A method and system for remote vehicle valuation

Abstract

The present invention discloses a method and system for remote vehicle valuation, including: receiving vehicle information sent by a user end; calling a corresponding vehicle decomposition model in a preset model library according to the vehicle information; determining the attribute information of key components of the vehicle according to the vehicle decomposition model; determining a corresponding guidance method according to the attribute information of the key components, and sending the guidance method to the user end for display; receiving the status information of the key components uploaded by the user end based on the guidance method; updating the vehicle decomposition model according to the status information to obtain a static model; valuing the vehicle according to the static model, obtaining the valuation result and displaying it. The vehicle can be accurately valued, the efficiency and accuracy of the valuation can be improved, and the user experience can be improved at the same time.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle evaluation, and in particular to a method and system for remote vehicle evaluation. Background Art

[0002] At present, with the development of the automobile market, the transaction volume of used cars is also increasing year by year. The traditional used car evaluation method requires professional appraisers to conduct on-site inspections and evaluations, which is not only time-consuming and labor-intensive, but also easily affected by subjective factors. Some automated evaluation methods in the prior art also have problems of inaccurate evaluation and poor user experience. Therefore, there is an urgent need for a method and system that can provide accurate and convenient remote automobile valuation to improve evaluation efficiency and user satisfaction. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems in the above-mentioned technology to a certain extent. To this end, the first object of the present invention is to provide a method for remote vehicle valuation, which can accurately value the vehicle, improve the efficiency and accuracy of the valuation, and improve the user experience.

[0004] A second object of the present invention is to provide a system for remote vehicle valuation.

[0005] To achieve the above object, a first embodiment of the present invention provides a method for remote vehicle valuation, comprising:

[0006] Receive vehicle information sent by the user;

[0007] Calling the corresponding vehicle decomposition model in the preset model library according to the vehicle information;

[0008] Determine the attribute information of key components of the vehicle based on the vehicle decomposition model;

[0009] Determine the corresponding guidance method according to the attribute information of the key components, and send the guidance method to the user end for display;

[0010] Receive status information of key components uploaded by the user based on the guidance method;

[0011] The vehicle decomposition model is updated according to the state information to obtain a static model;

[0012] The vehicle is valued based on the static model, and the valuation result is obtained and displayed.

[0013] According to some embodiments of the present invention, the vehicle information includes the brand, model and production year of the vehicle.

[0014] According to some embodiments of the present invention, the guidance method includes video guidance, outline guidance and text guidance; wherein,

[0015] Video guidance involves playing pre-recorded demonstration videos on how to photograph specific vehicle areas;

[0016] Contour guidance includes displaying contour images of vehicle parts on the user's screen and prompting the user to take photos at specific locations;

[0017] The text guidance includes providing the user with detailed text instructions for photographing vehicle parts.

[0018] According to some embodiments of the present invention, the state information is image information;

[0019] Before updating the vehicle decomposition model according to the state information, the image information is associated with the corresponding decomposition module included in the vehicle decomposition model.

[0020] According to some embodiments of the present invention, before associating the image information with the corresponding decomposition module included in the vehicle decomposition model, the process includes:

[0021] Divide the image information into several sub-images;

[0022] Calculate the signal-to-noise ratio of each sub-image, calculate the average signal-to-noise ratio, and compare it with a preset signal-to-noise ratio threshold;

[0023] When it is determined that the average signal-to-noise ratio is less than a preset signal-to-noise ratio threshold, image enhancement processing is performed on the image information.

[0024] According to some embodiments of the present invention, performing image enhancement processing on image information includes:

[0025] Obtain the channel values ​​of each pixel in the image information in the R channel, the G channel, and the B channel, and determine the maximum channel value of the same pixel as the target feature value, and generate a target image based on the pixels with the target feature value;

[0026] The target image is divided into several sub-target images, and the sub-target image in the central area of ​​the target image is used as the standard image;

[0027] Calculate the average standard feature value of the standard image, query a preset average standard feature value-enhancement coefficient data table according to the average standard feature value, and determine a number of target enhancement coefficients based on different distances from the standard image;

[0028] Calculate the distance information between the standard image and the sub-target image;

[0029] Determine a corresponding enhancement coefficient among a plurality of target enhancement coefficients according to distance information between the standard image and the sub-target image;

[0030] Calculate the average eigenvalue of other sub-target images except the standard image; enhance the average eigenvalue according to the corresponding enhancement coefficient of the sub-target image to obtain an enhanced image.

[0031] According to some embodiments of the present invention, evaluating a vehicle according to a static model, obtaining and displaying an evaluation result, includes:

[0032] Determine the wear information of each key component in the static model; compare the wear information of each key component with the corresponding preset wear threshold, and determine the valuation data of each key component based on the comparison; determine the static valuation result of the vehicle based on the valuation data of each key component;

[0033] Configure several preset operation scenarios; execute the preset operation scenarios respectively based on the static model to obtain the operation status data corresponding to each preset operation scenario; analyze the operation status data to determine the operation characteristic parameters; input the operation characteristic parameters into the pre-trained regression model; classify and identify the operation characteristic parameters and perform compensation processing according to the regression model to obtain the motion performance value under the preset operation scenario; compare the motion performance value under each preset operation scenario with the preset motion performance threshold value under the corresponding scenario, and determine the dynamic sub-valuation result of the vehicle according to the comparison result; calculate the dynamic valuation result of the vehicle according to the dynamic sub-valuation results of several vehicles;

[0034] Based on the static valuation result of the vehicle and the dynamic sub-valuation result of the vehicle, the valuation result is determined and displayed.

[0035] According to some embodiments of the present invention, before associating the image information with the corresponding decomposition module included in the vehicle decomposition model, the method further includes:

[0036] Segment the image information to obtain several regional images;

[0037] Performing fast Fourier transform processing on the plurality of regional images to convert the regional images from the spatial domain to the frequency domain to obtain a frequency spectrum representation of each regional image;

[0038] Determine the high-frequency components according to the frequency spectrum representation of each regional image to obtain a high-frequency image;

[0039] The high frequency image is associated with a corresponding decomposition module included in the vehicle decomposition model.

[0040] According to some embodiments of the present invention, the preset operation scenarios are respectively executed based on the static model to obtain the operation status data corresponding to each preset operation scenario; including:

[0041] Identify the management components and execution components in the static model;

[0042] Get the attribute information of the execution component;

[0043] According to the attribute information of the execution components, the execution components are classified to obtain a plurality of classification sets; a target classification set is determined, and the target classification set includes at least two execution components;

[0044] Based on the control strategy of the execution layer, a first association relationship is established between each execution component in the target classification set; and an association system of the execution layer is constructed according to the association relationship;

[0045] Based on the control strategy of the management layer, a second association relationship between the management component and the association system is established to establish a control relationship between the management component and the execution component;

[0046] The management component determines the target execution component according to the preset operation scenario based on the control relationship; executes the preset operation scenario according to the target execution component, and collects the operation data of each target execution component as the operation status data corresponding to the preset operation scenario.

[0047] To achieve the above object, a second embodiment of the present invention provides a system for remote vehicle valuation, comprising:

[0048] A first receiving module, used for receiving vehicle information sent by a user terminal;

[0049] A calling module, used to call the corresponding vehicle decomposition model in the preset model library according to the vehicle information;

[0050] A first determination module is used to determine attribute information of key components of the vehicle according to the vehicle decomposition model;

[0051] The second determination module is used to determine the corresponding guidance method according to the attribute information of the key components, and send the guidance method to the user end for display;

[0052] The second receiving module is used to receive the status information of key components uploaded by the user end based on the guidance method;

[0053] An updating module, used for updating the vehicle decomposition model according to the state information to obtain a static model;

[0054] The valuation module is used to value the vehicle based on the static model, obtain the valuation result and display it.

[0055] The present invention proposes a method and system for remote vehicle valuation, which calls a corresponding vehicle decomposition model in a preset model library according to vehicle information, guides users to upload status information of corresponding key components, updates the vehicle decomposition model according to the status information, obtains a static model, determines an estimated vehicle model for the vehicle to be valued, values ​​the vehicle based on the static model, estimates the vehicle from the system as a whole, improves the efficiency and accuracy of the valuation, and further improves the user experience.

[0056] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0057] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0059] Figure 1 is a flow chart of a method for remote vehicle valuation according to one embodiment of the present invention;

[0060] Figure 2 The invention is a block diagram of a system for remote vehicle valuation according to an embodiment of the present invention. DETAILED DESCRIPTION

[0061] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0062] like Figure 1 As shown, the first embodiment of the present invention proposes a method for remote vehicle valuation, including steps S1-S7:

[0063] S1. Receive vehicle information sent by the user terminal;

[0064] S2. Calling a corresponding vehicle decomposition model in a preset model library according to vehicle information;

[0065] S3. Determine attribute information of key components of the vehicle according to the vehicle decomposition model;

[0066] S4. Determine a corresponding guidance method according to the attribute information of the key components, and send the guidance method to the user end for display;

[0067] S5, receiving the status information of key components uploaded by the user end based on the guidance method;

[0068] S6. Update the vehicle decomposition model according to the state information to obtain a static model;

[0069] S7. Evaluate the vehicle according to the static model, obtain the valuation result and display it.

[0070] Working principle of the above technical solution: In this embodiment, the preset model library is a database of preset vehicle decomposition models, including models of vehicles of different years and models, including cars, trucks, etc. The vehicle decomposition model includes multiple set decomposition modules, each of which corresponds to a part of the vehicle. The attribute information of key components is to describe the specific characteristics of key components. Key components include engines, motors, three-way catalysts, etc.

[0071] In this embodiment, the corresponding guidance method is determined according to the attribute information of the key components, and the guidance method is sent to the user end for display, so that the user can upload the corresponding data according to the corresponding guidance.

[0072] In this embodiment, the vehicle decomposition model is updated according to the state information to obtain a static model, the state information is annotated in the vehicle decomposition model and updated, and an estimated vehicle model representing the vehicle to be estimated is obtained based on the static model.

[0073] The beneficial effects of the above technical solution are as follows: calling the corresponding vehicle decomposition model in the preset model library according to the vehicle information, guiding the user to upload the status information of the corresponding key components, updating the vehicle decomposition model according to the status information, obtaining a static model, determining an estimated vehicle model for the vehicle to be estimated, estimating the vehicle based on the static model, estimating the vehicle from the system as a whole, improving the efficiency and accuracy of the valuation, and thereby improving the user experience.

[0074] According to some embodiments of the present invention, the vehicle information includes the brand, model and production year of the vehicle.

[0075] According to some embodiments of the present invention, the guidance method includes video guidance, outline guidance and text guidance; wherein,

[0076] Video guidance involves playing pre-recorded demonstration videos on how to photograph specific vehicle areas;

[0077] Contour guidance includes displaying contour images of vehicle parts on the user's screen and prompting the user to take photos at specific locations;

[0078] The text guidance includes providing the user with detailed text instructions for photographing vehicle parts.

[0079] According to some embodiments of the present invention, the state information is image information;

[0080] Before updating the vehicle decomposition model according to the state information, the image information is associated with the corresponding decomposition module included in the vehicle decomposition model.

[0081] The working principle and beneficial effects of the above technical solution: the corresponding decomposition module included in the vehicle decomposition model is a key component of the vehicle, and an association is established with the key component based on the image information, so as to facilitate better evaluation of the corresponding key component.

[0082] According to some embodiments of the present invention, before associating the image information with the corresponding decomposition module included in the vehicle decomposition model, the process includes:

[0083] Divide the image information into several sub-images;

[0084] Calculate the signal-to-noise ratio of each sub-image, calculate the average signal-to-noise ratio, and compare it with a preset signal-to-noise ratio threshold;

[0085] When it is determined that the average signal-to-noise ratio is less than a preset signal-to-noise ratio threshold, image enhancement processing is performed on the image information.

[0086] The working principle and beneficial effects of the above technical solution are as follows: the image information is divided into several sub-images; the signal-to-noise ratios of the sub-images are calculated respectively, the average signal-to-noise ratio is calculated, and compared with the preset signal-to-noise ratio threshold; when it is determined that the average signal-to-noise ratio is less than the preset signal-to-noise ratio threshold, the image information is enhanced to improve the accuracy of the image.

[0087] According to some embodiments of the present invention, performing image enhancement processing on image information includes:

[0088] Obtain the channel values ​​of each pixel in the image information in the R channel, the G channel, and the B channel, and determine the maximum channel value of the same pixel as the target feature value, and generate a target image based on the pixels with the target feature value;

[0089] The target image is divided into several sub-target images, and the sub-target image in the central area of ​​the target image is used as the standard image;

[0090] Calculate the average standard feature value of the standard image, query a preset average standard feature value-enhancement coefficient data table according to the average standard feature value, and determine a number of target enhancement coefficients based on different distances from the standard image;

[0091] Calculate the distance information between the standard image and the sub-target image;

[0092] Determine a corresponding enhancement coefficient among a plurality of target enhancement coefficients according to distance information between the standard image and the sub-target image;

[0093] Calculate the average eigenvalue of other sub-target images except the standard image; enhance the average eigenvalue according to the corresponding enhancement coefficient of the sub-target image to obtain an enhanced image.

[0094] The working principle and beneficial effects of the above technical solution are as follows: the channel values ​​of each pixel in the image information in the R channel, the G channel and the B channel are obtained, and the maximum channel value of the same pixel is determined as the target characteristic value, and the target image is generated according to the pixel with the target characteristic value; the target image is divided into several sub-target images, and the sub-target image in the central area of ​​the target image is used as the standard image; the average standard characteristic value of the standard image is calculated, and the preset average standard characteristic value-enhancement coefficient data table is queried according to the average standard characteristic value to determine several target enhancement coefficients based on different distances from the standard image; the distance information between the standard image and the sub-target image is calculated; the corresponding enhancement coefficient among several target enhancement coefficients is determined according to the distance information between the standard image and the sub-target image; the average characteristic value of other sub-target images except the standard image is calculated; the average characteristic value is enhanced according to the corresponding enhancement coefficient of the sub-target image to obtain an enhanced image. It is convenient to enhance other sub-target images with the standard image as a reference, so as to improve the efficiency and accuracy of image enhancement.

[0095] According to some embodiments of the present invention, evaluating a vehicle according to a static model, obtaining and displaying an evaluation result, includes:

[0096] Determine the wear information of each key component in the static model; compare the wear information of each key component with the corresponding preset wear threshold, and determine the valuation data of each key component based on the comparison; determine the static valuation result of the vehicle based on the valuation data of each key component;

[0097] Configure several preset operation scenarios; execute the preset operation scenarios respectively based on the static model to obtain the operation status data corresponding to each preset operation scenario; analyze the operation status data to determine the operation characteristic parameters; input the operation characteristic parameters into the pre-trained regression model; classify and identify the operation characteristic parameters and perform compensation processing according to the regression model to obtain the motion performance value under the preset operation scenario; compare the motion performance value under each preset operation scenario with the preset motion performance threshold value under the corresponding scenario, and determine the dynamic sub-valuation result of the vehicle according to the comparison result; calculate the dynamic valuation result of the vehicle according to the dynamic sub-valuation results of several vehicles;

[0098] Based on the static valuation result of the vehicle and the dynamic sub-valuation result of the vehicle, the valuation result is determined and displayed.

[0099] The working principle of the above technical solution: In this embodiment, each key component should have a preset wear threshold, which is based on the manufacturer's recommendations, industry standards or professional assessments. The collected wear information of each component is compared with these preset thresholds, and the impact of each component on the overall value of the vehicle can be evaluated based on the comparison results of the wear degree of the component and the preset threshold. If the component is severely worn, it may require higher repair or replacement costs, which will reduce its value in the vehicle valuation. On the contrary, if the component is in good condition, its valuation will be higher. The valuation data of all key components are combined, considering their impact on the overall value of the vehicle, and determining the static valuation result of the vehicle; the static valuation result is the valuation information given to the key components of the vehicle themselves.

[0100] In this embodiment, the preset operation scenarios should cover various typical working conditions that the vehicle may encounter, including but not limited to: cruising on highways, urban road congestion, climbing mountain roads, emergency braking and acceleration, driving on slippery roads, idling for a long time, etc. Each scenario should contain specific operating parameters, such as speed, acceleration, braking force, steering angle, road conditions, etc. The static model of the vehicle is used to simulate the vehicle behavior in each preset operation scenario. By inputting the corresponding operation parameters, the model will output the corresponding operation status data, including but not limited to vehicle speed, acceleration, energy consumption, component load, etc. The operation status data obtained from the static model is deeply analyzed to extract the characteristic parameters that have an important impact on the evaluation of the vehicle's dynamic performance. These characteristic parameters include: maximum / average speed, acceleration / deceleration time, energy efficiency, component stress peak, stability index (such as sideslip angle, yaw rate); the extracted operation characteristic parameters are used as input and passed to the pre-trained regression model. This regression model should be able to predict or evaluate the performance of the vehicle in different operation scenarios based on the input characteristic parameters. The regression model not only predicts, but also classifies and identifies to distinguish different performance levels or problem categories. At the same time, the model also performs compensation processing to correct the prediction deviation caused by model errors or external interference. After being processed by the regression model, the vehicle's sports performance values ​​for each preset operating scenario are obtained. These values ​​quantify the performance of the vehicle under different working conditions. Set corresponding sports performance thresholds for each preset operating scenario. Compare the actual sports performance values ​​with these thresholds to evaluate whether the performance of the vehicle in different scenarios is up to standard or excellent. Based on the comparison results, a dynamic sub-valuation result is assigned to the vehicle performance in each preset operating scenario. These sub-valuation results reflect the dynamic value of the vehicle under different working conditions. Finally, all dynamic sub-valuation results are combined, and the overall dynamic valuation result of the vehicle is calculated using weighted average or other appropriate algorithms. This result comprehensively considers the performance of the vehicle in different operating scenarios and provides a comprehensive evaluation of the dynamic value of the vehicle. The dynamic sub-valuation result is the valuation information for determining the vehicle under dynamic driving.

[0101] Based on the static valuation result of the vehicle and the dynamic sub-valuation result of the vehicle, a weighted average method can be used to determine the final valuation result and display it.

[0102] The beneficial effects of the above technical solution are: static and dynamic evaluation of the vehicle is carried out to facilitate accurate determination of the final valuation result.

[0103] According to some embodiments of the present invention, before associating the image information with the corresponding decomposition module included in the vehicle decomposition model, the method further includes:

[0104] Segment the image information to obtain several regional images;

[0105] Performing fast Fourier transform processing on the plurality of regional images to convert the regional images from the spatial domain to the frequency domain to obtain a frequency spectrum representation of each regional image;

[0106] Determine the high-frequency components according to the frequency spectrum representation of each regional image to obtain a high-frequency image;

[0107] The high frequency image is associated with a corresponding decomposition module included in the vehicle decomposition model.

[0108] The working principle and beneficial effects of the above technical solution are as follows: Segmentation is performed based on image segmentation methods based on image content, color, texture or other features, and the image segmentation methods include threshold segmentation, edge detection, region growing, level set method, etc. Fast Fourier transform (FFT) is applied to each segmented regional image, and in the frequency domain, the image is represented as a series of frequency components and corresponding amplitudes (or energy). The purpose of this step is to reveal the frequency components in the image, and the high-frequency part contains the details and edge information of the image. By applying a high-pass filter (or simply setting a threshold to retain the high-frequency components), high-frequency components can be extracted from the spectrum of each regional image. These high-frequency components are then converted back to the spatial domain to form a high-frequency image. The high-frequency image of each region is associated with the corresponding decomposition module of the vehicle decomposition model, which facilitates the association of key information with the corresponding decomposition module of the vehicle decomposition model, reduces the amount of data processing, and improves data processing efficiency.

[0109] According to some embodiments of the present invention, the preset operation scenarios are respectively executed based on the static model to obtain the operation status data corresponding to each preset operation scenario; including:

[0110] Identify the management components and execution components in the static model;

[0111] Get the attribute information of the execution component;

[0112] According to the attribute information of the execution components, the execution components are classified to obtain a plurality of classification sets; a target classification set is determined, and the target classification set includes at least two execution components;

[0113] Based on the control strategy of the execution layer, a first association relationship is established between each execution component in the target classification set; and an association system of the execution layer is constructed according to the association relationship;

[0114] Based on the control strategy of the management layer, a second association relationship between the management component and the association system is established to establish a control relationship between the management component and the execution component;

[0115] The management component determines the target execution component according to the preset operation scenario based on the control relationship; executes the preset operation scenario according to the target execution component, and collects the operation data of each target execution component as the operation status data corresponding to the preset operation scenario.

[0116] The working principle and beneficial effects of the above technical solution: clarify which components are management components (such as central controllers, management systems, etc.) and which components are execution components (such as motors, sensors, actuators, etc.). The management component is usually responsible for overall control and scheduling, while the execution component performs specific operations according to the instructions of the management component. Each execution component has its specific attribute information, such as type, function, location, parameter range, etc. According to the attribute information of the execution component, it can be divided into different classification sets. These classifications can be based on factors such as function, location, type, etc. Then, one or more are selected from all classification sets as target classification sets, and the execution components in these sets will be associated and controlled in more detail in subsequent steps. Based on the control strategy of the execution layer, it is necessary to determine the association relationship between each execution component in the target classification set. These association relationships involve synchronization, coordination, dependency and other relationships between the execution components. By constructing these association relationships, it can be ensured that each execution component on the execution layer can work together in the expected manner. The above association relationships are integrated to construct a complete execution layer association system. This system describes the interaction and dependency between all execution components in the target classification set, providing a basis for subsequent control and management. Based on the control strategy of the management layer, it is necessary to establish an association relationship between the management component and the execution layer association system. This association relationship defines how the management component controls and schedules the execution layer, and how to adjust the control strategy through feedback from the execution layer. The establishment of this association relationship enables the management layer to effectively manage and control the operation of the execution layer. In the preset operation scenario, the management component will determine the target execution components that need to participate in the execution based on the control relationship. Then, it will send control instructions to these target execution components to make them perform corresponding operations according to the preset operation scenario. In the process of executing the preset operation scenario, the management component will collect the operation data of each target execution component in real time. These data include the status, parameters, performance indicators, etc. of the execution component, which are used to evaluate the operation status of the execution component and the performance of the entire system. In summary, this process involves the determination of the management component and the execution component in the static model, the classification of the execution component and the establishment of association relationships, and the execution and data collection based on these relationships in the preset operation scenario. These steps together constitute a complete control and management process, ensuring that the system can operate in the expected manner and obtain accurate operation status data corresponding to the preset operation scenario.

[0117] like Figure 2As shown, the second embodiment of the present invention provides a system for remote vehicle valuation, comprising:

[0118] A first receiving module, used for receiving vehicle information sent by a user terminal;

[0119] A calling module, used to call the corresponding vehicle decomposition model in the preset model library according to the vehicle information;

[0120] A first determination module is used to determine attribute information of key components of the vehicle according to the vehicle decomposition model;

[0121] The second determination module is used to determine the corresponding guidance method according to the attribute information of the key components, and send the guidance method to the user end for display;

[0122] The second receiving module is used to receive the status information of key components uploaded by the user end based on the guidance method;

[0123] An updating module, used for updating the vehicle decomposition model according to the state information to obtain a static model;

[0124] The valuation module is used to value the vehicle based on the static model, obtain the valuation result and display it.

[0125] The beneficial effects of the above technical solution are as follows: calling the corresponding vehicle decomposition model in the preset model library according to the vehicle information, guiding the user to upload the status information of the corresponding key components, updating the vehicle decomposition model according to the status information, obtaining a static model, determining an estimated vehicle model for the vehicle to be estimated, estimating the vehicle based on the static model, estimating the vehicle from the system as a whole, improving the efficiency and accuracy of the valuation, and thereby improving the user experience.

[0126] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for remote vehicle valuation, characterized in that: include: Receive vehicle information sent by the user; Calling the corresponding vehicle decomposition model in the preset model library according to the vehicle information; Determine the attribute information of key components of the vehicle based on the vehicle decomposition model; Determine the corresponding guidance method according to the attribute information of the key components, and send the guidance method to the user end for display; Receive status information of key components uploaded by the user based on the guidance method; The vehicle decomposition model is updated according to the state information to obtain a static model; Evaluate the vehicle according to the static model, obtain the valuation result and display it; The vehicle is valued based on the static model, and the valuation results are obtained and displayed, including: Determine the wear information of each key component in the static model; compare the wear information of each key component with the corresponding preset wear threshold, and determine the valuation data of each key component based on the comparison; determine the static valuation result of the vehicle based on the valuation data of each key component; Configure several preset operation scenarios; execute the preset operation scenarios respectively based on the static model to obtain the operation status data corresponding to each preset operation scenario; analyze the operation status data to determine the operation characteristic parameters; input the operation characteristic parameters into the pre-trained regression model; classify and identify the operation characteristic parameters and perform compensation processing according to the regression model to obtain the motion performance value under the preset operation scenario; compare the motion performance value under each preset operation scenario with the preset motion performance threshold value under the corresponding scenario, and determine the dynamic sub-valuation result of the vehicle according to the comparison result; calculate the dynamic valuation result of the vehicle according to the dynamic sub-valuation results of several vehicles; Based on the static valuation result of the vehicle and the dynamic sub-valuation result of the vehicle, the valuation result is determined and displayed.

2. The method for remote vehicle valuation as claimed in claim 1, characterized in that: The vehicle information includes the brand, model and production year of the vehicle.

3. The method for remote vehicle valuation as claimed in claim 1, characterized in that: The guidance methods include video guidance, outline guidance and text guidance; wherein, Video guidance involves playing pre-recorded demonstration videos on how to photograph specific vehicle areas; Contour guidance includes displaying contour images of vehicle parts on the user's screen and prompting the user to take photos at specific locations; The text guidance includes providing the user with detailed text instructions for photographing vehicle parts.

4. The method for remote vehicle valuation as claimed in claim 1, characterized in that: The state information is image information; Before updating the vehicle decomposition model according to the state information, the image information is associated with the corresponding decomposition module included in the vehicle decomposition model.

5. The method for remote vehicle valuation as claimed in claim 4, characterized in that: Before associating the image information with the corresponding decomposition module included in the vehicle decomposition model, the following steps are included: Divide the image information into several sub-images; Calculate the signal-to-noise ratio of each sub-image, calculate the average signal-to-noise ratio, and compare it with a preset signal-to-noise ratio threshold; When it is determined that the average signal-to-noise ratio is less than a preset signal-to-noise ratio threshold, image enhancement processing is performed on the image information.

6. The method for remote vehicle valuation as claimed in claim 5, characterized in that: Perform image enhancement processing on image information, including: Obtain the channel values ​​of each pixel in the image information in the R channel, the G channel, and the B channel, and determine the maximum channel value of the same pixel as the target feature value, and generate a target image based on the pixels with the target feature value; The target image is divided into several sub-target images, and the sub-target image in the central area of ​​the target image is used as the standard image; Calculate the average standard feature value of the standard image, query a preset average standard feature value-enhancement coefficient data table according to the average standard feature value, and determine a number of target enhancement coefficients based on different distances from the standard image; Calculate the distance information between the standard image and the sub-target image; Determine a corresponding enhancement coefficient among a plurality of target enhancement coefficients according to distance information between the standard image and the sub-target image; Calculate the average eigenvalue of other sub-target images except the standard image; enhance the average eigenvalue according to the corresponding enhancement coefficient of the sub-target image to obtain an enhanced image.

7. The method for remote vehicle valuation as claimed in claim 4, characterized in that: Before associating the image information with the corresponding decomposition module included in the vehicle decomposition model, the method further includes: Segment the image information to obtain several regional images; Performing fast Fourier transform processing on the plurality of regional images to convert the regional images from the spatial domain to the frequency domain to obtain a frequency spectrum representation of each regional image; Determine the high-frequency components according to the frequency spectrum representation of each regional image to obtain a high-frequency image; The high frequency image is associated with a corresponding decomposition module included in the vehicle decomposition model.

8. The method for remote vehicle valuation as claimed in claim 1, characterized in that: Based on the static model, the preset operation scenarios are respectively executed to obtain the operation status data corresponding to each preset operation scenario; including: Identify the management components and execution components in the static model; Get the attribute information of the execution component; According to the attribute information of the execution components, the execution components are classified to obtain a plurality of classification sets; a target classification set is determined, and the target classification set includes at least two execution components; Based on the control strategy of the execution layer, a first association relationship is established between each execution component in the target classification set; and an association system of the execution layer is constructed according to the association relationship; Based on the control strategy of the management layer, a second association relationship between the management component and the association system is established to establish a control relationship between the management component and the execution component; The management component determines the target execution component according to the preset operation scenario based on the control relationship; executes the preset operation scenario according to the target execution component, and collects the operation data of each target execution component as the operation status data corresponding to the preset operation scenario.

9. A system for remote vehicle valuation, characterized in that: include: A first receiving module, used for receiving vehicle information sent by a user terminal; A calling module, used to call the corresponding vehicle decomposition model in the preset model library according to the vehicle information; A first determination module is used to determine attribute information of key components of the vehicle according to the vehicle decomposition model; The second determination module is used to determine the corresponding guidance method according to the attribute information of the key components, and send the guidance method to the user end for display; The second receiving module is used to receive the status information of key components uploaded by the user end based on the guidance method; An updating module, used for updating the vehicle decomposition model according to the state information to obtain a static model; The valuation module is used to value the vehicle according to the static model, obtain the valuation result and display it; The valuation module estimates the vehicle according to the static model, obtains the valuation result and displays the method, including: Determine the wear information of each key component in the static model; compare the wear information of each key component with the corresponding preset wear threshold, and determine the valuation data of each key component based on the comparison; determine the static valuation result of the vehicle based on the valuation data of each key component; Configure several preset operation scenarios; execute the preset operation scenarios respectively based on the static model to obtain the operation status data corresponding to each preset operation scenario; analyze the operation status data to determine the operation characteristic parameters; input the operation characteristic parameters into the pre-trained regression model; classify and identify the operation characteristic parameters and perform compensation processing according to the regression model to obtain the motion performance value under the preset operation scenario; compare the motion performance value under each preset operation scenario with the preset motion performance threshold value under the corresponding scenario, and determine the dynamic sub-valuation result of the vehicle according to the comparison result; calculate the dynamic valuation result of the vehicle according to the dynamic sub-valuation results of several vehicles; Based on the static valuation result of the vehicle and the dynamic sub-valuation result of the vehicle, the valuation result is determined and displayed.

Images