CN118942038B - Method and system for measuring distance of hazardous sources at construction sites based on error correction model - Google Patents
Method and system for measuring distance of hazardous sources at construction sites based on error correction model Download PDFInfo
- Publication number
- CN118942038B CN118942038B CN202411031623.5A CN202411031623A CN118942038B CN 118942038 B CN118942038 B CN 118942038B CN 202411031623 A CN202411031623 A CN 202411031623A CN 118942038 B CN118942038 B CN 118942038B
- Authority
- CN
- China
- Prior art keywords
- ranging
- error correction
- model
- result
- error
- 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.)
- Active
Links
- 238000012937 correction Methods 0.000 title claims abstract description 173
- 238000010276 construction Methods 0.000 title claims abstract description 129
- 238000000034 method Methods 0.000 title claims abstract description 55
- 231100001261 hazardous Toxicity 0.000 title 1
- 238000012549 training Methods 0.000 claims abstract description 169
- 230000007613 environmental effect Effects 0.000 claims abstract description 47
- 238000011156 evaluation Methods 0.000 claims abstract description 47
- 238000005259 measurement Methods 0.000 claims abstract description 37
- 238000012216 screening Methods 0.000 claims abstract description 37
- 238000010801 machine learning Methods 0.000 claims abstract description 29
- 230000006870 function Effects 0.000 claims description 25
- 230000006978 adaptation Effects 0.000 claims description 22
- 238000007726 management method Methods 0.000 claims description 18
- 238000012512 characterization method Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 13
- 238000004088 simulation Methods 0.000 claims description 13
- 230000003993 interaction Effects 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000013144 data compression Methods 0.000 claims description 7
- 230000000007 visual effect Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000004806 packaging method and process Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000010191 image analysis Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 5
- 230000009286 beneficial effect Effects 0.000 description 8
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063114—Status monitoring or status determination for a person or group
-
- 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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- 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
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Multimedia (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Computer Security & Cryptography (AREA)
- Radar Systems Or Details Thereof (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a construction operation site dangerous source ranging method and system based on an error correction model, comprising the steps of retrieving training samples based on a database, screening the training samples, analyzing the screened training samples, and extracting corresponding ranging results and error evaluation; the method comprises the steps of training a machine learning model based on a ranging result and error evaluation, constructing an error correction model, associating the error correction model with a ranging terminal in an execution flow, controlling the ranging terminal to perform differential ranging on a dangerous source based on environmental characteristics of a construction operation site, and performing error correction on the differential ranging result based on the error correction model after associating the execution flow. The accuracy and the reliability of the distance detection of the dangerous sources are ensured, the accurate and effective understanding of the distribution situation of the dangerous sources according to the distance measurement result is also facilitated, and the safe operation of the construction operation site is ensured.
Description
Technical Field
The invention relates to the technical field of ranging, in particular to a construction operation site dangerous source ranging method and system based on an error correction model.
Background
Various dangerous sources exist in the construction operation site, such as falling at a high place, striking objects and the like, which threatens the safety of operators, and the effective ranging of the dangerous sources can improve the safety coefficient of the construction operation site and ensure the safety of the operators;
however, the traditional ranging method mainly relies on a mode of combining a machine and personnel to perform dangerous source ranging operation, and is easily influenced by external environment factors, so that errors exist in ranging of dangerous sources, and accurate assessment of the dangerous sources is influenced;
therefore, in order to overcome the defects, the invention provides a construction operation site hazard source ranging method and system based on an error correction model.
Disclosure of Invention
The invention provides a construction operation site dangerous source ranging method and system based on an error correction model, which are used for accurately and effectively determining a ranging result and error evaluation of a training sample by calling a corresponding training sample from a database and screening and analyzing the training sample, providing data support for constructing the error correction model, training a machine learning model through the obtained ranging result and error evaluation, reliably constructing the error correction model, guaranteeing error correction of the ranging result, controlling a ranging terminal to perform differential ranging on a dangerous source according to environmental characteristics of a construction operation site, and effectively correcting the obtained differential ranging result through the error correction model, thereby ensuring the accuracy and reliability of distance detection on the dangerous source, facilitating accurate and effective understanding of the distribution situation of the dangerous source according to the ranging result, and ensuring safe operation of the construction operation site.
The invention provides a construction operation site hazard source ranging method based on an error correction model, which comprises the following steps:
Step 1, retrieving training samples based on a database, screening the training samples, analyzing the screened training samples, and extracting corresponding ranging results and error evaluation;
training a machine learning model based on a ranging result and error evaluation, constructing an error correction model, and correlating the error correction model with an execution flow of a ranging terminal;
and 3, controlling the ranging terminal to perform differential ranging on the dangerous sources based on the environmental characteristics of the construction operation site, and performing error correction on a differential ranging result based on an error correction model after the process association is performed.
Preferably, in step 1, a training sample is retrieved based on a database, which includes:
Acquiring a sample retrieval task based on a management terminal, analyzing the sample retrieval task, and determining retrieval dimensions of training samples and retrieval indexes under each retrieval dimension;
Determining a database corresponding to each dimension based on the retrieval dimension, and traversing cache data in the corresponding database based on the retrieval index;
Locking the cache data to be called in each database based on the traversing result, performing data compression on the cache data to be called, generating dimension labels based on the calling dimension, and performing dimension marking on the data compression result;
and carrying out distributed calling on the cache data to be called in each database based on the dimension marking result to obtain a training sample.
Preferably, in step 1, a method for measuring a dangerous source in a construction operation site based on an error correction model includes:
acquiring the obtained training samples, and acquiring data screening events of different types of training samples from a management terminal based on sample attributes of the training samples;
Determining event center characteristics and screening indexes based on the data screening event, and analyzing training samples of corresponding types based on the screening indexes to obtain target distances between sample centers of different training samples and the event center characteristics;
determining the attribution degree of each training sample in different types of training samples relative to the event center characteristics based on the target distance, and screening each training sample of different types of training samples based on the relative magnitude relation between the attribution degree and a preset threshold value.
Preferably, in step 1, analyzing the screened training sample, extracting a corresponding ranging result and error evaluation, including:
Acquiring a screened training sample, and splitting the training sample based on the text structure of the training sample;
Extracting key data of each part based on a structure splitting result, carrying out semantic analysis on the key data based on a neural network, and determining abstract information of the key data;
And determining the corresponding ranging result and error evaluation in the training samples based on the abstract information, and binding the ranging result and error evaluation corresponding to each training sample based on a single alignment principle.
Preferably, in step 2, training a machine learning model based on a ranging result and error evaluation to construct an error correction model, including:
Retrieving a machine learning model structure from a model library based on model construction requirements, and initializing parameters of the machine learning model structure to obtain a target model structure;
determining an error measurement index and a regularization parameter value of an error correction model based on a model construction task, and generating an initial model loss function of a target model structure based on the error measurement index;
combining the regularization parameter value with the initial model loss function to obtain a model loss function;
Respectively analyzing the ranging results and the error evaluation of different training samples to obtain a distance characterization value and a distance error value corresponding to the ranging results and the error evaluation, and performing difference display on the distance characterization value and the distance error value of different training samples of the same ranging type in the same coordinate system;
Obtaining a ranging index value of each ranging type, and carrying out same-object mapping display in a difference display result by taking the ranging index value as an associated influence factor;
Obtaining parameter comparison groups of different training samples of the same ranging type based on the same object mapping display result, and determining the interaction weight among the distance characterization value, the distance error value and the associated influence factors in each training sample based on the parameter comparison groups;
Performing weighted comprehensive analysis on the interaction weight of each training sample based on the parameter comparison group to obtain a distance error correction strategy of each ranging type;
sequentially carrying out iterative training on the target model structure based on a distance error correction strategy of each ranging type, and acquiring value range distribution characteristics of a model loss function based on an iterative training process;
and determining the minimum value of the model loss function based on the value range distribution characteristics, taking an iteration training result corresponding to the minimum value as an error correction level of the current ranging type, and packaging the error correction levels corresponding to different ranging types in a target model structure to obtain an error correction model.
Preferably, in step 2, the method for measuring the dangerous source of the construction operation site based on the error correction model correlates the execution flow of the error correction model and the distance measuring terminal, and includes:
acquiring an obtained error correction model, and determining a deployment environment of the error correction model based on operation requirements;
acquiring environmental characteristics of a deployment environment, and determining environment adaptation parameters of an error correction model based on the environmental characteristics;
Performing first parameter adaptation on the error correction model based on the environment adaptation parameters, acquiring equipment attributes of the ranging terminal, and performing second parameter adaptation on a model interface of the error correction model based on the equipment attributes;
And determining an error correction model and execution logic of the ranging terminal based on the ranging execution logic, and associating the error correction model after the first parameter adaptation and the second parameter adaptation with the execution flow of the ranging terminal based on the execution logic.
Preferably, in step 3, the method for measuring the dangerous sources in the construction operation site based on the error correction model controls the distance measuring terminal to measure the distances of the dangerous sources differently based on the environmental characteristics of the construction operation site, and includes:
Acquiring an environment image of a construction operation site, analyzing the environment image, and determining construction service and environment structure of the construction operation site;
The method comprises the steps of obtaining environmental characteristics of a construction operation site based on construction service and an environmental structure, extracting a recorded object in an environmental image based on an environmental image analysis result, and analyzing object attributes of the recorded object based on service execution standards to obtain a dangerous source;
and determining a corresponding ranging scheme based on the environmental characteristics and the dangerous sources, and controlling the ranging terminal to perform differential ranging on the corresponding dangerous sources according to the ranging scheme.
Preferably, in step 3, error correction is performed on the differential ranging result based on the error correction model after the execution flow association, which includes:
obtaining the obtained differential ranging result, and determining a ranging scheme source corresponding to the differential ranging result;
Respectively inputting a difference ranging result and a corresponding ranging scheme source into an error correction model, calling a corresponding error correction layer according to the ranging scheme source based on the input result to analyze the difference ranging result, and determining a correction value of the difference ranging result;
correcting the difference ranging result based on the correction value, and attributing and marking the corrected difference ranging result based on the identity information of the dangerous source;
and feeding back the corrected differential ranging result to the management terminal based on the attribution marking result.
Preferably, the method for measuring the dangerous source distance of the construction operation site based on the error correction model feeds back the corrected differential distance measurement result to the management terminal based on the attribution marking result comprises the following steps:
extracting multidimensional features of the construction operation site based on the environmental features to obtain a three-dimensional structure of the construction operation site, and virtually reconstructing the construction operation site based on the three-dimensional structure to obtain a three-dimensional simulation model of the construction operation site;
Acquiring the actual geographic position of the ranging terminal on a construction operation site, and performing first marking in a three-dimensional simulation model based on the actual geographic position;
Acquiring the corrected difference ranging result, and determining the relative position of the dangerous source and the ranging terminal based on the first marking result and the corrected difference ranging result;
determining a target position of the hazard source based on the relative position, and performing a second marking in the three-dimensional simulation model based on the target position;
and obtaining a three-dimensional danger source visual model based on the second marking result, and recording and retaining the three-dimensional danger source visual model.
The invention provides a construction operation site dangerous source ranging system based on an error correction model, which comprises the following components:
The sample acquisition and processing module is used for acquiring training samples based on the database, screening the training samples, analyzing the screened training samples and extracting corresponding ranging results and error evaluation;
The model building module is used for training the machine learning model based on the ranging result and the error evaluation, building an error correction model and correlating the error correction model with the ranging terminal in the execution flow;
The ranging and correcting module is used for controlling the ranging terminal to perform differential ranging on the dangerous sources based on the environmental characteristics of the construction operation, and performing error correction on the differential ranging result based on the error correction model after the execution flow association.
Compared with the prior art, the invention has the following beneficial effects:
1. The method has the advantages that the corresponding training samples are called from the database, the training samples are screened and analyzed, the distance measurement result and error evaluation of the training samples are accurately and effectively determined, data support is provided for constructing an error correction model, the machine learning model is trained through the obtained distance measurement result and error evaluation, reliable construction of the error correction model is achieved, error correction is guaranteed for the distance measurement result, finally, the distance measurement terminal is controlled to conduct differential distance measurement on the dangerous source according to the environmental characteristics of a construction operation site, the obtained differential distance measurement result is effectively corrected through the error correction model, accuracy and reliability of distance detection on the dangerous source are guaranteed, accurate and effective understanding of the distribution situation of the dangerous source is facilitated according to the distance measurement result, and safe operation of the construction operation site is guaranteed.
2. The sample retrieval task acquired by the management terminal is analyzed, so that the retrieval dimension and the retrieval index under each retrieval dimension are accurately and effectively determined, the cache data to be retrieved under each dimension are effectively retrieved according to the retrieval dimension and the retrieval index, the training sample is accurately and effectively acquired, and reliable data support is provided for constructing an error correction model.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application. The objects and other advantages of the application may be realized and obtained by means of the instrumentalities particularly pointed out in the specification.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of a construction operation site hazard source ranging method based on an error correction model in an embodiment of the invention;
FIG. 2 is a flowchart of step 1 in a construction operation site hazard source ranging method based on an error correction model according to an embodiment of the present invention;
Fig. 3 is a block diagram of a construction operation site hazard source ranging system based on an error correction model according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
Example 1:
The embodiment provides a construction operation site hazard source ranging method based on an error correction model, as shown in fig. 1, comprising the following steps:
Step 1, retrieving training samples based on a database, screening the training samples, analyzing the screened training samples, and extracting corresponding ranging results and error evaluation;
training a machine learning model based on a ranging result and error evaluation, constructing an error correction model, and correlating the error correction model with an execution flow of a ranging terminal;
and 3, controlling the ranging terminal to perform differential ranging on the dangerous sources based on the environmental characteristics of the construction operation site, and performing error correction on a differential ranging result based on an error correction model after the process association is performed.
In this embodiment, the ranging result refers to a specific ranging distance corresponding to each training sample, that is, a distance between the determined dangerous source and the ranging device.
In this embodiment, the error evaluation refers to an error between an actual distance and a measured distance, which is made based on a ranging result.
In this embodiment, the machine learning model is a model frame set in advance.
In this embodiment, performing the flow association refers to docking the error correction model with the ranging terminal, so as to facilitate direct input of the ranging result obtained by the ranging terminal to the error correction model for performing the result correction process.
In this embodiment, the environmental characteristics refer to information such as the type of construction at the construction site, the type of building included in the construction site, and the like.
In this embodiment, the hazard source refers to a hazard factor that affects normal construction, which may be a fire or the like, existing in the construction work site.
In this embodiment, the differential ranging refers to selecting a suitable ranging method according to the environmental characteristics and the type of the dangerous source to perform corresponding ranging, including ultrasonic ranging, laser ranging, infrared ranging, wireless signal ranging, and the like.
The working principle and the beneficial effects of the technical scheme are that the corresponding training samples are called from the database, the training samples are screened and analyzed, the distance measurement result and the error evaluation of the training samples are accurately and effectively determined, data support is provided for constructing an error correction model, the machine learning model is trained through the obtained distance measurement result and the error evaluation, reliable construction of the error correction model is achieved, the error correction of the distance measurement result is guaranteed, finally, the distance measurement terminal is controlled to conduct differential distance measurement on the dangerous source according to the environmental characteristics of the construction operation site, the obtained differential distance measurement result is effectively corrected through the error correction model, the accuracy and the reliability of distance detection on the dangerous source are guaranteed, the accurate and effective understanding of the distribution situation of the dangerous source according to the distance measurement result is facilitated, and the safe operation of the construction operation site is guaranteed.
Example 2:
on the basis of embodiment 1, the present embodiment provides a construction operation site hazard source ranging method based on an error correction model, as shown in fig. 2, in step 1, a training sample is called based on a database, including:
step 101, acquiring a sample retrieval task based on a management terminal, analyzing the sample retrieval task, and determining retrieval dimensions of training samples and retrieval indexes under each retrieval dimension;
102, determining a database corresponding to each dimension based on the retrieval dimension, and traversing cache data in the corresponding database based on the retrieval index;
Step 103, locking the cache data to be called in each database based on the traversing result, performing data compression on the cache data to be called, generating dimension labels based on the calling dimension, and performing dimension marking on the data compression result;
And 104, carrying out distributed retrieval on the cache data to be retrieved in each database based on the dimension marking result to obtain a training sample.
In this embodiment, the sample retrieval task is set in advance by the management terminal, and is used for characterizing the type of data to be retrieved and the corresponding retrieval amount.
In this embodiment, the dimension to be called refers to the type of data to be called, and specifically may be data corresponding to ultrasonic ranging, data corresponding to infrared ranging, data corresponding to laser ranging, and data corresponding to wireless signal ranging.
In this embodiment, the calling index refers to time information and the like required to be called in each calling dimension, and is used for locking the reference basis of the data required to be called.
In this embodiment, the dimension marking refers to marking the data compression result in a corresponding type, so as to facilitate distinguishing between different types of cache data to be called.
The technical scheme has the advantages that the sample retrieval task acquired by the management terminal is analyzed, the retrieval dimension and the retrieval index under each retrieval dimension are accurately and effectively determined, the cache data to be retrieved under each dimension are finally and effectively retrieved according to the retrieval dimension and the retrieval index, the training sample is accurately and effectively acquired, and reliable data support is provided for constructing an error correction model.
Example 3:
On the basis of embodiment 1, the present embodiment provides a construction operation site hazard source ranging method based on an error correction model, in step 1, a training sample is screened, including:
acquiring the obtained training samples, and acquiring data screening events of different types of training samples from a management terminal based on sample attributes of the training samples;
Determining event center characteristics and screening indexes based on the data screening event, and analyzing training samples of corresponding types based on the screening indexes to obtain target distances between sample centers of different training samples and the event center characteristics;
determining the attribution degree of each training sample in different types of training samples relative to the event center characteristics based on the target distance, and screening each training sample of different types of training samples based on the relative magnitude relation between the attribution degree and a preset threshold value.
In this embodiment, the sample attribute refers to the sample type of the training sample.
In this embodiment, the data screening event refers to the requirement of screening different types of training samples, i.e., the purpose of screening data. For example, data integrity may be required, data parameters may be retained, etc.
In this embodiment, the event center feature refers to a feature capable of characterizing the core gist of the data screening event, i.e., a parameter capable of characterizing the purpose of data screening.
In this embodiment, the screening index refers to information that needs to be referred to when screening the training samples.
In this embodiment, the sample center refers to the core data characteristics of the training sample, thereby facilitating a determination by the sample center as to whether the training sample can be retained.
In this embodiment, the target distance is used to characterize the probability that the sample center belongs to the event center feature, and a smaller distance indicates that the corresponding training sample belongs to the data screening event.
In this embodiment, the attribution degree is a probability for representing the consistency of the event center characteristics of different training samples and the data screening event, wherein the preset threshold is set in advance.
The working principle and the beneficial effects of the technical scheme are that through determining the data screening event of the training sample and determining the event center characteristics corresponding to the data screening event, the accurate and effective determination of the event center characteristics and the target distances of the sample centers of different training samples is realized, and finally, the locking of the attribution degree of the training sample relative to the data screening event according to the target distances is realized, so that the accurate and effective screening of the training sample is realized, and the accuracy and the reliability of the training sample are ensured.
Example 4:
on the basis of embodiment 1, the present embodiment provides a construction operation site hazard source ranging method based on an error correction model, in step 1, analyzing a screened training sample, extracting a corresponding ranging result and error evaluation, including:
Acquiring a screened training sample, and splitting the training sample based on the text structure of the training sample;
Extracting key data of each part based on a structure splitting result, carrying out semantic analysis on the key data based on a neural network, and determining abstract information of the key data;
And determining the corresponding ranging result and error evaluation in the training samples based on the abstract information, and binding the ranging result and error evaluation corresponding to each training sample based on a single alignment principle.
In this embodiment, the text structure refers to the composition of the training samples, and may be, for example, a text header, a data content segment, and the like.
In this embodiment, the key data refers to each segment of core data that is not part of the training sample after the training sample is structurally split.
In this embodiment, the summary information refers to data parameters that can characterize the gist of the key information.
In this embodiment, the single alignment principle refers to a one-to-one correspondence between the ranging result and the error evaluation for each training sample.
The working principle and the beneficial effects of the technical scheme are that the training samples after screening are analyzed, the training samples are split, the key information of each split part is extracted, the distance measurement result and the error evaluation of the training samples are accurately and effectively determined according to the key information, the machine learning model is conveniently and effectively trained, and convenience and guarantee are provided for constructing the error correction model.
Example 5:
on the basis of embodiment 1, the present embodiment provides a construction operation site hazard source ranging method based on an error correction model, in step 2, training a machine learning model based on a ranging result and error evaluation, and constructing an error correction model, including:
Retrieving a machine learning model structure from a model library based on model construction requirements, and initializing parameters of the machine learning model structure to obtain a target model structure;
determining an error measurement index and a regularization parameter value of an error correction model based on a model construction task, and generating an initial model loss function of a target model structure based on the error measurement index;
combining the regularization parameter value with the initial model loss function to obtain a model loss function;
Respectively analyzing the ranging results and the error evaluation of different training samples to obtain a distance characterization value and a distance error value corresponding to the ranging results and the error evaluation, and performing difference display on the distance characterization value and the distance error value of different training samples of the same ranging type in the same coordinate system;
Obtaining a ranging index value of each ranging type, and carrying out same-object mapping display in a difference display result by taking the ranging index value as an associated influence factor;
Obtaining parameter comparison groups of different training samples of the same ranging type based on the same object mapping display result, and determining the interaction weight among the distance characterization value, the distance error value and the associated influence factors in each training sample based on the parameter comparison groups;
Performing weighted comprehensive analysis on the interaction weight of each training sample based on the parameter comparison group to obtain a distance error correction strategy of each ranging type;
sequentially carrying out iterative training on the target model structure based on a distance error correction strategy of each ranging type, and acquiring value range distribution characteristics of a model loss function based on an iterative training process;
and determining the minimum value of the model loss function based on the value range distribution characteristics, taking an iteration training result corresponding to the minimum value as an error correction level of the current ranging type, and packaging the error correction levels corresponding to different ranging types in a target model structure to obtain an error correction model.
In this embodiment, the model construction requirements are known in advance for characterizing the construction requirements and the definition conditions for the error correction model, and the like.
In this embodiment, parameter initialization refers to unifying model parameters of a machine learning model structure, so as to facilitate targeted training of the initialized machine learning model structure, where the target model structure is a result obtained after parameter initialization of the machine learning model structure.
In this embodiment, the model building tasks are known in advance for characterizing the building criteria and requirements for the error correction model.
In this embodiment, the error metrics are data parameters defining the performance of the error correction model, including accuracy, processing efficiency, and the like.
In this embodiment, the regularized parameter values are parameters for preventing the model from being over fitted during the training process, for assisting in the training of the model.
In this embodiment, the initial model loss function refers to a model loss function generated according to an error metric, and no regularization parameter value is added.
In this embodiment, the model loss function is used to calculate the performance loss that the model will exhibit when training the target model structure.
In this embodiment, the distance characterization value and the distance error value refer to specific numerical values determined according to the ranging result and the error evaluation result.
In this embodiment, the ranging index value refers to interference factors, such as environment and obstacles, which are characterized by training samples and are received when ranging from dangerous sources.
In this embodiment, the same object mapping display refers to associating the related influence factors with the corresponding monitoring objects in the difference display result, so as to facilitate determining the influence factors existing in ranging of different dangerous sources.
In this embodiment, the interaction weight is used to characterize the degree of mutual definition between the distance characterization value, the distance error value, and the associated influencing factors in each training sample.
In this embodiment, the value domain distribution feature is used to characterize the model performance loss distribution situation obtained by calculating each training result through the model loss function in the iterative training process of the target model structure.
In this embodiment, the error correction hierarchy refers to training results for each ranging type as part of the final error correction model.
The working principle and the beneficial effects of the technical scheme are that the corresponding machine learning model structure is obtained from the model library, the obtained machine learning model structure is analyzed, the accurate and effective acquisition of the model loss function is realized, secondly, the ranging results and the error evaluation of different training samples are analyzed, the accurate and effective determination of the distance characterization values and the distance error values corresponding to the different training samples is realized, meanwhile, the associated influence factors corresponding to the training samples are comprehensively considered, the accurate and effective determination of the distance characterization values, the distance error values and the interaction weights among the associated influence factors of the different training samples is realized, finally, the distance error correction strategy corresponding to each ranging type is determined through the interaction weights, the iterative training of the target model structure is realized according to the distance error correction strategy, the reliable and effective error correction model is obtained according to the iterative training results, the reliable guarantee is provided for the ranging of the dangerous sources of the construction operation site, and the effective understanding of the dangerous source positions of the construction operation site is also convenient.
Example 6:
On the basis of embodiment 1, the present embodiment provides a construction operation site hazard source ranging method based on an error correction model, in step 2, the error correction model and a ranging terminal are associated with each other in execution flow, including:
acquiring an obtained error correction model, and determining a deployment environment of the error correction model based on operation requirements;
acquiring environmental characteristics of a deployment environment, and determining environment adaptation parameters of an error correction model based on the environmental characteristics;
Performing first parameter adaptation on the error correction model based on the environment adaptation parameters, acquiring equipment attributes of the ranging terminal, and performing second parameter adaptation on a model interface of the error correction model based on the equipment attributes;
And determining an error correction model and execution logic of the ranging terminal based on the ranging execution logic, and associating the error correction model after the first parameter adaptation and the second parameter adaptation with the execution flow of the ranging terminal based on the execution logic.
In this embodiment, the operating requirements are known in advance, and are used to characterize the deployment requirements of the error correction model, including the deployment environmental conditions, and the conditions for interfacing with other terminals, etc.
In this embodiment, the environmental characteristics refer to specific situations of the environment where the error correction model needs to be deployed, including compatibility with other applications, and the like.
In this embodiment, the environment adaptation parameters refer to deployment parameters that need to be performed when the error correction model is deployed in a deployment environment, so as to ensure that the error correction model can be effectively deployed in a corresponding deployment environment, where the first parameter adaptation is a specific parameter adjustment process for the error correction model according to the environment adaptation parameters.
In this embodiment, the device attribute refers to a terminal type of the ranging terminal and a specific operation condition corresponding to the ranging terminal in operation.
In this embodiment, the second parameter adaptation refers to parameter adjustment of the model interface of the error correction model according to the device attribute of the ranging terminal, so as to ensure that the error correction model can be accurately and effectively docked with the ranging terminal.
In this embodiment, the execution logic is used to characterize the working order between the ranging terminal and the error correction model.
The working principle and the beneficial effects of the technical scheme are that the environment parameters and the model interfaces are adapted to the error correction model, and the adapted error correction model and the ranging terminal are accurately and effectively associated, so that the distance detected by the ranging terminal is conveniently transmitted to the error correction model for timely and effectively analysis, and the accuracy and the reliability of the finally obtained dangerous source ranging are ensured.
Example 7:
On the basis of embodiment 1, the present embodiment provides a method for ranging dangerous sources on a construction operation site based on an error correction model, in step 3, a ranging terminal is controlled to perform differential ranging on the dangerous sources based on environmental features of the construction operation site, including:
Acquiring an environment image of a construction operation site, analyzing the environment image, and determining construction service and environment structure of the construction operation site;
The method comprises the steps of obtaining environmental characteristics of a construction operation site based on construction service and an environmental structure, extracting a recorded object in an environmental image based on an environmental image analysis result, and analyzing object attributes of the recorded object based on service execution standards to obtain a dangerous source;
and determining a corresponding ranging scheme based on the environmental characteristics and the dangerous sources, and controlling the ranging terminal to perform differential ranging on the corresponding dangerous sources according to the ranging scheme.
In this embodiment, the construction service refers to a type of construction currently performed at a construction site, and may be, for example, a building type, a fire fighting type, or the like.
In this embodiment, the environmental structure refers to whether there is obstacle shielding or other object placement conditions on the construction site.
In this embodiment, the environmental characteristics refer to parameters which are obtained by integrating the construction service and the environmental structure of the construction operation site and can represent specific conditions of the construction operation site.
In this embodiment, the recording object refers to various types of articles included in the environment image, including dangerous sources and other non-dangerous articles, and the like.
In this embodiment, the service execution standard is set in advance, and is used to characterize the security rule to be followed by the construction job site.
In this embodiment, the object attribute refers to an object type of each recording object, a form existing in a construction job site, and the like.
In this embodiment, determining the corresponding ranging scheme based on the environmental characteristics and the dangerous source refers to determining a suitable ranging method according to the types of the environmental characteristics and the dangerous source, and may be one of ultrasonic ranging, infrared ranging, laser ranging, and wireless signal ranging.
The working principle and the beneficial effects of the technical scheme are that the environment image of the construction operation site is analyzed, so that the environment characteristics and the dangerous sources of the construction operation site are accurately and effectively determined, the distance measurement scheme is accurately and effectively determined according to the environment characteristics and the dangerous sources, the distance measurement terminal is controlled to accurately and effectively perform the distance measurement operation on the dangerous sources according to the distance measurement scheme, and the accuracy and the reliability of the distance measurement are ensured.
Example 8:
On the basis of embodiment 1, the present embodiment provides a construction operation site hazard source ranging method based on an error correction model, in step 3, error correction is performed on a differential ranging result based on an error correction model after performing flow association, including:
obtaining the obtained differential ranging result, and determining a ranging scheme source corresponding to the differential ranging result;
Respectively inputting a difference ranging result and a corresponding ranging scheme source into an error correction model, calling a corresponding error correction layer according to the ranging scheme source based on the input result to analyze the difference ranging result, and determining a correction value of the difference ranging result;
correcting the difference ranging result based on the correction value, and attributing and marking the corrected difference ranging result based on the identity information of the dangerous source;
and feeding back the corrected differential ranging result to the management terminal based on the attribution marking result.
In this embodiment, the ranging scheme source refers to a specific ranging method adopted by the differential ranging result.
In this embodiment, the identity information refers to a parameter capable of characterizing the type of the hazard source, for example, the type of the hazard source, etc.
In this embodiment, the attribution marking refers to marking the corrected differential ranging result according to the obtained identity information, so as to aim at different dangerous sources in the construction operation site.
The technical scheme has the advantages that the obtained differential ranging result and the corresponding ranging scheme source are input into the error correction model for processing, so that the correct value corresponding to the ranging result is accurately and effectively determined, the corrected differential ranging result is marked according to the identity information of the dangerous source, and the marked result is fed back to the management terminal, so that the management terminal can accurately and effectively know the dangerous source condition in the construction operation site, and can timely position the dangerous source when the abnormal condition occurs, and the safe operation of the construction operation site is ensured.
Example 9:
On the basis of embodiment 8, the present embodiment provides a construction operation site hazard source ranging method based on an error correction model, and the corrected differential ranging result is fed back to a management terminal based on a attribution marking result, including:
extracting multidimensional features of the construction operation site based on the environmental features to obtain a three-dimensional structure of the construction operation site, and virtually reconstructing the construction operation site based on the three-dimensional structure to obtain a three-dimensional simulation model of the construction operation site;
Acquiring the actual geographic position of the ranging terminal on a construction operation site, and performing first marking in a three-dimensional simulation model based on the actual geographic position;
Acquiring the corrected difference ranging result, and determining the relative position of the dangerous source and the ranging terminal based on the first marking result and the corrected difference ranging result;
determining a target position of the hazard source based on the relative position, and performing a second marking in the three-dimensional simulation model based on the target position;
and obtaining a three-dimensional danger source visual model based on the second marking result, and recording and retaining the three-dimensional danger source visual model.
In this embodiment, the multi-dimensional feature extraction refers to feature extraction of different angles for the construction site, in order to perform simulated reconstruction for the construction site.
In this embodiment, the first marking refers to marking in the three-dimensional virtual model according to the opportunistic geographical position of the ranging terminal in the construction work site.
In this embodiment, the target location refers to a specific location of the hazard source in the construction work site.
In this embodiment, the second marking means marking the specific location of the hazard source in the three-dimensional simulation model.
In this embodiment, the three-dimensional hazard visualization model refers to a final model obtained by marking the hazard in the obtained three-dimensional simulation model.
The technical scheme has the advantages that the three-dimensional structure of the construction operation site is accurately and effectively determined by extracting the multidimensional features of the construction operation site, the construction operation site is virtually reconstructed according to the obtained three-dimensional structure, the three-dimensional simulation model of the construction operation site is accurately and effectively built, finally, the positions of the ranging terminal and the dangerous source are marked in the obtained three-dimensional simulation model, the three-dimensional dangerous source visualization model is accurately and effectively built, the management terminal is convenient to effectively know the specific position distribution condition of the dangerous source, and accordingly the safety coefficient of the construction operation site is improved.
Example 10:
The embodiment provides a construction operation site hazard source ranging system based on an error correction model, as shown in fig. 3, including:
The sample acquisition and processing module is used for acquiring training samples based on the database, screening the training samples, analyzing the screened training samples and extracting corresponding ranging results and error evaluation;
The model building module is used for training the machine learning model based on the ranging result and the error evaluation, building an error correction model and correlating the error correction model with the ranging terminal in the execution flow;
The ranging and correcting module is used for controlling the ranging terminal to perform differential ranging on the dangerous sources based on the environmental characteristics of the construction operation, and performing error correction on the differential ranging result based on the error correction model after the execution flow association.
The working principle and the beneficial effects of the technical scheme are that the corresponding training samples are called from the database, the training samples are screened and analyzed, the distance measurement result and the error evaluation of the training samples are accurately and effectively determined, data support is provided for constructing an error correction model, the machine learning model is trained through the obtained distance measurement result and the error evaluation, reliable construction of the error correction model is achieved, the error correction of the distance measurement result is guaranteed, finally, the distance measurement terminal is controlled to conduct differential distance measurement on the dangerous source according to the environmental characteristics of the construction operation site, the obtained differential distance measurement result is effectively corrected through the error correction model, the accuracy and the reliability of distance detection on the dangerous source are guaranteed, the accurate and effective understanding of the distribution situation of the dangerous source according to the distance measurement result is facilitated, and the safe operation of the construction operation site is guaranteed.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (9)
1. The construction operation site hazard source ranging method based on the error correction model is characterized by comprising the following steps of:
Step 1, retrieving training samples based on a database, screening the training samples, analyzing the screened training samples, and extracting corresponding ranging results and error evaluation;
training a machine learning model based on a ranging result and error evaluation, constructing an error correction model, and correlating the error correction model with an execution flow of a ranging terminal;
step 3, controlling a ranging terminal to perform differential ranging on the dangerous sources based on environmental characteristics of a construction operation site, and performing error correction on a differential ranging result based on an error correction model after the process association is performed;
in step 2, training a machine learning model based on a ranging result and error evaluation, and constructing an error correction model, including:
Retrieving a machine learning model structure from a model library based on model construction requirements, and initializing parameters of the machine learning model structure to obtain a target model structure;
determining an error measurement index and a regularization parameter value of an error correction model based on a model construction task, and generating an initial model loss function of a target model structure based on the error measurement index;
combining the regularization parameter value with the initial model loss function to obtain a model loss function;
Respectively analyzing the ranging results and the error evaluation of different training samples to obtain a distance characterization value and a distance error value corresponding to the ranging results and the error evaluation, and performing difference display on the distance characterization value and the distance error value of different training samples of the same ranging type in the same coordinate system;
Obtaining a ranging index value of each ranging type, and carrying out same-object mapping display in a difference display result by taking the ranging index value as an associated influence factor;
Obtaining parameter comparison groups of different training samples of the same ranging type based on the same object mapping display result, and determining the interaction weight among the distance characterization value, the distance error value and the associated influence factors in each training sample based on the parameter comparison groups;
Performing weighted comprehensive analysis on the interaction weight of each training sample based on the parameter comparison group to obtain a distance error correction strategy of each ranging type;
sequentially carrying out iterative training on the target model structure based on a distance error correction strategy of each ranging type, and acquiring value range distribution characteristics of a model loss function based on an iterative training process;
and determining the minimum value of the model loss function based on the value range distribution characteristics, taking an iteration training result corresponding to the minimum value as an error correction level of the current ranging type, and packaging the error correction levels corresponding to different ranging types in a target model structure to obtain an error correction model.
2. The method for measuring the distance of a dangerous source at a construction site based on an error correction model according to claim 1, wherein in step 1, retrieving training samples based on a database comprises:
Acquiring a sample retrieval task based on a management terminal, analyzing the sample retrieval task, and determining retrieval dimensions of training samples and retrieval indexes under each retrieval dimension;
Determining a database corresponding to each dimension based on the retrieval dimension, and traversing cache data in the corresponding database based on the retrieval index;
Locking the cache data to be called in each database based on the traversing result, performing data compression on the cache data to be called, generating dimension labels based on the calling dimension, and performing dimension marking on the data compression result;
and carrying out distributed calling on the cache data to be called in each database based on the dimension marking result to obtain a training sample.
3. The method for measuring the range of the dangerous source of the construction operation site based on the error correction model according to claim 1, wherein in the step 1, the training samples are screened, and the method comprises the following steps:
acquiring the obtained training samples, and acquiring data screening events of different types of training samples from a management terminal based on sample attributes of the training samples;
Determining event center characteristics and screening indexes based on the data screening event, and analyzing training samples of corresponding types based on the screening indexes to obtain target distances between sample centers of different training samples and the event center characteristics;
determining the attribution degree of each training sample in different types of training samples relative to the event center characteristics based on the target distance, and screening each training sample of different types of training samples based on the relative magnitude relation between the attribution degree and a preset threshold value.
4. The method for measuring the dangerous source of the construction operation site based on the error correction model according to claim 1, wherein in the step 1, analyzing the screened training sample, extracting the corresponding measuring result and the error evaluation, and comprising the following steps:
Acquiring a screened training sample, and splitting the training sample based on the text structure of the training sample;
Extracting key data of each part based on a structure splitting result, carrying out semantic analysis on the key data based on a neural network, and determining abstract information of the key data;
And determining the corresponding ranging result and error evaluation in the training samples based on the abstract information, and binding the ranging result and error evaluation corresponding to each training sample based on a single alignment principle.
5. The construction site hazard source ranging method based on the error correction model according to claim 1, wherein in step 2, the execution flow association of the error correction model and the ranging terminal comprises:
acquiring an obtained error correction model, and determining a deployment environment of the error correction model based on operation requirements;
acquiring environmental characteristics of a deployment environment, and determining environment adaptation parameters of an error correction model based on the environmental characteristics;
Performing first parameter adaptation on the error correction model based on the environment adaptation parameters, acquiring equipment attributes of the ranging terminal, and performing second parameter adaptation on a model interface of the error correction model based on the equipment attributes;
And determining an error correction model and execution logic of the ranging terminal based on the ranging execution logic, and associating the error correction model after the first parameter adaptation and the second parameter adaptation with the execution flow of the ranging terminal based on the execution logic.
6. The method for measuring the dangerous source distance of the construction operation site based on the error correction model according to claim 1, wherein in the step 3, the distance measuring terminal is controlled to measure the differential distance of the dangerous source based on the environmental characteristics of the construction operation site, and the method comprises the following steps:
Acquiring an environment image of a construction operation site, analyzing the environment image, and determining construction service and environment structure of the construction operation site;
The method comprises the steps of obtaining environmental characteristics of a construction operation site based on construction service and an environmental structure, extracting a recorded object in an environmental image based on an environmental image analysis result, and analyzing object attributes of the recorded object based on service execution standards to obtain a dangerous source;
and determining a corresponding ranging scheme based on the environmental characteristics and the dangerous sources, and controlling the ranging terminal to perform differential ranging on the corresponding dangerous sources according to the ranging scheme.
7. The method for measuring the range of the dangerous source of the construction operation site based on the error correction model according to claim 1, wherein in the step 3, the error correction is performed on the difference ranging result based on the error correction model after the execution of the process association, and the method comprises the following steps:
obtaining the obtained differential ranging result, and determining a ranging scheme source corresponding to the differential ranging result;
Respectively inputting a difference ranging result and a corresponding ranging scheme source into an error correction model, calling a corresponding error correction layer according to the ranging scheme source based on the input result to analyze the difference ranging result, and determining a correction value of the difference ranging result;
correcting the difference ranging result based on the correction value, and attributing and marking the corrected difference ranging result based on the identity information of the dangerous source;
and feeding back the corrected differential ranging result to the management terminal based on the attribution marking result.
8. The method for measuring the range of the dangerous source of the construction operation site based on the error correction model according to claim 7, wherein the corrected differential ranging result is fed back to the management terminal based on the attribution marking result, comprising:
extracting multidimensional features of the construction operation site based on the environmental features to obtain a three-dimensional structure of the construction operation site, and virtually reconstructing the construction operation site based on the three-dimensional structure to obtain a three-dimensional simulation model of the construction operation site;
Acquiring the actual geographic position of the ranging terminal on a construction operation site, and performing first marking in a three-dimensional simulation model based on the actual geographic position;
Acquiring the corrected difference ranging result, and determining the relative position of the dangerous source and the ranging terminal based on the first marking result and the corrected difference ranging result;
determining a target position of the hazard source based on the relative position, and performing a second marking in the three-dimensional simulation model based on the target position;
and obtaining a three-dimensional danger source visual model based on the second marking result, and recording and retaining the three-dimensional danger source visual model.
9. The utility model provides a construction operation scene hazard source ranging system based on error correction model which characterized in that includes:
The sample acquisition and processing module is used for acquiring training samples based on the database, screening the training samples, analyzing the screened training samples and extracting corresponding ranging results and error evaluation;
The model building module is used for training the machine learning model based on the ranging result and the error evaluation, building an error correction model and correlating the error correction model with the ranging terminal in the execution flow;
The ranging and correcting module is used for controlling the ranging terminal to perform differential ranging on the dangerous sources based on the environmental characteristics of the construction operation, and performing error correction on the differential ranging result based on the error correction model after the process association is performed;
Wherein, the model construction module includes:
Retrieving a machine learning model structure from a model library based on model construction requirements, and initializing parameters of the machine learning model structure to obtain a target model structure;
determining an error measurement index and a regularization parameter value of an error correction model based on a model construction task, and generating an initial model loss function of a target model structure based on the error measurement index;
combining the regularization parameter value with the initial model loss function to obtain a model loss function;
Respectively analyzing the ranging results and the error evaluation of different training samples to obtain a distance characterization value and a distance error value corresponding to the ranging results and the error evaluation, and performing difference display on the distance characterization value and the distance error value of different training samples of the same ranging type in the same coordinate system;
Obtaining a ranging index value of each ranging type, and carrying out same-object mapping display in a difference display result by taking the ranging index value as an associated influence factor;
Obtaining parameter comparison groups of different training samples of the same ranging type based on the same object mapping display result, and determining the interaction weight among the distance characterization value, the distance error value and the associated influence factors in each training sample based on the parameter comparison groups;
Performing weighted comprehensive analysis on the interaction weight of each training sample based on the parameter comparison group to obtain a distance error correction strategy of each ranging type;
sequentially carrying out iterative training on the target model structure based on a distance error correction strategy of each ranging type, and acquiring value range distribution characteristics of a model loss function based on an iterative training process;
and determining the minimum value of the model loss function based on the value range distribution characteristics, taking an iteration training result corresponding to the minimum value as an error correction level of the current ranging type, and packaging the error correction levels corresponding to different ranging types in a target model structure to obtain an error correction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411031623.5A CN118942038B (en) | 2024-07-30 | 2024-07-30 | Method and system for measuring distance of hazardous sources at construction sites based on error correction model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411031623.5A CN118942038B (en) | 2024-07-30 | 2024-07-30 | Method and system for measuring distance of hazardous sources at construction sites based on error correction model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118942038A CN118942038A (en) | 2024-11-12 |
| CN118942038B true CN118942038B (en) | 2025-03-04 |
Family
ID=93343997
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411031623.5A Active CN118942038B (en) | 2024-07-30 | 2024-07-30 | Method and system for measuring distance of hazardous sources at construction sites based on error correction model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118942038B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119204267B (en) * | 2024-11-26 | 2025-02-25 | 环球数科股份有限公司 | An error detection and correction system for large model generated content |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111473755A (en) * | 2020-04-21 | 2020-07-31 | 福建汇川物联网技术科技股份有限公司 | Remote distance measurement method and device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112965048B (en) * | 2021-02-09 | 2023-04-07 | 深圳市灵明光子科技有限公司 | Laser ranging error correction method, device, electronic equipment and storage medium |
| CN113219475B (en) * | 2021-07-06 | 2021-10-22 | 北京理工大学 | Method and system for correcting monocular ranging by using single-line lidar |
| TWI764842B (en) * | 2021-10-13 | 2022-05-11 | 英屬維爾京群島商飛思捷投資股份有限公司 | Ranging-type positioning system and method based on crowdsourced calibration |
| CN116882269A (en) * | 2023-06-21 | 2023-10-13 | 国网河北省电力有限公司 | Wind power plant error correction model construction method and device and wind power plant control system |
| CN117177356A (en) * | 2023-08-11 | 2023-12-05 | 清华大学 | Ranging error correction method based on domain adversarial training and adaptive encoding and decoding |
-
2024
- 2024-07-30 CN CN202411031623.5A patent/CN118942038B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111473755A (en) * | 2020-04-21 | 2020-07-31 | 福建汇川物联网技术科技股份有限公司 | Remote distance measurement method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118942038A (en) | 2024-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114997682B (en) | Construction site safety monitoring system and method based on big data | |
| CN118942038B (en) | Method and system for measuring distance of hazardous sources at construction sites based on error correction model | |
| US10771994B2 (en) | Method and test system for mobile network testing as well as a network testing system | |
| CN114519498A (en) | Quality evaluation method and system based on BIM (building information modeling) | |
| CN116594801A (en) | Fault analysis system for big data cloud computing | |
| CN115932530B (en) | Method for calibrating semiconductor detection equipment | |
| KR101953558B1 (en) | Apparatus and Method for Fault Management of Smart Devices | |
| CN118378196A (en) | Industrial control host abnormal behavior identification method based on multi-mode data fusion | |
| CN114255784A (en) | A fault diagnosis method and related device for substation equipment based on voiceprint recognition | |
| CN116244886B (en) | Virtual-real test data matching method and system | |
| CN118794481B (en) | A high-precision acoustic-optical three-dimensional imaging system performance test device and test method | |
| CN119649549A (en) | A geological disaster monitoring and early warning method and system based on digital twin technology | |
| CN119151131A (en) | Intelligent construction site supervision method, device, medium and equipment under multi-source data fusion | |
| CN111879456B (en) | Building curtain wall safety detection method and system | |
| CN116678368B (en) | BIM technology-based intelligent acquisition method for assembled steel structure data | |
| CN117422427B (en) | Online batch analysis method and system for low-strain data | |
| CN118227725A (en) | Meteorological model quantitative comprehensive evaluation method, device and electronic equipment | |
| Wells et al. | Evaluation of ground plane detection for estimating breast height in stereo images | |
| CN111831862A (en) | High-quality insulation evaluation system | |
| CN109359047B (en) | A software testing adequacy measurement method based on system characteristic state | |
| CN117893959A (en) | Quick fitting calibration method and system for distribution network operation site ranging | |
| CN113297998B (en) | Method, device, equipment and storage medium for identifying territorial space planning problem | |
| CN112732773B (en) | Method and system for checking uniqueness of relay protection defect data | |
| CN114154843A (en) | Method and system for identifying slope instability slip factor by displacement monitoring | |
| CN118710647B (en) | Intelligent rapid acceptance method and system for transformer |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |