the definition of the close-range image is lower than a preset third preset threshold, judging that the close-range image does not meet the loss assessment requirement.

The third preset threshold may be set according to an empirical value, or determined by an experimental method, for example, and will not be described herein.

As an example, the image classification phase comprises, for example: for each of a plurality of images received or acquired by the image acquisition stage: identifying damaged regions and undamaged regions in the image; calculating the ratio of the area of all damaged areas to the second area of all undamaged areas in the image; and if the ratio of the second areas reaches a second preset threshold value, determining that the image is a medium image of the vehicle related to the case to be processed.

As an example, the image classification phase comprises, for example: for each of a plurality of images received or acquired by the image acquisition stage: identifying damaged regions and undamaged regions in the image; and if the number of the identified damaged areas in the image is larger than 1, determining that the image is a medium scene image of the vehicle related to the case to be processed.

As an example, the method may further include: and judging whether the medium view image and/or the close view image of the vehicle related to the case to be processed, which are determined in the image classification stage, meet the damage assessment requirement.

For example, in the image acquisition stage, first prompt information may be output to prompt a user to acquire or select an image meeting the loss assessment requirement as a corresponding loss assessment image through the first prompt information; the first prompt message includes display information and/or sound information, wherein the display information includes any one or more of images, texts, videos and animations.

As an example, a real-time image acquired by the image acquisition apparatus may be displayed using a predetermined display screen, and display information may be displayed in a predetermined area of the predetermined display screen, for example.

As an example, a real-time image captured by an image capturing device is displayed in the entire display area of a predetermined display screen, for example, and display information floating above the real-time image is displayed at a corresponding position of the real-time image.

For example, the content of the first prompt message may include: the content is used for representing the loss assessment requirement corresponding to the loss assessment image; and/or contents of a photographing position reference value and/or a photographing parameter reference value for indicating a user operating the image capturing apparatus, wherein the photographing parameter reference value includes any one or more of a corresponding photographing angle reference value, aperture reference value, and shutter reference value.

As an example, if the acquired loss assessment image does not meet the loss assessment requirement, second prompt information may be output to prompt the user to adjust the shooting position and/or the shooting parameters through the second prompt information to reacquire the required loss assessment image; wherein, the shooting parameters comprise any one or more of corresponding shooting angles, apertures and shutters.

As an example, the step of prompting the user to adjust the shooting position and/or the shooting parameters through the second prompt message to reacquire the required damage image includes, for example: acquiring the shooting position and/or shooting parameters of the acquired loss assessment image; and determining the adjustment operation required by the user according to the shooting position and/or shooting parameter of the acquired loss assessment image and the corresponding shooting position reference value and/or shooting parameter reference value.

As an example, during the acquisition of the required damage assessment image by the image acquisition device, for example, the current shooting position and/or shooting parameters may be acquired in real time; and determining the current required adjustment operation in real time according to the current shooting position and/or shooting parameters and the shooting position reference value and/or shooting parameter reference value corresponding to the required damage assessment image so as to instruct a user to perform corresponding adjustment.

As an example, during the acquisition of the required damage assessment image by the image acquisition device, for example, the current shooting position and/or shooting parameters may be acquired in real time; and determining the current required adjustment operation in real time according to the current shooting position and/or shooting parameters and the shooting position reference value and/or shooting parameter reference value corresponding to the required loss image so as to perform corresponding automatic adjustment until the distance between the current shooting position and/or shooting parameters and the shooting position reference value and/or shooting parameter reference value corresponding to the required loss image is smaller than a preset difference value.

The preset difference may be set based on an empirical value, or determined by a test method, for example, and will not be described herein.

As an example, the adjustment operation includes, for example: the adjustment trend of the shooting position and/or the shooting parameter; and/or the adjustment operation further includes an adjustment amount of the photographing position and/or the photographing parameter.

As an example, the step of performing claim processing on the case to be processed includes displaying the following information: and the related information of the matched case of the case to be processed at least comprises the claim data.

The beneficial effect of this embodiment lies in:

Example 4

An exemplary processing device of the vehicle damage assessment method based on historical claims according to the embodiment of the disclosure, as shown in fig. 7, may include the following devices:

a vehicle damage assessment apparatus based on historical claims, comprising:

an obtaining module 401, configured to obtain a damage assessment image and accident information of a case to be processed; the acquisition module further comprises:

the display first prompt information submodule 4011 is configured to obtain a loss assessment image, where the first prompt information is used to indicate demand content corresponding to the obtained loss assessment image;

the damage assessment image sub-module 4012 judges whether the obtained damage assessment image meets the shooting reference value, if so, the obtained damage assessment image is determined to be a damage assessment image of the case to be processed;

and a second prompt information sub-module 4013 is displayed, the loss assessment image is obtained again, and the second prompt information is used for indicating the content of the loss assessment image which needs to be adjusted.

An identifying impairment image module 402 for identifying an area of a damaged region and an area of an undamaged region in an impairment image;

a damaged region calculation module 403, configured to calculate a ratio of an area of a damaged region to an area of an undamaged region in the image and a number of damaged regions;

a damaged region determining module 404, configured to determine whether a ratio of an area of a damaged region to an area of an undamaged region in the damaged image reaches a preset threshold and/or determine whether the number of damaged regions in the damaged image reaches a threshold; if so, the loss assessment image is a medium scene image, and first loss assessment data of the case to be processed is obtained according to the medium scene image and accident information; if not, the damage assessment image is a close-range image, and first damage assessment data of the case to be processed is obtained according to the close-range image and accident information.

The calculation module 405 is configured to obtain first damage data of the case to be processed according to the damage assessment image and the accident information; namely, first damage data of the case to be processed is obtained according to the medium-view image and the accident information or the first damage data of the case to be processed is obtained according to the close-view image and the accident information.

The calling module 406 is configured to call, based on the first damage data, second damage data and historical claim data, which correspond to at least one historical case in the predetermined database, where similarity of the first damage data and the historical case is higher than a preset value; the retrieval module further comprises:

the sub-similarity degree operator module 4061 is used for respectively calculating the sub-similarity degree of the sub-data corresponding to the case to be processed and the sub-data corresponding to each historical case in the preset database;

a similarity operator module 4062, configured to determine a similarity between the history case and the case to be processed based on the sub-similarity calculation;

a judging submodule 4063, configured to judge whether the similarity is greater than a preset value;

and the calling submodule 4064 is used for calling the second damage assessment data and the historical claims data corresponding to the historical case when the similarity is greater than the preset value.

The claim case module 407 is configured to claim cases to be processed according to the historical claim case data. The claim module comprises:

a highest similarity submodule 4071, configured to select a history case with the highest similarity from the history cases with the similarity greater than a preset value; and taking the claim data of the historical case with the highest similarity as the reference data of the claim of the case to be processed. The highest similarity sub-module further comprises:

a verification unit 40711 for verifying the reference data with the historical claim data.

The claim module 407 further includes: an average similarity submodule 4072, configured to select multiple history cases from the history cases with similarity greater than a preset value; and taking the average value of the claim data of the plurality of historical cases as the reference data of the claim of the case to be processed. The average similarity submodule includes:

a category selection unit 40721 that selects corresponding historical claim data from different one or more historical cases according to the category of the claim data;

a synthesizing unit 40722 for synthesizing the selected various types of historical claim data as reference data of the case claim to be processed.

A verification unit 40723 for verifying the reference data with the historical claim data.

A claim settlement module 408 for displaying the claim settlement data.

The beneficial effect of this embodiment lies in:

Example 5

An exemplary processing device of the vehicle damage assessment method based on the historical claims according to the embodiment of the disclosure may include the following devices: an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor when executing the program implementing the historical claims-based vehicle damage assessment method of the present invention.

Example 6

An exemplary processing device of the vehicle damage assessment method based on the historical claims according to the embodiment of the disclosure may include the following devices: a non-transitory storage medium storing computer instructions for causing a computer to perform the historical claims-based vehicle damage assessment method of the present invention.

Those of ordinary skill in the art will appreciate that the various illustrative modules and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and devices may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and in actual implementation, there may be other divisions, for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.

In addition, functional modules in the embodiments of the present invention may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module.

The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method for transmitting/receiving the power saving signal according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by a person skilled in the art that the scope of the invention as referred to in the present application is not limited to the embodiments with a specific combination of the above-mentioned features, but also covers other embodiments with any combination of the above-mentioned features or their equivalents without departing from the inventive concept. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.

It should be understood that the order of execution of the steps in the summary of the invention and the embodiments of the present invention does not absolutely imply any order of execution, and the order of execution of the steps should be determined by their functions and inherent logic, and should not be construed as limiting the process of the embodiments of the present invention.

Claims

1. A vehicle damage assessment method based on historical claims is characterized by comprising the following steps:

acquiring a loss assessment image and accident information of a case to be processed;

obtaining first damage data of the case to be processed according to the damage assessment image and the accident information;

calling historical claim settlement data corresponding to at least one historical case with similarity higher than a preset value with the first damage data in a preset database based on the first damage data, wherein the historical claim settlement data comprises second damage data and historical claim data;

and carrying out claim settlement on the case to be processed according to the historical claim settlement data.

2. The historical claims-based vehicle damage assessment method according to claim 1, wherein said first damage data and said second damage data comprise at least one sub-data, said sub-data comprising:

at least one of damage assessment image data, image feature data extracted from a damage assessment image, a damaged part of a vehicle determined based on the damage assessment image, and a damage type and/or damage degree identified based on the damaged part of the vehicle;

and/or the presence of a gas in the gas,

at least one of vehicle information corresponding to the case to be processed, place information of the case to be processed, accident type information of the case to be processed and weather information of the case to be processed when an accident occurs.

3. The vehicle damage assessment method based on historical claims according to claim 2, wherein the retrieving historical claim data corresponding to at least one historical case in a predetermined database, the similarity of which to the first damage data is higher than a preset value, based on the first damage data comprises:

respectively calculating the sub-similarity of the sub-data corresponding to the case to be processed and the sub-data corresponding to each historical case in the preset database;

calculating and determining the similarity between the historical claim data corresponding to the historical case and the first damage data of the case to be processed based on the sub-similarity;

judging whether the similarity is greater than a preset value or not;

and when the similarity is larger than a preset value, calling second damage assessment data and historical claim data corresponding to the historical claim data of the historical case.

4. The vehicle damage assessment method based on historical claims according to claim 1, wherein said filing said pending cases according to said historical filing data comprises:

selecting the historical case with the highest similarity from the historical cases with the similarity larger than a preset value;

and taking the historical claim data of the historical case with the highest similarity as the reference data of the claim of the case to be processed.

5. The vehicle damage assessment method based on historical claims according to claim 1, wherein said filing said pending case according to said historical claims data further comprises:

selecting a plurality of historical cases from the historical cases with the similarity greater than a preset value;

and taking the average value of the historical claim data of the plurality of historical cases as the reference data of the case claim to be processed.

6. The historical claims-based vehicle damage assessment method according to claim 5, wherein said taking the average of the historical claims data of said plurality of historical cases as the reference data of said pending cases comprises:

selecting corresponding historical claim settlement data from one or more different historical cases according to the categories of the historical cases;

and comprehensively selecting historical claim data of the historical cases of various types, and taking the historical claim data corresponding to the historical claim data as reference data of the claim of the case to be processed.

7. The historical claims-based vehicle damage assessment method according to any one of claims 4-6, wherein said settling said pending cases according to said historical claims data further comprises:

and verifying the reference data by using the historical claim settlement data.

8. The historical claims-based vehicle damage assessment method according to any one of claims 1-6, wherein said obtaining a damage assessment image of a case to be processed comprises:

displaying first prompt information to obtain a loss assessment image, wherein the first prompt information is used for representing the requirement content corresponding to the loss assessment image;

judging whether the acquired loss assessment image accords with a shooting reference value or not;

if so, judging that the acquired loss assessment image is the loss assessment image of the case to be processed;

and if not, displaying second prompt information and re-acquiring the loss assessment image, wherein the second prompt information is used for indicating the content which needs to be adjusted for acquiring the loss assessment image.

9. The historical claims-based vehicle damage assessment method according to claim 1, wherein before obtaining the first damage data of the case to be processed according to the damage assessment image and the accident information, the method further comprises:

identifying the area of a damaged area and the area of an undamaged area in the damage assessment image;

calculating the ratio of the area of the damaged area to the area of the undamaged area in the damage assessment image and the number of the damaged areas;

judging whether the ratio of the area of the damaged area to the area of the undamaged area in the damage assessment image reaches a preset threshold or whether the number of the damaged areas in the damage assessment image reaches the threshold;

if the ratio of the area of the damaged area to the area of the undamaged area in the damage assessment image reaches a preset threshold value or the number of the damaged areas in the damage assessment image reaches a threshold value, the damage assessment image is a medium image, and first damage data of the case to be processed are obtained according to the medium image and the accident information;

if the ratio of the area of the damaged area to the area of the undamaged area in the damage assessment image does not reach a preset threshold value and the number of the damaged areas in the damage assessment image does not reach the threshold value, the damage assessment image is a close-range image, and first damage data of the case to be processed are obtained according to the close-range image and the accident information.

10. A vehicle damage assessment device based on historical claims, comprising:

the acquisition module is used for acquiring the damage assessment image and the accident information of the case to be processed;

the calculation module is used for obtaining first damage data of the case to be processed according to the damage assessment image and the accident information;

the calling module is used for calling historical claim settlement data corresponding to at least one historical case with similarity higher than a preset value with the first damage data in a preset database based on the first damage data, and the historical claim settlement data comprise second damage assessment data and historical claim data;

and the claim case module is used for carrying out claim settlement on the case to be processed according to the historical claim settlement data.

11. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor when executing the program implementing the historical claims-based vehicle damage assessment method of any one of claims 1-9.

12. A non-transitory storage medium storing computer instructions for causing a computer to perform the historical claims-based vehicle damage assessment method of any one of claims 1-9.