Power transmission line tree line distance analysis method based on monocular vision

Abstract

The invention discloses a power transmission line tree line distance analysis method based on monocular vision, and belongs to the technical field of visual analysis distance measurement, and the method comprises the steps: obtaining the length of a preset power transmission line section, marking the length as an inspection length, collecting the related data of trees at two sides in the inspection length, and marking the trees as preset trees. The related data comprises height data of trees on two sides and distance data between the tail end of each tree branch and a preset power transmission line section; on the basis of the distance data, growth changes of a preset tree are collected in different time periods, the time periods are divided according to different temperature periods, and a database is constructed according to the collected growth changes; according to the method, monocular vision collection is performed on the preset tree and growth data analysis is performed on different temperature sections, so that more reliable data support can be provided for distance change between the preset tree in the future time period and the preset power transmission line section besides monocular vision data, and potential risks between branches and the preset power transmission line section are reduced.

Description

Technical Field

[0001] The invention relates to the technical field of visual analysis and distance measurement, in particular to a method for analyzing the distance between trees and lines of a power transmission line based on monocular vision. Background Art

[0002] Power supply is one of the important cornerstones of modern economic development, and transmission lines bear the heavy responsibility of connecting power stations with power users to ensure the efficiency, safety and reliability of power transmission. However, the tree barrier problem has brought severe challenges to the normal operation of transmission lines, which not only increases the complexity of power system operation, but also increases potential risks. In recent years, how to effectively conduct tree barrier inspections has become a topic that many research teams have devoted their efforts to studying. Researchers are committed to exploring more efficient and accurate inspection methods in order to reduce the impact of tree barriers on transmission lines and ensure the safety and stability of power transmission. In order to effectively solve the problem of tree barriers on transmission lines, the application document with technical application number CN202110570500.9 provides a method for judging the safe distance of trees under transmission lines based on visual analysis soft measurement. This technical solution uses the widely installed online video monitoring equipment for transmission lines to obtain on-site video photos at regular intervals, and performs visual recognition analysis and calculation based on the existing line tower coordinates, tower height, line length, etc. It has the advantages of real-time monitoring of tree height and timely warning without going to the site or knowing what kind of trees.

[0003] Another application document with technical application number CN202111374751.6 provides a transmission line detection method based on monocular visual positioning. This technical solution obtains the interval distance between adjacent monocular cameras through the positioning module and the calibration module. The image data obtained by the monocular camera is converted by the image processing module and enters the gimbal processor through the image information upload module. The changed feature points in the image are compared with the image at the same position in the previous period of time. After obtaining the data of the feature points, they are judged by the probability detection module. The data of abnormal feature points can be accurately obtained and judged to avoid losses caused by misjudgment.

[0004] However, in real life, power transmission lines are usually located at high positions. The growth of trees that can grow to the same height as the power transmission lines is easily affected by natural environmental factors. Among the many natural environmental factors, the blowing of natural wind on trees will cause the branches at high places to flutter. The above-mentioned technical solutions all focus on inspecting trees in a static state through video monitoring equipment, which affects the judgment of the distance between the end of the branch and the power transmission line, making the judgment of this distance inaccurate, and thus posing potential risks. In addition, the above-mentioned technical solutions only perform distance analysis based on the data provided by the video monitoring equipment, which makes it difficult to effectively predict the growth trend of the corresponding tree branches in the future period, resulting in a lag in the distance analysis. Summary of the invention

[0005] In view of the above-mentioned problems existing in the existing field of visual analysis ranging technology, the present invention is proposed.

[0006] Therefore, one of the objects of the present invention is to provide a transmission line tree-line distance analysis method based on monocular vision, which utilizes monocular vision collection of preset trees and growth data analysis of different temperature sections. Through this parallel method, the growth pattern of the preset trees can be better predicted, and more reliable data support can be provided for the distance change between the preset trees and the preset transmission line section in future time periods in addition to the monocular vision data. In addition, the abnormally growing branches can be locked according to the analysis of the data, thereby establishing the branches that need priority inspection and monitoring to reduce the potential risks between the branches and the preset transmission line section.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] The present invention provides a method for analyzing the distance between trees and lines of power transmission lines based on monocular vision, comprising the following steps:

[0009] The method for analyzing the distance between trees and lines of power transmission lines based on monocular vision includes the following steps:

[0010] Obtaining the length of a preset transmission line section, marking the length as an inspection length, collecting relevant data of trees on both sides of the inspection length, marking the trees as preset trees, the relevant data including height data of the trees on both sides and distance data between the ends of branches of each tree and the preset transmission line section;

[0011] Based on the distance data, the growth changes of the preset trees are collected in different time periods, wherein the time periods are divided into different temperature ranges, and a database is constructed according to the collected growth changes;

[0012] Acquire image data of the end of the branch of the preset tree according to the growth change, pre-process the image data, and calculate the distance between the end of the branch and the preset power transmission line segment based on the image data;

[0013] The growth characteristics of the preset trees in the different temperature ranges are obtained, the growth characteristics are differentiated, and a prediction model is constructed based on the growth characteristics.

[0014] As a preferred solution of the present invention, the different temperature sections include a summer temperature section and a winter temperature section, wherein a given number of statistical days is given in the summer temperature section, the growth data of at least 10 times of the branches of the preset tree are counted, and a data set is generated, and at the same time, the correlation law between the growth data and the temperature value in the corresponding temperature section is calculated in the data set, and the result is calculated according to the following formula:

[0015] Among them, j o The jth growth data in the oth statistical day in the summer temperature period;

[0016] Where, δ represents the average growth data of the branches of the preset tree in the oth statistical day, x i represents the xth data difference obtained from the ith adjacent data in the growth data, u e represents the u-th temperature value collected for the e-th time according to the data difference;

[0017] Collect 3 to 4 largest data differences, and obtain the distance between the end of the preset tree branch and the preset transmission line section based on the data differences. Among the 3 to 4 largest data differences collected, if one of the data differences is greater than the distance, the distance between the preset tree branch and the preset transmission line section is determined to be a dangerous distance, and the preset tree branch is pruned; otherwise, it is determined to be a safe distance.

[0018] As a preferred solution of the present invention, the image features of the ends of the branches of the preset trees are obtained based on the data difference, the image features include edge features of the image before acquisition and edge features of the image after acquisition, at least 3 edge points are collected in the edge features of the image before acquisition, the edge points are marked as reference points, the straight-line distance between the 3 edge points is calculated, the straight-line distance is marked as the reference distance, and the data change of the reference distance is calculated in the edge features of the image after acquisition, the data change is uploaded to the prediction model, and the prediction model is updated.

[0019] As a preferred solution of the present invention, the growth law of the fastest growing branch is analyzed based on the data change, and the analysis method includes taking 3 days as an analysis period, collecting temperature values ​​corresponding to the number of days in the analysis period, and obtaining a distance image between the corresponding branch end and the preset transmission line section under the temperature value, and calculating the distance change law between the two according to the following formula:

[0020] Among them, y t represents the yth temperature value obtained at the tth time within the analysis period;

[0021] Wherein, p represents the distance image between the corresponding branch end and the preset transmission line section obtained under the yth temperature value, b orepresents the bth intermediate distance between the end of the tree branch and the preset transmission line section calculated for the oth time based on the distance image, r represents a predicted value, which is the number of days required for the corresponding tree branch to grow to the intermediate distance predicted based on the temperature value, l o It represents the lth temperature value predicted based on the required number of days for the oth time.

[0022] As a preferred solution of the present invention, the preprocessing of image data includes denoising, image enhancement and image segmentation, wherein in the image segmentation, the three edge points are obtained and transmitted to the segmented image of the preset transmission line segment, and reference points are given in the segmented image. The reference points are given in equal proportion according to the distance change law between the corresponding tree branch end and the preset transmission line segment, and the given number is at least 3 according to the distance from the preset transmission line segment. The three reference points are divided into short-distance reference points, medium-distance reference points and long-distance reference points. In the distance image obtained in the future time period, if the distance between one of the edge points and the preset transmission line segment exceeds the medium-distance reference point, the branch corresponding to the edge point is marked as a key monitoring branch, otherwise, it is not marked.

[0023] As a preferred solution of the present invention, based on the number of days required for the corresponding branch predicted by the temperature value to grow to the intermediate value distance, each week is used as the acquisition period of the distance image, and images of the key monitored branches are acquired. When the distance between the key monitored branch and the preset power transmission line section changes faster than the required number of days, the key monitored branch is determined to be an abnormally growing branch and is pruned. Otherwise, it is not determined.

[0024] As a preferred solution of the present invention, when the distance change between the key monitored tree branch and the preset transmission line section is faster than the required number of days, at least 6 to 10 distance change data in the actual number of days are obtained, the distance change data are marked as risk data, and at least 4 of the distance change data are analyzed for patterns. When the distance change between other branches other than the corresponding branch in the future time period and the preset transmission line section conforms to the pattern analysis, the branch is determined to be an abnormally growing branch; otherwise, it is not determined.

[0025] As a preferred solution of the present invention, wherein: all distance change data obtained in the actual number of days are counted, the distance change data are divided into several evaluation indicators, and the data are normalized to calculate the weight of the risk data in each evaluation indicator; and the weight value is preset according to the result of the calculation, when the weight of the risk data of other branches outside the corresponding branch in the future time period in each evaluation indicator exceeds the weight value, it is determined that the branch is in the abnormal growth range and / or has an abnormal growth tendency; otherwise, it is not determined.

[0026] A terminal comprises a processor, an input interface, an output interface and a memory, wherein the processor, the input interface, the output interface and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 8.

[0027] A computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the method according to any one of claims 1 to 8.

[0028] The present invention utilizes monocular vision collection of preset trees and growth data analysis of different temperature sections. Through this parallel method, the growth law of the preset trees can be better predicted, and more reliable data support can be provided for the distance change between the preset trees and the preset power transmission line section in the future time period in addition to the monocular vision data. In addition, the abnormally growing branches can be locked according to the analysis of the data, so that the branches that need priority inspection and monitoring can be established to reduce the potential risks between the branches and the preset power transmission line section. At the same time, by collecting the straight-line distance between the edge points of each branch in the acquired image features, the distance change can be accurately calculated when the branch is floating, thereby improving the reliability of the distance analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0030] Figure 1 A schematic diagram of a method flow of an embodiment of the present invention;

[0031] Figure 2 It is a schematic diagram of the process structure of an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0033] Since the existing technical solutions all focus on inspecting trees in a static state through video monitoring equipment, the judgment of the distance between the end of the tree branch and the transmission line is affected, making the judgment of this distance inaccurate, and thus posing potential risks; and the existing technical solutions only perform distance analysis based on the data provided by the video monitoring equipment, which makes it difficult to effectively predict the growth trend of the corresponding tree branches in the future period, resulting in a lag in the distance analysis.

[0034] Based on this, the present invention proposes a transmission line tree-line distance analysis method based on monocular vision, which utilizes monocular vision collection of preset trees and growth data analysis of different temperature sections. Through this parallel method, the growth law of the preset trees can be better predicted, and more reliable data support can be provided for the distance changes between the preset trees and the preset transmission line sections in future time periods in addition to the monocular vision data. In addition, the abnormally growing branches can be locked according to the analysis of the data, thereby establishing the branches that need priority inspection and monitoring to reduce the potential risks between the branches and the preset transmission line sections.

[0035] The present invention is further described in detail below through embodiments and in conjunction with the accompanying drawings.

[0036] Reference Figure 1 to Figure 2 , is an embodiment of the present invention, which provides a transmission line tree-line distance analysis method based on monocular vision, comprising the following steps:

[0037] S10: Obtain the length of a preset transmission line section, mark the length as an inspection length, collect relevant data of trees on both sides of the inspection length, mark the trees as preset trees, and the relevant data include height data of the trees on both sides and distance data between the ends of the branches of each tree and the preset transmission line section;

[0038] S20: collecting growth changes of preset trees in different time periods based on the distance data, wherein the time periods are divided into different temperature ranges, and a database is constructed based on the collected growth changes;

[0039] S30: acquiring image data of the end of a branch of a preset tree according to the growth change, preprocessing the image data, and calculating the distance between the end of the branch and the preset transmission line section based on the image data;

[0040] S40: obtaining growth characteristics of preset trees in different temperature ranges, distinguishing the growth characteristics, and building a prediction model based on the growth characteristics;

[0041] It should be noted that in this embodiment, distinguishing the growth characteristics includes presetting the branch growth and growth angle of the tree;

[0042] At the same time, it should be noted that in this embodiment, different temperature sections include summer temperature sections and winter temperature sections, wherein a given number of statistical days is given in the summer temperature section, and the growth data of at least 10 preset tree branches are counted, and a data set is generated. At the same time, the correlation law between the growth data and the temperature value in the corresponding temperature section is calculated in the data set, and the calculation is obtained according to the following formula:

[0043] Among them, j o Represents the jth growth data in the oth statistical day in the summer temperature period;

[0044] In the formula, δ represents the average growth data of the branches of the preset tree in the oth statistical day, x i Indicates the xth data difference obtained from the ith adjacent data in the growth data, u e represents the u-th temperature value collected for the e-th time based on the data difference;

[0045] Collect 3 to 4 largest data differences, and obtain the distance between the end of the preset tree branch and the preset power transmission line section based on the data differences. Among the 3 to 4 largest data differences collected, if one of the data differences is greater than the distance, the distance between the preset tree branch and the preset power transmission line section is determined to be a dangerous distance, and the preset tree branch is pruned. Otherwise, it is determined to be a safe distance.

[0046] On the basis of the above, the present embodiment obtains the image features of the ends of the branches of the preset trees based on the data difference, the image features include the edge features of the image before acquisition and the edge features of the image after acquisition, collects at least 3 edge points in the edge features of the image before acquisition, marks the edge points as reference points, calculates the straight-line distance between the 3 edge points, marks the straight-line distance as the reference distance, calculates the data change of the reference distance in the edge features of the image after acquisition, uploads the data change to the prediction model, and updates the prediction model;

[0047] This embodiment further analyzes the growth law of the fastest growing branch based on data changes. The analysis method includes taking 3 days as an analysis period, collecting temperature values ​​corresponding to the number of days in the analysis period, and obtaining a distance image between the corresponding branch end and the preset transmission line section under the temperature value, and calculating the distance change law between the two according to the following formula:

[0048] Among them, y t represents the yth temperature value obtained at the tth time in the analysis period;

[0049] Where p represents the distance image between the corresponding branch end and the preset transmission line section obtained under the yth temperature value, b o represents the bth intermediate distance between the end of the branch and the preset transmission line section calculated based on the distance image for the oth time, r represents the predicted value, which is the number of days required for the corresponding branch to grow to the intermediate distance based on the temperature value, l o represents the lth temperature value predicted for the oth time based on the required number of days;

[0050] Specifically, in this embodiment, the preprocessing of image data includes denoising, image enhancement and image segmentation, wherein, in the image segmentation, three edge points are obtained and transmitted to a segmented image of a preset transmission line segment, and reference points are given in the segmented image. The reference points are given in equal proportion according to the distance change law between the end of the corresponding tree branch and the preset transmission line segment, and the given number is at least three according to the distance from the preset transmission line segment. The three reference points are divided into short-distance reference points, medium-distance reference points and long-distance reference points. In the distance image obtained in the future time period, if the distance between one of the edge points and the preset transmission line segment exceeds the medium-distance reference point, the branch corresponding to the edge point is marked as a key monitoring branch, otherwise, it is not marked;

[0051] On the basis of the above, based on the number of days required for the corresponding branch to grow to the middle value predicted by the temperature value, the distance image acquisition period is one week, and the image acquisition is performed on the key monitored branches. When the distance between the key monitored branches and the preset transmission line section changes faster than the required number of days, the key monitored branches are judged as abnormal growth branches and pruned. Otherwise, no judgment is made.

[0052] It should be noted that in this embodiment, studies in real life have shown that the growth rate of trees may be abnormally fast under certain conditions. For example, the urban heat island effect can cause trees to grow 25% faster than in rural areas because heat can promote the growth of trees. In addition, climate change can also affect the growth rate of trees. Rising global temperatures extend the growing season of trees in cold regions and make the tree rings thicker.

[0053] In this embodiment, when the distance change between the key monitored tree branch and the preset transmission line section is faster than the required number of days, at least 6 to 10 distance change data in the actual number of days are obtained, the distance change data are marked as risk data, and at least 4 of the distance change data are analyzed for regularity. When the distance change between other branches other than the corresponding branch in the future time period and the preset transmission line section conforms to the regularity analysis, the branch is determined to be an abnormal growth branch; otherwise, it is not determined;

[0054] Among them, all the distance change data obtained in the actual days are counted, the distance change data are divided into several evaluation indicators, and the data are normalized to calculate the weight of the risk data in each evaluation indicator; and the weight value is preset according to the calculation result. When the weight of the risk data of other branches outside the corresponding branch in the future time period in each evaluation indicator exceeds the weight value, it is determined that the branch is in the abnormal growth range and / or has an abnormal growth tendency; otherwise, it is not determined.

[0055] A terminal comprises a processor, an input interface, an output interface and a memory, wherein the processor, the input interface, the output interface and the memory are connected to each other, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute a method as claimed in any one of claims 1 to 8.

[0056] A computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the method as claimed in any one of claims 1 to 8.

[0057] In summary, the present invention utilizes monocular vision collection of preset trees and growth data analysis of different temperature sections. Through this parallel method, the growth law of the preset trees can be better predicted, and more reliable data support can be provided for the distance change between the preset trees and the preset transmission line section in the future time period in addition to the monocular vision data. In addition, the abnormally growing branches can be locked according to the analysis of the data, so that the branches that need to be inspected and monitored first can be established to reduce the potential risks between the branches and the preset transmission line section. At the same time, by collecting the straight-line distance between the edge points of each branch in the acquired image features, the distance change can be accurately calculated when the branch is floating, thereby improving the reliability of the distance analysis.

[0058] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for analyzing the distance between trees and lines of power transmission lines based on monocular vision, characterized in that: The following steps are involved: Obtaining the length of a preset transmission line section, marking the length as an inspection length, collecting relevant data of trees on both sides of the inspection length, marking the trees as preset trees, the relevant data including height data of the trees on both sides and distance data between the ends of branches of each tree and the preset transmission line section; Based on the distance data, the growth changes of the preset trees are collected in different time periods, wherein the time periods are divided into different temperature ranges, and a database is constructed according to the collected growth changes; Acquire image data of the end of the branch of the preset tree according to the growth change, pre-process the image data, and calculate the distance between the end of the branch and the preset power transmission line segment based on the image data; The growth characteristics of the preset trees in the different temperature ranges are obtained, the growth characteristics are differentiated, and a prediction model is constructed based on the growth characteristics.

2. The method for analyzing the distance between trees and lines of power transmission lines based on monocular vision according to claim 1, characterized in that: The different temperature sections include a summer temperature section and a winter temperature section, wherein, given statistical days in the summer temperature section, the growth data of at least 10 times of the branches of the preset tree are statistically collected, and a data set is generated. At the same time, the correlation law between the growth data and the temperature value in the corresponding temperature section is calculated in the data set, and the result is calculated according to the following formula: Among them, j o The jth growth data in the oth statistical day in the summer temperature period; Where, δ represents the average growth data of the branches of the preset tree in the oth statistical day, x i represents the xth data difference obtained from the ith adjacent data in the growth data, u e represents the u-th temperature value collected for the e-th time according to the data difference; Collect 3 to 4 largest data differences, and obtain the distance between the end of the preset tree branch and the preset transmission line section based on the data differences. Among the 3 to 4 largest data differences collected, if one of the data differences is greater than the distance, the distance between the preset tree branch and the preset transmission line section is determined to be a dangerous distance, and the preset tree branch is pruned; otherwise, it is determined to be a safe distance.

3. The method for analyzing the distance between trees and lines of power transmission lines based on monocular vision according to claim 2, characterized in that: Based on the data difference, image features of the ends of the branches of the preset trees are obtained, and the image features include edge features of the image before acquisition and edge features of the image after acquisition. At least three edge points are collected in the edge features of the image before acquisition, and the edge points are marked as reference points. The straight-line distance between the three edge points is calculated, and the straight-line distance is marked as the reference distance. The data change of the reference distance is calculated in the edge features of the image after acquisition, and the data change is uploaded to the prediction model, and the prediction model is updated.

4. The method for analyzing the distance between trees and lines of power transmission lines based on monocular vision according to claim 3, characterized in that: The growth law of the fastest growing branch is analyzed based on the data change, and the analysis method includes taking 3 days as an analysis period, collecting temperature values ​​corresponding to the number of days in the analysis period, and obtaining a distance image between the corresponding branch end and the preset transmission line section under the temperature value, and calculating the distance change law between the two according to the following formula: Among them, y t represents the yth temperature value obtained at the tth time within the analysis period; Wherein, p represents the distance image between the corresponding branch end and the preset transmission line section obtained under the yth temperature value, b o represents the bth intermediate distance between the end of the tree branch and the preset transmission line section calculated for the oth time based on the distance image, r represents a predicted value, which is the number of days required for the corresponding tree branch to grow to the intermediate distance predicted based on the temperature value, l o It represents the lth temperature value predicted based on the required number of days for the oth time.

5. The method for analyzing the distance between trees and lines of power transmission lines based on monocular vision according to claim 4, characterized in that: The preprocessing of the image data includes denoising, image enhancement and image segmentation, wherein, in the image segmentation, the three edge points are obtained and transmitted to the segmented image of the preset transmission line section, and a reference point is given in the segmented image. The reference point is given in proportion according to the distance change law between the corresponding tree branch end and the preset transmission line section, and the given number is at least 3 according to the distance from the preset transmission line section. The three reference points are divided into short-distance reference points, medium-distance reference points and long-distance reference points. In the distance image obtained in the future time period, if the distance between one of the edge points and the preset transmission line section exceeds the medium-distance reference point, the branch corresponding to the edge point is marked as a key monitoring branch, otherwise, it is not marked.

6. The method for analyzing the distance between trees and lines of power transmission lines based on monocular vision according to claim 5, characterized in that: Based on the number of days required for the corresponding branch predicted by the temperature value to grow to the intermediate value distance, each week is used as the acquisition period of the distance image, and images of the key monitored branches are acquired. When the distance between the key monitored branch and the preset transmission line section changes faster than the required number of days, the key monitored branch is determined to be an abnormally growing branch and is pruned. Otherwise, it is not determined.

7. The method for analyzing the distance between trees and lines of power transmission lines based on monocular vision according to claim 6, characterized in that: When the distance change between the key monitored branch and the preset transmission line section is faster than the required number of days, at least 6 to 10 distance change data in the actual number of days are obtained, the distance change data are marked as risk data, and at least 4 of the distance change data are analyzed for regularity. When the distance change between other branches other than the corresponding branch in the future time period and the preset transmission line section conforms to the regularity analysis, the branch is determined to be an abnormal growth branch; Otherwise, no judgment is made.

8. The method for analyzing the distance between trees and lines of power transmission lines based on monocular vision according to claim 7, characterized in that: Count all the distance change data obtained in the actual days, divide the distance change data into several evaluation indicators, normalize the data, and calculate the weight of the risk data in each evaluation indicator; A weight value is preset according to the result of the calculation, and when the weight of the risk data of other branches outside the corresponding branch in the future period accounts for each evaluation index exceeding the weight value, it is determined that the branch is in an abnormal growth range and / or has an abnormal growth tendency; Otherwise, no judgment is made.

9. A terminal, characterized in that: The method comprises a processor, an input interface, an output interface and a memory, wherein the processor, the input interface, the output interface and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is enabled to perform the method according to any one of claims 1 to 8.

Images