CN115345440A - Method and system for intelligently distributing highway maintenance tasks based on pavement monitoring - Google Patents
Method and system for intelligently distributing highway maintenance tasks based on pavement monitoring Download PDFInfo
- Publication number
- CN115345440A CN115345440A CN202210867979.7A CN202210867979A CN115345440A CN 115345440 A CN115345440 A CN 115345440A CN 202210867979 A CN202210867979 A CN 202210867979A CN 115345440 A CN115345440 A CN 115345440A
- Authority
- CN
- China
- Prior art keywords
- maintenance
- type
- disease
- strategy
- road
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 603
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012544 monitoring process Methods 0.000 title claims abstract description 32
- 201000010099 disease Diseases 0.000 claims abstract description 147
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 147
- 238000012216 screening Methods 0.000 claims abstract description 59
- 238000011156 evaluation Methods 0.000 claims abstract description 39
- 238000010801 machine learning Methods 0.000 claims abstract description 12
- 238000013210 evaluation model Methods 0.000 claims description 30
- 238000012795 verification Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 6
- 230000007547 defect Effects 0.000 claims description 5
- 230000010354 integration Effects 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 239000000428 dust Substances 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 claims description 3
- 238000012797 qualification Methods 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 230000002354 daily effect Effects 0.000 description 29
- 230000000737 periodic effect Effects 0.000 description 8
- 239000000370 acceptor Substances 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000009429 distress Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
Abstract
The application discloses a method and a system for intelligently distributing highway maintenance tasks based on pavement monitoring, belongs to the technical field of highway maintenance application, integrates and classifies maintenance strategies through a big data platform, performs a disease level learning evaluation module based on machine learning, establishes a module through a new maintenance task and intelligently distributes the maintenance tasks, transmits new maintenance task parameters into a maintenance strategy screening model, screens corresponding maintenance types, determines the maintenance types according to maintenance type priority, determines the maintenance strategies, matches new maintenance task bearers based on a highway maintenance supervision center module, and completes intelligent distribution of the highway maintenance tasks.
Description
Technical Field
The application relates to the technical field of highway maintenance application, in particular to a method and a system for intelligently distributing highway maintenance tasks based on pavement monitoring.
Background
In order to ensure the normal operation and maintenance of the routes of the regions under jurisdiction, the highway maintenance department needs to send out patrol maintenance personnel to inspect the highway and the structures attached to the highway every day, update, store and analyze maintenance management data of the highway, provide data analysis for the maintenance management personnel to improve management quality so as to find existing problems in time, take measures to prevent the problems in the bud, and provide guarantee for the normal smooth traffic and safe operation of the regions under jurisdiction through patrol inspection and evaluation work.
Patent with application number CN2018103386187 discloses a highway maintenance method, which can realize comprehensive integrity analysis of highway conditions, so that people can find and handle problems as soon as possible, thereby prolonging the service life of the highway; the patent with the application number of CN2021203617352 discloses a highway maintenance safety supervision system, which can shoot the road surface condition through a first camera, and record the shot image information through a computer, thereby effectively avoiding the problem of missing manual visual inspection in highway supervision and patrol, controlling an unmanned aerial vehicle over the road surface, avoiding traffic flow, not hindering traffic, and eliminating the potential safety hazard of manual inspection.
Disclosure of Invention
The embodiment of the application aims to provide a method and a system for intelligently allocating a highway maintenance task based on pavement monitoring, so as to solve the problem that in the prior art, a maintenance strategy cannot be quickly selected and a task bearer cannot be allocated on the highway maintenance task.
In order to solve the above technical problems, embodiments of the present application provide a method for intelligently allocating a highway maintenance task based on road surface monitoring, which adopts the following technical solutions:
the method for intelligently distributing the highway maintenance tasks based on the pavement monitoring comprises the following steps:
102, screening a plurality of road surface maintenance strategies based on a big data platform, carrying out distinguishing numbering, and classifying the plurality of road surface maintenance strategies according to different maintenance types, wherein the maintenance types comprise: a daily maintenance type, a regular maintenance type, a special maintenance type and an improved project type;
103, grabbing a plurality of pavement damage pictures and maintenance strategies corresponding to different pavement damage pictures based on a web crawler, respectively performing damage grade learning evaluation on the plurality of pavement damage pictures based on a preset learning evaluation model, and identifying the maintenance types corresponding to the plurality of pavement damage pictures based on the maintenance strategies;
104, respectively obtaining pavement disease pictures corresponding to a daily maintenance type, a regular maintenance type, a special maintenance type and an improvement project type and a disease evaluation level corresponding to the pavement disease pictures, and determining disease evaluation level ranges respectively corresponding to the daily maintenance type, the regular maintenance type, the special maintenance type and the improvement project type;
105, constructing a maintenance strategy screening model based on the incidence relation among the maintenance type, the disease grade and the distinguishing numbers corresponding to the plurality of road surface maintenance strategies, and inputting the maintenance strategy screening model into a highway maintenance supervision center;
106, acquiring images based on a road patrol unmanned aerial vehicle, acquiring a plurality of road pavement disease images, transmitting the road pavement disease images as a test set into the study evaluation model after study, detecting the images, and identifying disease levels respectively corresponding to the road pavement disease images as new maintenance task parameters;
and 107, transmitting the new maintenance task parameters into the maintenance strategy screening model, screening maintenance types corresponding to the maintenance strategy screening model, if the new maintenance task corresponds to multiple maintenance types, improving the priority of the project type according to the daily maintenance type, the periodic maintenance type, the special maintenance type and the like, determining the maintenance type, then determining the maintenance strategy, matching a new maintenance task bearer based on the maintenance task bearer information, and completing intelligent distribution of the highway maintenance task.
Further, the entering of maintenance task bearer information in the highway maintenance supervision center in advance at least includes:
and inputting qualification information, sustainable maintenance type information and implementable maintenance strategy information of a maintenance task bearer.
Further, select a plurality of road surface maintenance strategies based on big data platform to carry out the difference serial number, the concrete implementation is:
pre-arranging a retrieval field related to highway maintenance implementation as a search parameter;
and sequentially putting the search parameters into a search box of a preset big data platform, searching to obtain a plurality of pavement maintenance implementation schemes, taking each implementation scheme as a pavement maintenance strategy, and performing difference numbering.
Further, the plurality of road surface maintenance strategies are classified according to different maintenance types, and the specific classification mode is as follows:
analyzing the character information in the plurality of road surface maintenance strategies based on a semantic recognition technology, and if the corresponding maintenance type is directly noted to be any one of a daily maintenance type, a regular maintenance type, a special maintenance type and an improved engineering type in the current road surface maintenance strategy through analysis, directly confirming the maintenance type corresponding to the current road surface maintenance strategy; if the maintenance type corresponding to the maintenance type is not clearly shown to be any one of a daily maintenance type, a periodic maintenance type, a special maintenance type and an improved engineering type, determining the maintenance type corresponding to the current road surface maintenance strategy based on a preset associated word bank, wherein the preset associated word bank comprises four tables, and associated words in each table are respectively in one-to-one correspondence with the daily maintenance type, the periodic maintenance type, the special maintenance type and the improved engineering type.
Further, the web crawler based method for capturing a plurality of road surface disease pictures and maintenance strategies corresponding to different disease pictures comprises the following specific implementation modes:
acquiring a plurality of pavement defect pictures by using a picture grabbing tool;
and searching a maintenance strategy corresponding to the picture similar to the retrieval picture, namely a plurality of maintenance strategies corresponding to the retrieval picture by taking the pavement disease picture as the retrieval picture and searching the picture based on the CNN neural network.
Further, based on a preset learning evaluation model, the plurality of road surface defect pictures are subjected to defect level learning evaluation respectively, and the specific learning mode is as follows:
dividing the plurality of pavement disease pictures into a training sample and a verification sample according to the proportion of 9;
the method comprises the steps of setting disease grades as four grades in advance, wherein the four grades are I, II, III and IV respectively, and setting disease grade classification conditions for the I, II, III and IV grades simultaneously;
the training samples are transmitted into a preset learning evaluation model for machine learning, and are divided into four grades of I, II, III and IV based on the disease grade classification conditions;
the verification sample is transmitted into a preset learning evaluation model after machine learning for cross verification, and if the verification sample can obtain results corresponding to different disease levels after being evaluated by the learning evaluation model, the evaluation is successful;
and constructing four difference sets according to four grades of I, II, III and IV, and adding the plurality of pavement disease pictures into the four difference sets according to learning evaluation results.
Further, the maintenance strategy screening model comprises the following steps:
and 204, acquiring the difference number corresponding to the final maintenance strategy, sending the difference number to the highway maintenance supervision center, and sending the maintenance strategies corresponding to the difference number to a receiver after the receiver is selected by the highway maintenance supervision center.
Further, the pavement disease comprises:
road surface crack, water accumulation, pit slot, broken plate, bulge and dust collection.
Further, before the road surface disease picture is respectively subjected to disease level learning evaluation based on the preset learning evaluation model, the method includes:
acquiring RGB (R, G, B) values of each pixel point in the pavement damage picture;
based on a floating point algorithm: replacing the RGB (R, G, B) value of the corresponding pixel point with RGB (Gray, gray, gray) by Gray =0.3R +0.59G + 0.11B;
and acquiring the replaced picture as a picture transmitted into a preset learning evaluation model.
In order to solve the technical problem, an embodiment of the present application further provides a system for intelligently allocating a highway maintenance task based on road surface monitoring, and the following technical scheme is adopted:
system based on road surface monitoring carries out intelligent distribution to highway maintenance task includes:
and the maintenance strategy integration and classification module is used for screening a plurality of road maintenance strategies based on a big data platform, carrying out distinguishing and numbering, and classifying the plurality of road maintenance strategies according to different maintenance types, wherein the maintenance types comprise: a daily maintenance type, a regular maintenance type, a special maintenance type and an improvement project type;
the system comprises a disease level learning and evaluating module, a maintenance strategy judging module and a maintenance strategy judging module, wherein the disease level learning and evaluating module is used for capturing a plurality of road surface disease pictures and maintenance strategies corresponding to different road surface disease pictures based on a web crawler, respectively performing disease level learning and evaluation on the plurality of road surface disease pictures based on a preset learning and evaluating model, and identifying maintenance types corresponding to the plurality of road surface disease pictures based on the maintenance strategies;
the maintenance type and disease level corresponding module is used for respectively obtaining a pavement disease picture corresponding to a daily maintenance type, a regular maintenance type, a special maintenance type and an improvement project type and a disease evaluation level corresponding to the pavement disease picture, and determining a disease evaluation level range corresponding to the daily maintenance type, the regular maintenance type, the special maintenance type and the improvement project type;
the highway maintenance supervision center module is used for recording maintenance task receiver information in advance; the system is also used for constructing a maintenance strategy screening model based on the incidence relation among the maintenance type, the disease grade and the distinguishing numbers corresponding to a plurality of road surface maintenance strategies, and recording the maintenance strategy screening model into a highway maintenance supervision center;
the new maintenance task establishing module is used for acquiring images based on a road patrol unmanned aerial vehicle, acquiring a plurality of road pavement disease images, transmitting the road pavement disease images into the study evaluation model after study as a test set, detecting the images, and identifying disease levels respectively corresponding to the road pavement disease images as new maintenance task parameters;
and the maintenance task intelligent distribution module is used for transmitting the new maintenance task parameters into the maintenance strategy screening model, screening the corresponding maintenance types, if the new maintenance task corresponds to multiple maintenance types, improving the priority of the project type according to the daily maintenance type, the regular maintenance type, the special maintenance type and the engineering type, firstly determining the maintenance type, then determining the maintenance strategy, matching a new maintenance task bearer based on the maintenance task bearer information, and completing the intelligent distribution of the highway maintenance tasks.
Compared with the prior art, the embodiment of the application mainly has the following beneficial effects:
the embodiment of the application discloses a method and a system for intelligently distributing highway maintenance tasks based on pavement monitoring, maintenance strategies are integrated and classified through a big data platform, a disease level learning evaluation module is carried out based on machine learning, a new maintenance task building module and a maintenance task intelligent distribution module are used for transmitting new maintenance task parameters into a maintenance strategy screening model, maintenance types corresponding to the maintenance strategies are screened, maintenance type determination is carried out firstly according to maintenance type priority, then maintenance strategy determination is carried out, intelligent distribution of highway maintenance tasks is completed by matching new maintenance task acceptors based on a highway maintenance supervision center module, highway maintenance strategies and acceptor information are integrated in advance, and maintenance strategies and the new maintenance tasks are quickly selected and assigned to the task acceptors through a machine learning model and a strategy screening model, so that the distribution efficiency of the highway maintenance tasks is improved.
Drawings
In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
FIG. 1 is a flowchart of an embodiment of a method for intelligently allocating roadway maintenance tasks based on roadway monitoring according to an embodiment of the present disclosure;
FIG. 2 is a flow chart illustrating screening of an embodiment of a maintenance strategy screening model according to an embodiment of the present disclosure;
FIG. 3 is an embodiment of a system for intelligently allocating roadway maintenance tasks based on roadway monitoring in an embodiment of the present application;
fig. 4 is an execution logic diagram of an embodiment of a method for intelligently allocating a road maintenance task based on road surface monitoring in the embodiment of the present application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof, in the description and claims of this application and the description of the above figures are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein may be combined with other embodiments.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that, the method for intelligently allocating a road maintenance task based on road surface monitoring provided in the embodiments of the present application is generally executed by a server/terminal device, and accordingly, the system for intelligently allocating a road maintenance task based on road surface monitoring is generally disposed in the server/terminal device.
Referring to fig. 1, a flowchart of an embodiment of a method for intelligently allocating a road maintenance task based on road monitoring according to the present application is shown, where the method for intelligently allocating a road maintenance task based on road monitoring includes the following steps:
In some embodiments of the present application, the entering of the information of the maintenance task bearer in the highway maintenance supervision center in advance includes at least: and inputting qualification information, sustainable maintenance type information and implementable maintenance strategy information of a maintenance task bearer.
102, screening a plurality of road maintenance strategies based on a big data platform, carrying out distinguishing numbering, and classifying the plurality of road maintenance strategies according to different maintenance types, wherein the maintenance types comprise: a daily maintenance type, a regular maintenance type, a special maintenance type and an improvement project type.
In some embodiments of the present application, the screening out a plurality of road maintenance strategies based on the big data platform, and performing difference numbering, where a specific implementation manner is: pre-arranging a retrieval field related to highway maintenance implementation as a search parameter; and sequentially putting the search parameters into a search box of a preset big data platform, searching to obtain a plurality of pavement maintenance implementation schemes, taking each implementation scheme as a pavement maintenance strategy, and carrying out differential numbering.
In some embodiments of the present application, the plurality of road surface maintenance strategies are classified according to different maintenance types, and the specific classification manner is as follows: analyzing the character information in the plurality of road surface maintenance strategies based on a semantic recognition technology, and if the corresponding maintenance type is directly noted to be any one of a daily maintenance type, a regular maintenance type, a special maintenance type and an improved engineering type in the current road surface maintenance strategy through analysis, directly confirming the maintenance type corresponding to the current road surface maintenance strategy; if the maintenance type corresponding to the maintenance type is not clearly shown to be any one of a daily maintenance type, a periodic maintenance type, a special maintenance type and an improved engineering type, determining the maintenance type corresponding to the current road surface maintenance strategy based on a preset associated word bank, wherein the preset associated word bank comprises four tables, and associated words in each table are respectively in one-to-one correspondence with the daily maintenance type, the periodic maintenance type, the special maintenance type and the improved engineering type.
103, grabbing a plurality of pavement disease pictures and maintenance strategies corresponding to different disease pictures based on a web crawler, respectively performing disease grade learning evaluation on the plurality of pavement disease pictures based on a preset learning evaluation model, and identifying maintenance types corresponding to the plurality of pavement disease pictures based on the maintenance strategies.
In some embodiments of the present application, the capturing a plurality of road surface disease pictures and maintenance strategies corresponding to different disease pictures based on a web crawler includes: acquiring a plurality of pavement defect pictures by using a picture grabbing tool; and searching a maintenance strategy corresponding to the picture similar to the retrieval picture, namely a plurality of maintenance strategies corresponding to the retrieval picture by taking the pavement disease picture as the retrieval picture and searching the picture based on the CNN neural network.
In some embodiments of the present application, based on a preset learning evaluation model, the disease level learning evaluation is performed on the plurality of road surface disease pictures, and the specific learning manner is as follows: dividing the plurality of pavement damage pictures into a training sample and a verification sample according to the proportion of 9; setting disease levels to four levels, namely I, II, III and IV levels in advance, and setting disease level classification conditions for the I, II, III and IV levels; the training samples are transmitted into a preset learning evaluation model for machine learning, and are divided into four grades of I, II, III and IV based on the disease grade classification conditions; transmitting the verification sample into a preset learning evaluation model after machine learning, performing cross verification, and if the verification sample can obtain results corresponding to different disease levels after being evaluated by the learning evaluation model, successfully evaluating; and constructing four difference sets according to four grades of I, II, III and IV, and adding the plurality of pavement disease pictures into the four difference sets according to learning evaluation results.
In some embodiments of the present application, before performing disease level learning evaluation on road disease pictures respectively based on a preset learning evaluation model, the method includes: acquiring an RGB (R, G, B) value of each pixel point in the pavement disease picture; based on a floating point algorithm: replacing the RGB (R, G, B) value of the corresponding pixel point with RGB (Gray, gray, gray) by Gray =0.3R +0.59G + 0.11B; and acquiring the replaced picture as a picture transmitted into a preset learning evaluation model.
And 104, respectively obtaining the pavement damage pictures corresponding to the daily maintenance type, the regular maintenance type, the special maintenance type and the improvement project type and the damage evaluation level corresponding to the pavement damage pictures, and determining the range of the damage evaluation level corresponding to the daily maintenance type, the regular maintenance type, the special maintenance type and the improvement project type.
And 105, constructing a maintenance strategy screening model based on the association relationship among the maintenance type, the disease grade and the distinguishing numbers corresponding to the plurality of road surface maintenance strategies, and inputting the maintenance strategy screening model into a highway maintenance supervision center.
And 106, acquiring images based on the road patrol unmanned aerial vehicle, acquiring a plurality of road pavement disease pictures, transmitting the road pavement disease pictures as a test set into the study evaluation model after the study is completed, detecting the pictures, and identifying disease levels corresponding to the road pavement disease pictures as new maintenance task parameters.
And 107, transmitting the new maintenance task parameters into the maintenance strategy screening model, screening maintenance types corresponding to the maintenance strategy screening model, if the new maintenance task corresponds to multiple maintenance types, improving the priority of the project type according to the daily maintenance type, the periodic maintenance type, the special maintenance type and the like, determining the maintenance type, then determining the maintenance strategy, matching a new maintenance task bearer based on the maintenance task bearer information, and completing intelligent distribution of the highway maintenance task.
In some embodiments of the present application, the pavement distress includes: road surface crack, water accumulation, pit and groove, broken plate, bulge and dust collection.
In some embodiments of the present application, the maintenance strategy screening model is specifically executed in the following manner: starting the maintenance strategy screening model, and taking the disease levels respectively corresponding to the plurality of road pavement disease pictures as new maintenance task parameters; determining a maintenance type corresponding to the new maintenance task parameter based on the new maintenance task parameter, if the new maintenance task parameter is within the range of disease assessment levels belonging to a plurality of maintenance types, improving the priority of the project type according to the daily maintenance type, the regular maintenance type, the special maintenance type and the maintenance type, and selecting the maintenance type with high priority as the maintenance type corresponding to the new maintenance task parameter, namely the first maintenance type; obtaining a plurality of maintenance strategies corresponding to the first maintenance type to be used as a first strategy set, obtaining a plurality of maintenance strategies corresponding to the new maintenance task parameters to be used as a second strategy set, directly using the maintenance strategy as a final maintenance strategy if the maintenance strategies in the first strategy set are the same as and unique to the maintenance strategies in the second strategy set, and selecting the maintenance strategy based on the lowest cost to be used as the final maintenance strategy if the maintenance strategies in the first strategy set are the same as the maintenance strategies in the second strategy set; and obtaining a difference number corresponding to the final maintenance strategy and sending the difference number to the highway maintenance supervision center, and after the highway maintenance supervision center selects a receiver, sending the maintenance strategies corresponding to the difference number to the receiver together.
With continuing reference to fig. 2, fig. 2 shows a screening flowchart of an embodiment of the maintenance strategy screening model in the embodiment of the present application, including:
And 202, determining a maintenance type corresponding to the new maintenance task parameter based on the new maintenance task parameter, if the new maintenance task parameter is in the range of disease assessment levels belonging to a plurality of maintenance types, improving the priority of the project type according to the daily maintenance type, the regular maintenance type, the special maintenance type and the like, and selecting the maintenance type with high priority as the maintenance type corresponding to the new maintenance task parameter, namely the first maintenance type.
And 204, acquiring the difference number corresponding to the final maintenance strategy, sending the difference number to the highway maintenance supervision center, and sending the maintenance strategies corresponding to the difference number to a bearer after the highway maintenance supervision center selects the bearer.
The method for intelligently distributing the highway maintenance tasks based on the pavement monitoring in the embodiment of the application can integrate and classify maintenance strategies through a big data platform, a disease level learning evaluation module is carried out based on machine learning, a new maintenance task establishing module and a maintenance task intelligent distribution module are used for transmitting new maintenance task parameters into a maintenance strategy screening model, corresponding maintenance types are screened, maintenance types are determined according to maintenance type priority, maintenance strategies are determined, intelligent distribution of the highway maintenance tasks is completed based on matching of a new maintenance task bearer by a highway maintenance supervision center module, the highway maintenance strategies and bearer information are integrated in advance, and maintenance strategies and the assignment task bearer are quickly selected and distributed by the machine learning model and the strategy screening model, so that the highway maintenance task distribution efficiency is improved.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the computer program is executed. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of execution is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
With further reference to fig. 3, as an implementation of the method shown in fig. 1, the present application provides an embodiment of a system for intelligently allocating a road maintenance task based on road surface monitoring, where the embodiment of the system corresponds to the embodiment of the method shown in fig. 1, and the system may be specifically applied to various electronic devices.
As shown in fig. 3, the system 3 for intelligently allocating a highway maintenance task based on road surface monitoring according to this embodiment includes: the maintenance management system comprises a maintenance strategy integration and classification module 301, a disease level learning and evaluation module 302, a maintenance type and disease level corresponding module 303, a highway maintenance supervision center module 304, a new maintenance task establishing module 305 and a maintenance task intelligent distribution module 306. Wherein:
the maintenance strategy integration and classification module 301 is configured to screen out a plurality of road maintenance strategies based on a big data platform, perform difference numbering, and classify the plurality of road maintenance strategies according to different maintenance types, where the maintenance types include: a daily maintenance type, a regular maintenance type, a special maintenance type and an improvement project type;
a disease level learning evaluation module 302, configured to capture a plurality of road surface disease pictures and maintenance strategies corresponding to different disease pictures based on a web crawler, perform disease level learning evaluation on the plurality of road surface disease pictures based on a preset learning evaluation model, and identify maintenance types corresponding to the plurality of road surface disease pictures based on the maintenance strategies;
a maintenance type and disease level corresponding module 303, configured to obtain pavement disease pictures corresponding to a daily maintenance type, a periodic maintenance type, a special maintenance type and an improvement project type, and disease evaluation levels corresponding to the pavement disease pictures, respectively, and determine disease evaluation level ranges corresponding to the daily maintenance type, the periodic maintenance type, the special maintenance type and the improvement project type, respectively;
the highway maintenance supervision center module 304 is used for recording maintenance task receiver information in advance; the maintenance strategy screening model is also used for constructing a maintenance strategy screening model based on the association relationship among the maintenance type, the disease grade and the distinguishing numbers corresponding to the plurality of pavement maintenance strategies, and the maintenance strategy screening model is input into a highway maintenance supervision center;
a new maintenance task establishing module 305, configured to perform image acquisition based on a road patrol unmanned aerial vehicle, obtain a plurality of road pavement disease pictures, transmit the plurality of road pavement disease pictures as a test set into the learning evaluation model after learning, perform picture detection, and identify disease levels corresponding to the plurality of road pavement disease pictures, respectively, as new maintenance task parameters;
and the maintenance task intelligent allocation module 306 is configured to transmit the new maintenance task parameters to the maintenance strategy screening model, screen the maintenance types corresponding to the maintenance strategy screening model, if the new maintenance task corresponds to multiple maintenance types, improve the priority of the engineering type according to the daily maintenance type, the regular maintenance type, the special maintenance type and the engineering type, determine the maintenance strategy, match a new maintenance task bearer based on the maintenance task bearer information, and complete intelligent allocation of the highway maintenance task.
The system for carrying out intelligent distribution on the highway maintenance tasks based on road surface monitoring carries out maintenance strategy integration and classification through a big data platform, carries out disease level learning evaluation module based on machine learning, and through a new maintenance task establishing module and a maintenance task intelligent distribution module, new maintenance task parameters are transmitted into a maintenance strategy screening model, screens maintenance types corresponding to the maintenance strategy screening model, firstly carries out maintenance type determination according to maintenance type priority, then carries out maintenance strategy determination, and is matched with a new maintenance task bearer based on a highway maintenance supervision center module to complete intelligent distribution on the highway maintenance tasks.
With continuing reference to fig. 4, fig. 4 is a logic diagram of an implementation of an embodiment of a method for intelligently allocating a road maintenance task based on road surface monitoring according to the embodiment of the present application, including: recording maintenance task bearer information in a highway maintenance supervision center in advance; screening out a plurality of road surface maintenance strategies based on a big data platform, carrying out distinguishing numbering, and classifying the plurality of road surface maintenance strategies according to different maintenance types, wherein the maintenance types comprise: a daily maintenance type, a regular maintenance type, a special maintenance type and an improved project type; capturing a plurality of pavement disease pictures and maintenance strategies corresponding to different disease pictures based on a web crawler, respectively performing disease grade learning evaluation on the plurality of pavement disease pictures based on a preset learning evaluation model, and identifying maintenance types corresponding to the plurality of pavement disease pictures respectively based on the maintenance strategies; respectively obtaining pavement damage pictures corresponding to a daily maintenance type, a regular maintenance type, a special maintenance type and an improvement project type and a damage evaluation level corresponding to the pavement damage pictures, and determining the range of the damage evaluation level corresponding to the daily maintenance type, the regular maintenance type, the special maintenance type and the improvement project type; constructing a maintenance strategy screening model based on the association relationship among the maintenance type, the disease grade and the distinctive numbers corresponding to the plurality of pavement maintenance strategies, and inputting the maintenance strategy screening model into a highway maintenance supervision center; acquiring images based on a highway patrol unmanned aerial vehicle, acquiring a plurality of highway pavement disease pictures, transmitting the highway pavement disease pictures serving as a test set into a study evaluation model after study, detecting the pictures, and identifying disease levels respectively corresponding to the highway pavement disease pictures as new maintenance task parameters; and transmitting the new maintenance task parameters into the maintenance strategy screening model, screening the corresponding maintenance types, if the new maintenance is corresponding to multiple maintenance types, improving the priority of the project type according to the daily maintenance type, the regular maintenance type, the special maintenance type and the maintenance type, determining the maintenance type, then determining the maintenance strategy, matching a new maintenance task bearer based on the maintenance task bearer information, and completing intelligent distribution of the highway maintenance task.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
It is to be understood that the above-described embodiments are merely illustrative of some, but not restrictive, of the broad invention, and that the appended drawings illustrate preferred embodiments of the invention and do not limit the scope of the invention. This application is capable of embodiments in many different forms and the embodiments are provided so that this disclosure will be thorough and complete. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.
Claims (10)
1. The method for intelligently distributing the highway maintenance tasks based on the pavement monitoring is characterized by comprising the following steps of:
step 101, recording maintenance task bearer information in a highway maintenance supervision center in advance;
102, screening a plurality of road maintenance strategies based on a big data platform, carrying out distinguishing numbering, and classifying the plurality of road maintenance strategies according to different maintenance types, wherein the maintenance types comprise: a daily maintenance type, a regular maintenance type, a special maintenance type and an improvement project type;
103, grabbing a plurality of pavement disease pictures and maintenance strategies corresponding to different disease pictures based on a web crawler, respectively performing disease grade learning evaluation on the plurality of pavement disease pictures based on a preset learning evaluation model, and identifying maintenance types corresponding to the plurality of pavement disease pictures based on the maintenance strategies;
104, respectively obtaining pavement disease pictures corresponding to a daily maintenance type, a regular maintenance type, a special maintenance type and an improvement project type and a disease evaluation level corresponding to the pavement disease pictures, and determining disease evaluation level ranges respectively corresponding to the daily maintenance type, the regular maintenance type, the special maintenance type and the improvement project type;
105, constructing a maintenance strategy screening model based on the incidence relation among the maintenance type, the disease grade and the distinguishing numbers corresponding to the plurality of road surface maintenance strategies, and inputting the maintenance strategy screening model into a highway maintenance supervision center;
106, acquiring images based on a road patrol unmanned aerial vehicle, acquiring a plurality of road pavement damage pictures, transmitting the road pavement damage pictures serving as a test set into the study evaluation model after study, detecting the pictures, and identifying disease levels respectively corresponding to the road pavement damage pictures as new maintenance task parameters;
and 107, transmitting the new maintenance task parameters into the maintenance strategy screening model, screening maintenance types corresponding to the maintenance strategy screening model, if the new maintenance task corresponds to multiple maintenance types, improving the priority of the project type according to the daily maintenance type, the regular maintenance type, the special maintenance type and the like, determining the maintenance type, determining the maintenance strategy, matching a new maintenance task acceptor based on the maintenance task acceptor information, and completing intelligent distribution of the highway maintenance task.
2. The method for intelligently allocating a roadway maintenance task based on roadway monitoring of claim 1, wherein the entering of maintenance task bearer information in advance at a roadway maintenance supervision center at least comprises:
and inputting qualification information, sustainable maintenance type information and implementable maintenance strategy information of a maintenance task bearer.
3. The method for intelligently allocating the road maintenance tasks based on the road surface monitoring as claimed in claim 1, wherein the method for screening out a plurality of road surface maintenance strategies based on the big data platform and performing differential numbering comprises the following specific implementation modes:
pre-arranging a retrieval field related to highway maintenance implementation as a search parameter;
and sequentially putting the search parameters into a search box of a preset big data platform, searching to obtain a plurality of pavement maintenance implementation schemes, taking each implementation scheme as a pavement maintenance strategy, and performing difference numbering.
4. The method for intelligently allocating roadway maintenance tasks based on roadway monitoring of claim 1, wherein the plurality of roadway maintenance strategies are classified according to different maintenance types in a specific classification manner:
analyzing the character information in the plurality of road surface maintenance strategies based on a semantic recognition technology, and if the corresponding maintenance type is directly noted to be any one of a daily maintenance type, a regular maintenance type, a special maintenance type and an improved engineering type in the current road surface maintenance strategy through analysis, directly confirming the maintenance type corresponding to the current road surface maintenance strategy; if the maintenance type corresponding to the maintenance type is not definitely indicated to be any one of a daily maintenance type, a regular maintenance type, a special maintenance type and an improvement project type, determining the maintenance type corresponding to the current pavement maintenance strategy based on a preset associated word library, wherein the preset associated word library comprises four tables, and associated words in each table are respectively in one-to-one correspondence with the daily maintenance type, the regular maintenance type, the special maintenance type and the improvement project type.
5. The method for intelligently allocating the road maintenance tasks based on the road surface monitoring as claimed in claim 1, wherein the maintenance strategies corresponding to a plurality of road surface disease pictures and different disease pictures are captured based on a web crawler, and the specific implementation manner is as follows:
acquiring a plurality of pavement defect pictures by using a picture grabbing tool;
and searching a maintenance strategy corresponding to the picture similar to the retrieval picture, namely a plurality of maintenance strategies corresponding to the retrieval picture by taking the pavement damage picture as the retrieval picture and searching the picture based on the CNN neural network.
6. The method for intelligently allocating a road maintenance task based on road surface monitoring according to claim 1, wherein the disease level learning and evaluation is respectively performed on the plurality of road surface disease pictures based on a preset learning and evaluation model, and the specific learning manner is as follows:
dividing the plurality of pavement disease pictures into a training sample and a verification sample according to the proportion of 9;
the method comprises the steps of setting disease grades as four grades in advance, wherein the four grades are I, II, III and IV respectively, and setting disease grade classification conditions for the I, II, III and IV grades simultaneously;
the training samples are transmitted into a preset learning evaluation model for machine learning, and are divided into four grades of I, II, III and IV based on the disease grade classification conditions;
the verification sample is transmitted into a preset learning evaluation model after machine learning for cross verification, and if the verification sample can obtain results corresponding to different disease levels after being evaluated by the learning evaluation model, the evaluation is successful;
and constructing four difference sets according to four grades of I, II, III and IV, and adding the plurality of pavement disease pictures into the four difference sets according to learning evaluation results.
7. The method for intelligently allocating roadway maintenance tasks based on roadway monitoring of claim 1, wherein the maintenance strategy screens models, the screening step comprising:
step 201, starting the maintenance strategy screening model, and taking the disease levels respectively corresponding to the plurality of road pavement disease pictures as new maintenance task parameters;
step 202, determining a corresponding maintenance type based on the new maintenance task parameter, if the new maintenance task parameter is within the range of disease assessment levels belonging to a plurality of maintenance types, improving the priority of the project type according to the daily maintenance type, the regular maintenance type, the special maintenance type and the like, and selecting the maintenance type with high priority as the maintenance type corresponding to the new maintenance task parameter, namely the first maintenance type;
step 203, obtaining a plurality of maintenance strategies corresponding to the first maintenance type as a first strategy set, obtaining a plurality of maintenance strategies corresponding to the new maintenance task parameters as a second strategy set, directly taking the maintenance strategy as a final maintenance strategy if the first strategy set and the second strategy set have the same and unique maintenance strategies, and selecting the maintenance strategy based on the lowest cost as the final maintenance strategy if the first strategy set and the second strategy set have the same maintenance strategies;
and 204, acquiring the difference number corresponding to the final maintenance strategy, sending the difference number to the highway maintenance supervision center, and sending the maintenance strategies corresponding to the difference number to a bearer after the highway maintenance supervision center selects the bearer.
8. A method for intelligent allocation of road maintenance tasks based on road surface monitoring according to any of claims 1 to 7, wherein the road surface diseases comprise:
road surface crack, water accumulation, pit slot, broken plate, bulge and dust collection.
9. The method for intelligently allocating the road maintenance task based on the road surface monitoring as claimed in any one of claims 1 to 7, wherein before the disease level learning evaluation is respectively carried out on the road surface disease pictures based on the preset learning evaluation model, the method comprises the following steps:
acquiring an RGB (R, G, B) value of each pixel point in the pavement disease picture;
based on a floating point algorithm: gray =0.3R +0.59G +0.11B, and replacing the RGB (R, G, B) value of the corresponding pixel point with RGB (Gray, gray, gray);
and acquiring the replaced picture as a picture transmitted into a preset learning evaluation model.
10. System based on road surface monitoring carries out intelligent distribution to highway maintenance task, its characterized in that includes:
and the maintenance strategy integration and classification module is used for screening a plurality of road maintenance strategies based on a big data platform, carrying out distinguishing and numbering, and classifying the plurality of road maintenance strategies according to different maintenance types, wherein the maintenance types comprise: a daily maintenance type, a regular maintenance type, a special maintenance type and an improved project type;
the system comprises a disease level learning and evaluating module, a maintenance strategy judging module and a maintenance strategy judging module, wherein the disease level learning and evaluating module is used for grabbing a plurality of road disease pictures and maintenance strategies corresponding to different road disease pictures based on a web crawler, respectively performing disease level learning and evaluation on the plurality of road disease pictures based on a preset learning and evaluating model, and identifying maintenance types corresponding to the plurality of road disease pictures based on the maintenance strategies;
the maintenance type and disease level corresponding module is used for respectively obtaining a pavement disease picture corresponding to a daily maintenance type, a regular maintenance type, a special maintenance type and an improvement project type and a disease evaluation level corresponding to the pavement disease picture, and determining a disease evaluation level range corresponding to the daily maintenance type, the regular maintenance type, the special maintenance type and the improvement project type;
the highway maintenance supervision center module is used for recording maintenance task receiver information in advance; the maintenance strategy screening model is also used for constructing a maintenance strategy screening model based on the association relationship among the maintenance type, the disease grade and the distinguishing numbers corresponding to the plurality of pavement maintenance strategies, and the maintenance strategy screening model is input into a highway maintenance supervision center;
the new maintenance task establishing module is used for acquiring images based on a road patrol unmanned aerial vehicle, acquiring a plurality of road pavement disease images, transmitting the road pavement disease images into the study evaluation model after study as a test set, detecting the images, and identifying disease levels respectively corresponding to the road pavement disease images as new maintenance task parameters;
and the maintenance task intelligent distribution module is used for transmitting the new maintenance task parameters into the maintenance strategy screening model, screening the corresponding maintenance types, if the new maintenance task corresponds to multiple maintenance types, improving the priority of the project type according to the daily maintenance type, the regular maintenance type, the special maintenance type and the engineering type, firstly determining the maintenance type, then determining the maintenance strategy, matching a new maintenance task bearer based on the maintenance task bearer information, and completing the intelligent distribution of the highway maintenance tasks.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210867979.7A CN115345440A (en) | 2022-07-22 | 2022-07-22 | Method and system for intelligently distributing highway maintenance tasks based on pavement monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210867979.7A CN115345440A (en) | 2022-07-22 | 2022-07-22 | Method and system for intelligently distributing highway maintenance tasks based on pavement monitoring |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115345440A true CN115345440A (en) | 2022-11-15 |
Family
ID=83949517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210867979.7A Withdrawn CN115345440A (en) | 2022-07-22 | 2022-07-22 | Method and system for intelligently distributing highway maintenance tasks based on pavement monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115345440A (en) |
-
2022
- 2022-07-22 CN CN202210867979.7A patent/CN115345440A/en not_active Withdrawn
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111429726B (en) | Monitoring video illegal parking vehicle detection and management method and corresponding system | |
| CN104134080B (en) | A kind of road foundation collapses automatic testing method and system with slope failure | |
| CN113887412B (en) | Detection method, detection terminal, monitoring system and storage medium for pollution emission | |
| CN109344886B (en) | Occlusion number plate distinguishing method based on convolutional neural network | |
| CN111127465A (en) | Automatic generation method and system for bridge detection report | |
| CN111160432A (en) | Automatic classification method and system for panel production defects | |
| CN116805204B (en) | Intelligent plant monitoring method and system | |
| CN112991130A (en) | Artificial intelligence-based city management event processing method and device | |
| CN114662208B (en) | Construction visualization system and method based on Bim technology | |
| CN112233421A (en) | Intelligent city intelligent traffic monitoring system based on machine vision | |
| CN110164136B (en) | Fake-licensed vehicle identification method | |
| CN115035328A (en) | Converter image increment automatic machine learning system and establishment training method thereof | |
| WO2022034798A1 (en) | Scrap discrimination system and scrap discrimination method | |
| CN109001210B (en) | System and method for detecting aging and cracking of sealing rubber strip of civil air defense door | |
| CN115345440A (en) | Method and system for intelligently distributing highway maintenance tasks based on pavement monitoring | |
| CN116168356B (en) | Vehicle damage judging method based on computer vision | |
| CN107748866B (en) | Illegal parking automatic identification method and device | |
| CN111062827A (en) | Engineering supervision method based on artificial intelligence mode | |
| CN112633163B (en) | Detection method for realizing illegal operation vehicle detection based on machine learning algorithm | |
| KR102435435B1 (en) | System for searching numbers of vehicle and pedestrian based on artificial intelligence | |
| CN113888881A (en) | Method and system for analyzing and planning urban roadside parking resources based on microcomputer | |
| CN112149562A (en) | Road intelligent maintenance system and method based on multifunctional rod | |
| CN110827264A (en) | Evaluation system for apparent defects of concrete member | |
| CN112560562A (en) | Method, apparatus and storage medium for identifying violations | |
| CN114022826B (en) | Block chain-based rail detection method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20221115 |
|
| WW01 | Invention patent application withdrawn after publication |