Fund issuing risk control method and device, equipment, medium and program product
By obtaining and comparing the target area images of the project site, calculating the expected fund quota and issuing early warning signals, the problem of banks' difficulty in monitoring the risk of fund issuance in remote areas projects is solved, and more efficient and accurate risk control is achieved.
Patent Information
- Application Number
- CN202411700657.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-26
- Publication Date
- 2025-03-07
AI Technical Summary
When banks provide financial services for project projects, especially when newly built projects are located in remote areas, it is difficult to implement conventional risk control, making it difficult to track and monitor the risk of fund issuance.
By obtaining the image set of the target area, identifying the actual image outline, comparing it with the expected image, calculating the expected fund amount, and issuing an early warning signal when the expected fund amount is inconsistent with the amount of funds to be issued, so as to achieve risk control of fund issuance.
The implementation, timeliness and accuracy of monitoring the risk of fund issuance has been improved, especially in scenarios such as mountain bridge construction, which has reduced monitoring costs and improved monitoring accuracy and quality.
Smart Images
Figure CN119579937A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the fields of artificial intelligence technology and financial technology, and more specifically to a fund disbursement risk control method, device, equipment, medium and program product. Background Art
[0002] As the financial industry and the project engineering industry become increasingly integrated, when banks provide financial services for project engineering, they will be involved in the disbursement of funds from workers' special accounts. In this process, it is necessary to monitor the disbursement of funds to workers and issue abnormal warnings.
[0003] As for the payment of funds to these workers, the prior art often sends dedicated personnel to participate in the supervision of project progress, and then implements risk control on the payment service of funds from workers' special accounts through timely project progress.
[0004] However, when a new project is located in an area that is difficult to reach by conventional transportation, it is difficult for banks to implement conventional risk control. Therefore, how to ensure that the risk of capital disbursement is controllable is a technical problem that needs to be solved urgently. Summary of the invention
[0005] In view of the above problems, the present disclosure provides a fund disbursement risk control method, apparatus, device, medium and program product that improves the feasibility, timeliness and accuracy of project risk monitoring.
[0006] According to a first aspect of the present disclosure, a method for controlling the risk of fund disbursement is provided, the method comprising: acquiring a target area image set, the target area image set comprising N target area images, N being a positive integer; identifying actual image contours in the N target area images; obtaining N comparison results based on comparing the N actual image contours with expected images; calculating an expected fund amount based on the N comparison results; and issuing a warning signal when the expected fund amount is different from the fund amount to be disbursed.
[0007] According to an embodiment of the present disclosure, identifying the actual image contours in the N target area images includes: for any of the target area images, extracting the target color area in the target area image; performing contour recognition based on the target color area to obtain the actual image contour.
[0008] According to an embodiment of the present disclosure, extracting the target color area in the target area image includes: digitizing the pixels of the target area image; extracting the target area image after digitizing the pixels based on preset rules to obtain the target color area; or extracting the target area image after digitizing the pixels based on a machine learning model to obtain the target color area.
[0009] According to an embodiment of the present disclosure, extracting the target area image after pixel digitization based on preset rules to obtain the target color area includes: extracting the target area image after pixel digitization based on a preset target color range threshold to obtain the target color area.
[0010] According to an embodiment of the present disclosure, the target area image after pixel digitization is extracted based on a machine learning model to obtain the target color area, including: clustering each pixel point in the target area image after pixel digitization based on a clustering algorithm to obtain L clusters, where L is a positive integer; based on a preset target color, finding O target clusters in the L clusters, where O is a positive integer less than L; and extracting the target area image after pixel digitization based on the pixel points in the O target clusters to obtain the target color area.
[0011] According to an embodiment of the present disclosure, the contour recognition is performed based on the target color area to obtain the actual image contour, including: distinguishing the target color area from other areas of the target area image based on a specific color to obtain a first target area image; calculating the grayscale weighted value of the first target area image based on the RGB averaging method to obtain a second target area image after grayscale processing; obtaining a third target area image based on denoising the second target area image; and calculating the gradient amplitude and direction of the third target area image to obtain the actual image contour.
[0012] According to an embodiment of the present disclosure, the N comparison results are obtained based on comparing the N actual image contours with the expected image, including: obtaining a corresponding relationship based on a one-to-one matching of the N actual image contours with the fragments in the expected image; and based on the corresponding relationship, performing a feature point comparison between the actual image contour and the fragment in the expected image to obtain the comparison result.
[0013] According to an embodiment of the present disclosure, calculating the expected funding amount based on the N comparison results includes: acquiring budget information corresponding to the N comparison results; and calculating the expected funding amount based on the N comparison results and the budget information.
[0014] According to an embodiment of the present disclosure, the acquiring of a target area image set, wherein the target area image set includes N different target area images, includes: acquiring the target area image set by means of an Internet of Things camera; and / or acquiring the target area image set by means of a satellite.
[0015] The second aspect of the present disclosure provides a fund disbursement risk control device, which includes: an image acquisition module, used to acquire a target area image set, the target area image set includes N target area images, N is a positive integer; a contour recognition module, used to identify the actual image contours in the N target area images; a comparison module, used to compare the N actual image contours with the expected image to obtain N comparison results; a fund calculation module, used to calculate the expected fund amount based on the N comparison results; and an early warning module, used to issue a warning signal when the expected fund amount is different from the fund amount to be issued.
[0016] According to an embodiment of the present disclosure, the contour recognition module includes: a target color area extraction submodule and an actual image contour extraction submodule, the target color area extraction submodule is used to extract the target color area in the target area image for any of the target area images; the actual image contour extraction submodule is used to perform contour recognition based on the target color area to obtain the actual image contour.
[0017] According to an embodiment of the present disclosure, the target color area extraction submodule includes: a pixel digitization unit and a target color area extraction unit, the pixel digitization unit is used to digitize the pixel points of the target area image; the target color area extraction unit is used to extract the target area image after the pixel points are digitized based on preset rules to obtain the target color area; or extract the target area image after the pixel points are digitized based on a machine learning model to obtain the target color area.
[0018] According to an embodiment of the present disclosure, the target color region extraction unit is used to extract the target region image after pixel digitization based on a preset target color range threshold to obtain the target color region.
[0019] According to an embodiment of the present disclosure, the target color area extraction unit is also used to cluster each pixel point in the target area image after the pixel points are digitized based on a clustering algorithm to obtain L clusters, where L is a positive integer; based on a preset target color, find O target clusters in the L clusters, where O is a positive integer less than L; and extract the target area image after the pixel points are digitized based on the pixel points in the O target clusters to obtain the target color area.
[0020] According to an embodiment of the present disclosure, the actual image contour extraction submodule includes: a target image distinguishing unit, a grayscale unit, a denoising unit and an actual image contour extraction unit, the target image distinguishing unit is used to distinguish the target color area and other areas of the target area image based on a specific color to obtain a first target area image; the grayscale unit is used to calculate the grayscale weighted value of the first target area image based on the RGB averaging method to obtain a second target area image after grayscale processing; the denoising unit is used to obtain a third target area image based on denoising the second target area image; and the actual image contour extraction unit is used to calculate the gradient amplitude and direction of the third target area image to obtain the actual image contour.
[0021] According to an embodiment of the present disclosure, the comparison module includes: a matching unit and a comparison unit, the matching unit is used to obtain a corresponding relationship based on one-to-one matching of the N actual image contours with the fragments in the expected image; and the comparison unit is used to perform feature point comparison between the actual image contour and the fragment in the expected image based on the corresponding relationship to obtain the comparison result.
[0022] According to an embodiment of the present disclosure, the funds calculation module includes: a data acquisition unit and a funds calculation unit, the data acquisition unit is used to acquire budget data corresponding to the N comparison results; and the funds calculation unit is used to calculate the expected funds amount based on the N comparison results and the budget data.
[0023] According to an embodiment of the present disclosure, the image acquisition module is specifically used to acquire the target area image set collected by means of an Internet of Things camera; and / or acquire the target area image set collected by means of a satellite.
[0024] A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.
[0025] The fourth aspect of the present disclosure further provides a computer-readable storage medium having a computer program or instructions stored thereon, which implements the steps of the above method when the above computer program or instructions are executed by a processor.
[0026] The fifth aspect of the present disclosure further provides a computer program product, including a computer program or instructions, which implement the steps of the above method when the above computer program or instructions are executed by a processor.
[0027] In the embodiments of the present disclosure, in order to solve the technical problem that there is a great risk in the disbursement of funds during the project construction process, the embodiments of the present disclosure collect the target image of the project site through automated means, and compare the target image with the expected construction drawing after processing to realize the judgment of the envy progress, calculate the expected amount of funds by determining the good project progress, and realize the risk control of fund disbursement by judging the consistency between the expected amount of funds and the amount of funds to be issued. The embodiments based on the present disclosure solve the problem that the amount of funds disbursed by workers in engineering construction is difficult to track and warn, so as to better enable banks to strengthen the monitoring of the disbursement of funds to project workers, especially in the scenario of bridge construction in mountainous areas, which greatly reduces the monitoring cost and improves the accuracy and quality of monitoring. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:
[0029] Figure 1 A schematic diagram showing an application scenario of fund disbursement risk control according to an embodiment of the present disclosure;
[0030] Figure 2 A flowchart of a method for controlling fund disbursement risks according to an embodiment of the present disclosure is schematically shown;
[0031] Figure 3 A fund distribution curve according to an embodiment of the present disclosure is schematically shown;
[0032] Figure 4 A target area image according to an embodiment of the present disclosure is schematically shown;
[0033] Figure 5 A target color region according to an embodiment of the present disclosure is schematically shown;
[0034] Figure 6 Schematically shows an actual image profile according to an embodiment of the present disclosure;
[0035] Figure 7 A building drawing diagram according to an embodiment of the present disclosure is schematically shown;
[0036] Figure 8 Schematically shows an automatic comparison diagram of a contour and a construction drawing according to an embodiment of the present disclosure;
[0037] Fig. 9 A schematic diagram of a structure of a fund disbursement risk control device according to an embodiment of the present disclosure is shown; and
[0038] Fig.10A block diagram of an electronic device suitable for implementing a fund disbursement risk control method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION
[0039] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.
[0040] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.
[0041] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.
[0042] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).
[0043] In the technical solution of the present disclosure, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0044] In the scenario of using personal information for automated decision-making, the methods, devices, and systems provided by the embodiments of the present disclosure provide users with corresponding operation portals for users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating a person's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs, and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge and skills, and have reached a certain level of professionalism.
[0045] The banking industry is often involved in the agency payment of project funds, that is, the implementation of fund payment according to the completion of each node in the project progress. In the process of carrying out this business, the bank is often required to verify the progress of the project on the spot, but the terrain involved in the construction industry is complex and changeable. Due to the limitations of the terrain, there are difficulties in supervision under certain terrains. In a typical scenario, for example, in mountainous terrain, various large bridges are involved. When banks provide financial services for the construction of large bridges, they involve providing workers' special account fund payment services, and they also need to issue abnormal warnings for the payment of workers' funds.
[0046] However, because large-scale bridge construction projects are different from ordinary projects, there are many situations that cannot be monitored by existing technologies: first, many large cross-mountain bridges are located in remote areas and may not be accessible by road. On-site inspections must rely on traffic conditions provided by the construction party, making it difficult for banks to conduct on-site inspections of the project progress and carry out surprise inspections through independent identities; second, the capital disbursement curve does not develop linearly, and there is an exclusive development curve accompanying the progress of the project. Figure 3 A fund distribution curve according to an embodiment of the present disclosure is schematically shown. Figure 3 As shown in the figure, the curve of general road worker payment is relatively smooth and has small fluctuations, while the curve of worker fund payment for large bridges is usually not a smooth, linear curve. This makes it impossible to predict the amount of funds to be paid through past data, and it can only be judged through on-site project conditions. For example, when banks issue abnormal warnings for worker fund payment for general road construction projects, they usually judge by simple thresholds such as (this month's payment amount - last month's payment amount)>x. This is usually not suitable for large bridge construction projects. Therefore, the previous solution of manually monitoring key progress nodes from time to time is not applicable to fund payment in the field of bridge construction.
[0047] In order to solve the technical problems existing in the prior art, an embodiment of the present disclosure provides a method for controlling the risk of fund disbursement, the method comprising: acquiring a target area image set, the target area image set comprising N target area images, N being a positive integer; identifying actual image contours in the N target area images; obtaining N comparison results based on comparing the N actual image contours with expected images; calculating an expected fund amount based on the N comparison results; and issuing a warning signal when the expected fund amount is different from the fund amount to be disbursed.
[0048] In the embodiments of the present disclosure, in order to solve the technical problem that there is a great risk in the disbursement of funds during the project construction process, the embodiments of the present disclosure collect the target image of the project site through automated means, and compare the target image with the expected construction drawing after processing to realize the judgment of the envy progress, calculate the expected amount of funds by determining the good project progress, and realize the risk control of fund disbursement by judging the consistency between the expected amount of funds and the amount of funds to be issued. The embodiments based on the present disclosure solve the problem that the amount of funds disbursed by workers in engineering construction is difficult to track and warn, so as to better enable banks to strengthen the monitoring of the disbursement of funds to project workers, especially in the scenario of bridge construction in mountainous areas, which greatly reduces the monitoring cost and improves the accuracy and quality of monitoring.
[0049] Figure 1 The application scenario diagram of fund disbursement risk control according to an embodiment of the present disclosure is schematically shown.
[0050] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.
[0051] The user can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).
[0052] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.
[0053] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.
[0054] It should be noted that the fund disbursement risk control method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the fund disbursement risk control device provided in the embodiment of the present disclosure can generally be set in the server 105. The fund disbursement risk control method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the fund disbursement risk control device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.
[0055] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.
[0056] The following will be based on Figure 1 The scene described by Figure 2~Figure 8 The fund disbursement risk control method of the disclosed embodiment is described in detail.
[0057] Figure 2 The flowchart of the fund disbursement risk control method according to the embodiment of the present disclosure is schematically shown.
[0058] like Figure 2 As shown, the fund disbursement risk control method of this embodiment includes operations S210 to S250, and the fund disbursement risk control method can be executed by the server 105.
[0059] In operation S210, a target area image set is acquired, where the target area image set includes N target area images, where N is a positive integer.
[0060] Specifically, the target area images in the target area image set include images of different target areas shot at different angles.
[0061] According to an embodiment of the present disclosure, the acquiring of a target area image set, wherein the target area image set includes N different target area images, includes: acquiring the target area image set by means of an Internet of Things camera; and / or acquiring the target area image set by means of a satellite.
[0062] Specifically, the Internet of Things and satellite remote sensing technology can be used to solve to a certain extent the problem of difficulty in collecting the construction progress of large bridges in mountainous areas.
[0063] For example, IoT cameras can be used to collect data on the target area of the construction progress. Since the location of the new cross-mountain bridge is sparsely populated and the road has not yet been built, it is difficult for banks to carry out conventional methods. Therefore, the progress of the bridge can be monitored by deploying remote cameras. This method can achieve multi-camera and multi-angle shooting, and can better obtain more specific construction progress.
[0064] For another example, satellite images can be used to collect the progress of the target area under construction. Due to natural reasons such as lack of electricity in mountainous areas, steep cliffs, and wild animals damaging cameras, the cameras deployed in the previous step may not work properly, so satellite images are needed as a backup solution to collect construction progress. Although satellite images are not as accurate as directly deploying IoT cameras, they are clear enough to capture key structures such as bridge piers and bridge decks for large bridge projects.
[0065] For example, the Internet of Things and satellite remote sensing technology can be combined to simultaneously collect corresponding target area images to achieve all-round monitoring.
[0066] In operation S220, actual image contours in the N target area images are identified.
[0067] Identifying actual image contours in N region images includes: obtaining actual image contours through image preprocessing, edge detection, contour extraction, contour drawing, deep learning, and deep network methods.
[0068] It should be noted that during the construction of large cable-stayed bridges and cable-stayed bridges, steps such as arranging steel cables are usually completed by large machinery, so there is no money to be paid, while the stages involving framework assumptions often rely on a large number of workers. In other words, when paying attention to the total amount of funds to be paid to workers, the focus of the bank should be on the cement building part as the actual image contour to be extracted.
[0069] According to an embodiment of the present disclosure, identifying the actual image contours in the N target area images includes: for any of the target area images, extracting the target color area in the target area image; performing contour recognition based on the target color area to obtain the actual image contour.
[0070] In the embodiment of the present disclosure, since the objects constructed in the engineering project are of a single color, mainly cement color, the target color is set to cement color, and contour recognition is performed on the area corresponding to the color to obtain the actual image contour.
[0071] According to an embodiment of the present disclosure, extracting the target color area in the target area image includes: digitizing the pixels of the target area image; extracting the target area image after digitizing the pixels based on preset rules to obtain the target color area; or extracting the target area image after digitizing the pixels based on a machine learning model to obtain the target color area.
[0072] Specifically, the color space is extracted and the pixels in the image are digitized. Different color space calculation methods can be used to extract the digitized content, such as RGB, HSV and Lab. Specifically, RGB color space: the target color is determined by setting the value range of the three channels of red (R), green (G), and blue (B); HSV color space: the color is divided into three components of hue, saturation, and value, and the target color is determined more accurately by setting the HSV value range; Lab color space: more related to the human visual system, the target color is determined by setting the value range of L (brightness), a (red and green channels), and b (yellow and blue channels).
[0073] The extraction of the target color area can be achieved through fixed rules or automated algorithms. For example, fixed rules include: using other existing cement bridge photos to extract the threshold range of the cement building part. In the specific implementation, an automated tool is used to select pixels within the preset threshold range. Automated algorithms include: treating the colors in the image as data points, performing cluster analysis in the color space, and classifying similar colors into the same category, thereby highlighting the target color.
[0074] Figure 4 A target area image according to an embodiment of the present disclosure is schematically shown. Figure 5 A target color region according to an embodiment of the present disclosure is schematically shown. Figure 4 and Figure 5 As shown, the bridges in the target area image are extracted according to the target color (the target color may be a color corresponding to a value within a certain interval) to obtain the target color area.
[0075] According to an embodiment of the present disclosure, extracting the target area image after pixel digitization based on preset rules to obtain the target color area includes: extracting the target area image after pixel digitization based on a preset target color range threshold to obtain the target color area.
[0076] Specifically, the value corresponding to the target color is screened by setting the threshold interval to ensure Figure 4 and Figure 5 The bridge section is extracted and highlighted.
[0077] According to an embodiment of the present disclosure, the target area image after pixel digitization is extracted based on a machine learning model to obtain the target color area, including: clustering each pixel point in the target area image after pixel digitization based on a clustering algorithm to obtain L clusters, where L is a positive integer; based on a preset target color, finding O target clusters in the L clusters, where O is a positive integer less than L; and extracting the target area image after pixel digitization based on the pixel points in the O target clusters to obtain the target color area.
[0078] Specifically, when implementing the color extraction scheme through the clustering model, a certain error is considered, such as Figure 4 and 5 The illumination shadows on the bridge produced by natural lighting can extract the color regions corresponding to multiple target clusters as the target color regions.
[0079] According to an embodiment of the present disclosure, the contour recognition is performed based on the target color area to obtain the actual image contour, including: distinguishing the target color area from other areas of the target area image based on a specific color to obtain a first target area image; calculating the grayscale weighted value of the first target area image based on the RGB averaging method to obtain a second target area image after grayscale processing; obtaining a third target area image based on denoising the second target area image; and calculating the gradient amplitude and direction of the third target area image to obtain the actual image contour.
[0080] First, combine Figure 5 As shown, for the background part of the non-target color area, its color is converted into other arbitrary pure colors.
[0081] Then, the contour recognition algorithm can be used to identify the contour of the bridge. The grayscale weighted value is first obtained by the RGB average method, as shown in the following formula 1 or formula 2:
[0082] Formula 1
[0083] Formula 2
[0084] Of course, the above formulas 1 and 2 can also be optimized. The specific logic is that since the main body of the building has been obtained, the color of the main body of the cement building is used as the standard value, and the difference between other colors and the standard value is used as the Gary value. The formula is as follows: avg(Gary) is obtained by the RGB average value of all pixels in the target area, and then the Gary value is calculated by the average value, as shown in the following formula 3:
[0085] Formula 3
[0086] Furthermore, Gaussian filtering is used to smooth the image and reduce noise to alleviate the fuzzy recognition part, as shown in the following formula 4:
[0087] Formula 4
[0088] Among them, x and y are the pixel positions.
[0089] Finally, an edge detection algorithm is used to calculate the gradient magnitude and direction of the image, for example, the gradient magnitude and direction of the image is calculated by the Sobel operator. Figure 6 An actual image profile according to an embodiment of the present disclosure is schematically shown. Figure 6 As shown, the outline of the bridge has been outlined by line segments, and the outline can be compared with the expected image later.
[0090] In operation S230, N comparison results are obtained based on comparing the N actual image contours with the expected image.
[0091] Figure 7 A schematic diagram of a building drawing according to an embodiment of the present disclosure is shown. Figure 7 As shown, Figure 7 It is the expected image of the engineering architectural drawing, which includes the main structures of the bridge, such as pile foundation, tower base, tower column, tower top, main beam, cable-stayed cable, bridge deck, etc. At the same time, the architectural drawing will show the bridge view from various angles such as horizontal, top and side.
[0092] Specifically, the SIFT algorithm (Scale-Invariant Feature Transform) can be used to match each contour unit with the specific contour unit in the construction design drawing to determine whether the contour unit is completed. The descriptor obtains the features and matches the image feature points. The SIFT feature is scale-invariant, and even if the rotation angle, image brightness or shooting angle is changed, a good detection effect can still be obtained.
[0093] According to an embodiment of the present disclosure, the N comparison results are obtained based on comparing the N actual image contours with the expected image, including: obtaining a corresponding relationship based on a one-to-one matching of the N actual image contours with the fragments in the expected image; and based on the corresponding relationship, performing a feature point comparison between the actual image contour and the fragment in the expected image to obtain the comparison result.
[0094] Figure 8 The following schematically shows an automatic comparison diagram of a contour and a construction drawing according to an embodiment of the present disclosure. Figure 8 As shown in Table 1, each engineering project of the bridge can be compared with a plurality of actual contour images of the engineering project and the corresponding expected images to check whether the corresponding engineering progress is guaranteed, as shown in Table 1 below:
[0095] Table 1
[0096] Engineering Projects Completed Tower A yes Tower B yes Main beam section B no Bridge deck section XX no
[0097] As shown in Table 1, after feature comparison, it can be determined whether the engineering project corresponding to each image is completed, and then the amount of funds to be paid can be comprehensively calculated based on these completion results.
[0098] In operation S240, an expected amount of funds is calculated based on the N comparison results.
[0099] Specifically, when banks provide financial service solutions for large bridges, they will require the provision of architectural drawings, project cost tables, and construction period (project quantity) tables as budget information. The expected funding amount can be calculated based on the funds required for the project corresponding to each comparison result.
[0100] According to an embodiment of the present disclosure, calculating the expected funding amount based on the N comparison results includes: acquiring budget information corresponding to the N comparison results; and calculating the expected funding amount based on the N comparison results and the budget information.
[0101] Specifically, the total amount of workers' wages preset for the project and the amount of workers involved in each specific project (usually in "man-days") will be displayed through the project cost table and construction schedule. From this, the amount of workers involved in each specific structure can be obtained. As shown in Table 2 below:
[0102] Table 2
[0103] Engineering Projects Need manpower Estimated salary Tower A 500 worker days The estimated daily wage for each person is 600 Tower B 800 workers per day The estimated daily salary for each person is 500 Main beam section B 100 worker days The estimated daily salary for each person is 500 Bridge deck Gaosuntang section 300 workers per day The estimated daily wage for each person is 400
[0104] By combining Table 2 with the fund calculation formula, we can estimate the funds corresponding to each structure, and thus calculate the expected amount of funds for this regulatory process.
[0105] In operation S250, when the expected amount of funds is different from the amount of funds to be issued, a warning signal is issued.
[0106] Among them, the amount of funds to be disbursed is the amount of funds required at the end of the preset construction period. By comparing the expected amount of funds estimated this time with the preset amount of funds to be disbursed, it is determined whether the funds should be disbursed, and an early warning message is issued when the construction period arrives but the corresponding project is not completed.
[0107] In the embodiments of the present disclosure, in order to solve the technical problem that there is a great risk in the disbursement of funds during the project construction process, the embodiments of the present disclosure collect the target image of the project site through automated means, and compare the target image with the expected construction drawing after processing to realize the judgment of the envy progress, calculate the expected amount of funds by determining the good project progress, and realize the risk control of fund disbursement by judging the consistency between the expected amount of funds and the amount of funds to be issued. The embodiments based on the present disclosure solve the problem that the amount of funds disbursed by workers in engineering construction is difficult to track and warn, so as to better enable banks to strengthen the monitoring of the disbursement of funds to project workers, especially in the scenario of bridge construction in mountainous areas, which greatly reduces the monitoring cost and improves the accuracy and quality of monitoring.
[0108] Based on the above-mentioned fund disbursement risk control method, the present disclosure also provides a fund disbursement risk control device. Fig. 9 The device is described in detail.
[0109] Fig. 9 The structural block diagram of the fund disbursement risk control device according to an embodiment of the present disclosure is schematically shown.
[0110] like Fig. 9 As shown, the fund disbursement risk control device 900 of this embodiment includes an image acquisition module 910 , a contour recognition module 920 , a comparison module 930 , a fund calculation module 940 and an early warning module 950 .
[0111] The image acquisition module 910 is used to acquire a target area image set, where the target area image set includes N target area images, where N is a positive integer. In one embodiment, the image acquisition module 910 may be used to perform the operation S210 described above, which will not be described in detail herein.
[0112] The contour recognition module 920 is used to recognize the actual image contours in the N target area images. In one embodiment, the contour recognition module 920 can be used to perform the operation S220 described above, which will not be described in detail here.
[0113] The comparison module 930 is used to compare the N actual image contours with the expected image to obtain N comparison results. In one embodiment, the comparison module 930 can be used to perform the operation S230 described above, which will not be described in detail here.
[0114] The fund calculation module 940 is used to calculate the expected fund amount based on the N comparison results. In one embodiment, the fund calculation module 940 can be used to perform the operation S240 described above, which will not be described in detail here.
[0115] The early warning module 950 is used to send out an early warning signal when the expected amount of funds is different from the amount of funds to be issued. In one embodiment, the early warning module 950 can be used to perform the operation S250 described above, which will not be described in detail here.
[0116] In the embodiments of the present disclosure, in order to solve the technical problem that there is a great risk in the disbursement of funds during the project construction process, the embodiments of the present disclosure collect the target image of the project site through automated means, and compare the target image with the expected construction drawing after processing to realize the judgment of the envy progress, calculate the expected amount of funds by determining the good project progress, and realize the risk control of fund disbursement by judging the consistency between the expected amount of funds and the amount of funds to be issued. The embodiments based on the present disclosure solve the problem that the amount of funds disbursed by workers in engineering construction is difficult to track and warn, so as to better enable banks to strengthen the monitoring of the disbursement of funds to project workers, especially in the scenario of bridge construction in mountainous areas, which greatly reduces the monitoring cost and improves the accuracy and quality of monitoring.
[0117] According to an embodiment of the present disclosure, the contour recognition module includes: a target color area extraction submodule and an actual image contour extraction submodule, the target color area extraction submodule is used to extract the target color area in the target area image for any of the target area images; the actual image contour extraction submodule is used to perform contour recognition based on the target color area to obtain the actual image contour.
[0118] According to an embodiment of the present disclosure, the target color area extraction submodule includes: a pixel digitization unit and a target color area extraction unit, the pixel digitization unit is used to digitize the pixel points of the target area image; the target color area extraction unit is used to extract the target area image after the pixel points are digitized based on preset rules to obtain the target color area; or extract the target area image after the pixel points are digitized based on a machine learning model to obtain the target color area.
[0119] According to an embodiment of the present disclosure, the target color region extraction unit is used to extract the target region image after pixel digitization based on a preset target color range threshold to obtain the target color region.
[0120] According to an embodiment of the present disclosure, the target color area extraction unit is also used to cluster each pixel point in the target area image after the pixel points are digitized based on a clustering algorithm to obtain L clusters, where L is a positive integer; based on a preset target color, find O target clusters in the L clusters, where O is a positive integer less than L; and extract the target area image after the pixel points are digitized based on the pixel points in the O target clusters to obtain the target color area.
[0121] According to an embodiment of the present disclosure, the actual image contour extraction submodule includes: a target image distinguishing unit, a grayscale unit, a denoising unit and an actual image contour extraction unit, the target image distinguishing unit is used to distinguish the target color area and other areas of the target area image based on a specific color to obtain a first target area image; the grayscale unit is used to calculate the grayscale weighted value of the first target area image based on the RGB averaging method to obtain a second target area image after grayscale processing; the denoising unit is used to obtain a third target area image based on denoising the second target area image; and the actual image contour extraction unit is used to calculate the gradient amplitude and direction of the third target area image to obtain the actual image contour.
[0122] According to an embodiment of the present disclosure, the comparison module includes: a matching unit and a comparison unit, the matching unit is used to obtain a corresponding relationship based on one-to-one matching of the N actual image contours with the fragments in the expected image; and the comparison unit is used to perform feature point comparison between the actual image contour and the fragment in the expected image based on the corresponding relationship to obtain the comparison result.
[0123] According to an embodiment of the present disclosure, the funds calculation module includes: a data acquisition unit and a funds calculation unit, the data acquisition unit is used to acquire budget data corresponding to the N comparison results; and the funds calculation unit is used to calculate the expected funds amount based on the N comparison results and the budget data.
[0124] According to an embodiment of the present disclosure, the image acquisition module is specifically used to acquire the target area image set collected by means of an Internet of Things camera; and / or acquire the target area image set collected by means of a satellite.
[0125] According to an embodiment of the present disclosure, any multiple modules of the image acquisition module 910, the contour recognition module 920, the comparison module 930, the fund calculation module 940 and the early warning module 950 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the image acquisition module 910, the contour recognition module 920, the comparison module 930, the fund calculation module 940 and the early warning module 950 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in a suitable combination of any of them. Alternatively, at least one of the image acquisition module 910, the contour recognition module 920, the comparison module 930, the funds calculation module 940 and the warning module 950 can be at least partially implemented as a computer program module, and when the computer program module is executed, the corresponding function can be performed.
[0126] Fig.10 A block diagram of an electronic device suitable for implementing a fund disbursement risk control method according to an embodiment of the present disclosure is schematically shown.
[0127] like Fig.10 As shown, the electronic device 1000 according to an embodiment of the present disclosure includes a processor 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage part 1008 to a random access memory (RAM) 1003. The processor 1001 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 1001 may also include an onboard memory for caching purposes. The processor 1001 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.
[0128] In RAM 1003, various programs and data required for the operation of electronic device 1000 are stored. Processor 1001, ROM 1002 and RAM 1003 are connected to each other via bus 1004. Processor 1001 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 1002 and / or RAM 1003. It should be noted that the program can also be stored in one or more memories other than ROM 1002 and RAM 1003. Processor 1001 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.
[0129] According to an embodiment of the present disclosure, the electronic device 1000 may further include an input / output (I / O) interface 1005, which is also connected to the bus 1004. The electronic device 1000 may further include one or more of the following components connected to the input / output (I / O) interface 1005: an input portion 1006 including a keyboard, a mouse, etc.; an output portion 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 1008 including a hard disk, etc.; and a communication portion 1009 including a network interface card such as a LAN card, a modem, etc. The communication portion 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the input / output (I / O) interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1010 as needed, so that a computer program read therefrom is installed into the storage portion 1008 as needed.
[0130] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.
[0131] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 1002 and / or RAM 1003 described above and / or one or more memories other than ROM 1002 and RAM 1003.
[0132] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the fund disbursement risk control method provided by the embodiment of the present disclosure.
[0133] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 1001. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.
[0134] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 1009, and / or installed from the removable medium 1011. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.
[0135] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1009, and / or installed from the removable medium 1011. When the computer program is executed by the processor 1001, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.
[0136] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).
[0137] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0138] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.
[0139] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.
Claims
1. A method for controlling fund issuance risk, characterized in that: The method comprises: Acquire a target area image set, wherein the target area image set includes N target area images, where N is a positive integer; Identifying actual image contours in the N target area images; Based on the comparison of the N actual image contours with the expected image, N comparison results are obtained; Calculating an expected funding amount based on the N comparison results; and When the expected amount of funds is different from the amount of funds to be issued, an early warning signal is issued.
2. The method according to claim 1, characterized in that: The identifying actual image contours in the N target area images includes: For any of the target area images, extracting a target color area in the target area image; Contour recognition is performed based on the target color area to obtain the actual image contour.
3. The method according to claim 2, characterized in that The step of extracting the target color area in the target area image comprises: digitizing the pixels of the target area image; Extract the target area image after pixel digitization based on preset rules to obtain the target color area; or The target area image after pixel digitization is extracted based on the machine learning model to obtain the target color area.
4. The method according to claim 3, characterized in that The target area image after pixel digitization is extracted based on a preset rule to obtain the target color area includes: Based on a preset target color range threshold, the target area image after pixel digitization is extracted to obtain the target color area.
5. The method according to claim 3, characterized in that: The target area image obtained by extracting pixel digitization based on the machine learning model to obtain the target color area includes: Based on the clustering algorithm, each pixel point in the target area image after the pixel points are digitized is clustered to obtain L clusters, where L is a positive integer; Based on the preset target color, find O target clusters among L clusters, where O is a positive integer less than L; and The target area image after pixel digitization is extracted based on the pixel points in the O target clusters to obtain the target color area.
6. The method according to any one of claims 2 to 5, characterized in that: The performing contour recognition based on the target color area to obtain the actual image contour includes: Differentiate the target color area from other areas of the target area image based on a specific color, and obtain a first target area image; Calculating the grayscale weighted value of the first target area image based on the RGB average method to obtain a second target area image after grayscale processing; Obtaining a third target area image based on denoising the second target area image; and The gradient magnitude and direction of the third target region image are calculated to obtain an actual image contour.
7. The method according to any one of claims 2 to 5, characterized in that: The step of comparing the N actual image contours with the expected image to obtain N comparison results includes: Deriving a corresponding relationship based on one-to-one matching of the N actual image contours with the segments in the expected image; and Based on the corresponding relationship, feature point comparison is performed between the actual image contour and the segment in the expected image to obtain the comparison result.
8. The method according to claim 7, characterized in that The calculating the expected amount of funds based on the N comparison results includes: Obtaining budget information corresponding to the N comparison results; and The expected funding amount is calculated based on the N comparison results and the budget information.
9. The method according to any one of claims 1 to 5 and 8, characterized in that The acquiring of a target area image set, wherein the target area image set includes N different target area images, includes: Acquire the target area image set collected by an Internet of Things camera; and / or Acquire a set of images of the target area collected by satellite.
10. A fund disbursement risk control device, characterized in that: The device comprises: An image acquisition module, used to acquire a target area image set, wherein the target area image set includes N target area images, where N is a positive integer; A contour recognition module, used to recognize actual image contours in the N target area images; A comparison module, configured to obtain N comparison results based on the comparison of the N actual image contours with the expected image; A fund calculation module, used to calculate the expected fund amount based on the N comparison results; and The early warning module is used to issue an early warning signal when the expected amount of funds is different from the amount of funds to be issued.
11. An electronic device, comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 9.
12. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.
13. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.