CN116911470B - Data analysis method, system and storage medium based on deep learning - Google Patents
Data analysis method, system and storage medium based on deep learning Download PDFInfo
- Publication number
- CN116911470B CN116911470B CN202311172088.0A CN202311172088A CN116911470B CN 116911470 B CN116911470 B CN 116911470B CN 202311172088 A CN202311172088 A CN 202311172088A CN 116911470 B CN116911470 B CN 116911470B
- Authority
- CN
- China
- Prior art keywords
- data
- package
- logistics
- carrying
- appearance
- 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
- 238000013135 deep learning Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000007405 data analysis Methods 0.000 title claims abstract description 24
- 238000012544 monitoring process Methods 0.000 claims abstract description 119
- 238000004458 analytical method Methods 0.000 claims abstract description 71
- 238000011156 evaluation Methods 0.000 claims abstract description 44
- 238000000605 extraction Methods 0.000 claims abstract description 40
- 238000004088 simulation Methods 0.000 claims abstract description 36
- 230000000737 periodic effect Effects 0.000 claims description 22
- 230000004927 fusion Effects 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 18
- 238000010191 image analysis Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
- 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
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a data analysis method, a system and a storage medium based on deep learning, which are used for predicting package data based on a logistics prediction model to obtain package prediction data; carrying out loading simulation analysis based on the logistics package appearance data and the logistics vehicle carrying capacity data to obtain optimal loading plan and transportation cost estimated information; carrying out loading simulation evaluation based on package prediction data and logistics vehicle carrying capacity data to obtain human and material resource evaluation information; and carrying out feature analysis and monitoring feature extraction based on the appearance feature data and the monitoring video format information to obtain contrast feature data, and carrying out real-time monitoring on the appearance of the package based on the contrast feature data. By the method and the system, the logistics package can be reasonably predicted and the logistics resource can be analyzed. In addition, the invention can effectively improve the video monitoring and detecting efficiency of logistics goods, greatly improve the logistics stability and reduce the disorder condition of logistics data.
Description
Technical Field
The invention relates to the field of deep learning, in particular to a data analysis method, a system and a storage medium based on deep learning.
Background
In the current logistics industry, how to improve the logistics management efficiency, realize the large-scale development of the industry, improve the competitiveness of the industry and the running efficiency of the logistics industry is an important subject to be researched in the current logistics industry.
However, due to the fact that the conventional logistics technology is adopted, informatization is low, logistics goods monitoring and logistics package analysis prediction efficiency based on informatization are low, and the aim of rapid logistics development is difficult to achieve.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a data analysis method, a system and a storage medium based on deep learning.
The first aspect of the invention provides a data analysis method based on deep learning, comprising the following steps:
obtaining logistics package appearance data and transportation information of a target batch;
constructing a logistics prediction model based on deep learning, and importing historical logistics package data and historical logistics traffic into the logistics prediction model to perform model training;
the logistics package data and the transportation information are imported into a logistics prediction model to conduct package data prediction, and package prediction data are obtained;
acquiring logistics vehicle carrying capacity data, carrying out loading simulation analysis based on logistics package appearance data and logistics vehicle carrying capacity data, and obtaining optimal loading plan and transportation cost estimation information;
Carrying out loading simulation evaluation based on package prediction data and logistics vehicle carrying capacity data to obtain human and material resource evaluation information;
performing feature analysis and extraction on the logistic package appearance data of the target batch to obtain appearance feature data, and acquiring monitoring video format information and monitoring video data of a plurality of logistics points on the basis of the transportation information;
and carrying out feature analysis and monitoring feature extraction based on the appearance feature data and the monitoring video format information to obtain contrast feature data, and carrying out real-time monitoring on the appearance of the package based on the contrast feature data.
In this scheme, obtain commodity circulation parcel outward appearance data and the transportation information of target batch, specifically be:
acquiring multi-angle image data of logistics packages, and carrying out package region identification and image extraction based on the multi-angle image data to obtain multi-angle package image data;
based on a three-dimensional scanning device, acquiring three-dimensional scanning data of the logistics package, and analyzing actual specification information based on the three-dimensional scanning data to acquire package specification information;
and integrating the multi-angle package image data, the package specification information and the three-dimensional scanning data to obtain logistic package appearance data.
In the scheme, a logistics prediction model based on deep learning is constructed, historical logistics package data and historical logistics traffic are imported into the logistics prediction model to carry out model training, and the method specifically comprises the following steps:
constructing a logistics prediction model through a CNN network based on deep learning;
acquiring historical logistics package data and historical logistics transportation quantity within a preset time period;
dividing the time into N periods based on preset time, and acquiring periodic package data corresponding to the N periods based on historical logistics package data;
based on the historical logistics transportation quantity, periodic logistics transportation quantity corresponding to N periods is obtained;
information extraction is carried out based on the periodic package data, so that package quantity and package specification information are obtained;
and importing the corresponding parcel quantity, parcel specification information and periodic logistics traffic into a logistics prediction model for carrying out periodic-based data prediction training, wherein the prediction training comprises parcel quantity analysis, parcel specification analysis, traffic prediction analysis and parcel data prediction analysis.
In this scheme, import commodity circulation parcel data and transportation information into commodity circulation prediction model and carry out parcel data prediction, obtain parcel prediction data, specifically do:
Carrying out data integration on the logistics package data and the transportation information to form logistics package and transportation data in a period;
and importing the logistics package and transportation data into a logistics prediction model to perform package data prediction, so as to obtain package prediction data in the next period.
In this scheme, obtain commodity circulation vehicle capacity data, carry out loading simulation analysis based on commodity circulation parcel outward appearance data, commodity circulation vehicle capacity data to obtain preferred loading plan and transportation cost forecast information, specifically do:
acquiring the capacity of a carrying space of a current carrying vehicle based on three dimensions based on the carrying capacity data of the logistics vehicles;
carrying out package three-dimensional space analysis based on the logistics package appearance data, and generating space capacity required by carrying each package based on three dimensions according to a preset space position;
taking the carrying space capacity as the total capacity, taking the space capacity required by carrying as the filling object capacity, carrying out loading simulation based on a three-tree algorithm, and obtaining a plurality of loading plans;
and carrying out traffic assessment and cost calculation according to the plurality of loading plans, and obtaining optimal loading plans and estimated transportation cost information based on cost constraint.
In this scheme, load simulation evaluation is carried out based on parcel forecast data, logistics vehicle carrying capacity data, and the obtained manpower and material resources evaluation information specifically includes:
generating a required space capacity of the package based on the package forecast data;
carrying out loading simulation evaluation based on the space capacity required by the package and the carrying space capacity to generate a predicted loading plan;
carrying out logistics resource assessment based on the predicted loading plan to obtain human and material resource assessment information;
and carrying out logistics task pre-allocation according to the human and material resource evaluation information to generate a logistics personnel task plan and a transportation vehicle task plan.
In this scheme, the characteristic analysis and extraction are performed on the appearance data of the logistic package based on the target lot, so as to obtain appearance characteristic data, and the monitoring video format information and the monitoring video data of a plurality of logistic points are obtained based on the transportation information, specifically:
acquiring multi-angle package image data and three-dimensional scanning data in the logistics package appearance data of the target batch;
extracting image characteristics based on the multi-angle package image data, and obtaining appearance characteristic data of each angle;
according to the three-dimensional scanning data, combining the package movement and transportation limitation, performing multi-angle continuous combination analysis on a package space to obtain M angle combinations;
And forming appearance characteristic fusion data corresponding to the M angle combinations based on the angle combinations and the appearance characteristic data of each angle.
In this scheme, carry out feature analysis and monitoring feature extraction based on outward appearance characteristic data and monitoring video format information, obtain contrast characteristic data, carry out parcel outward appearance real-time supervision based on contrast characteristic data, specifically do:
based on the monitoring video format information, analyzing a video frame image format and obtaining a corresponding image standard;
converting the appearance characteristic fusion data corresponding to the M angle combinations based on image standards to obtain M contrast characteristic data;
extracting key frames based on the monitoring video data to obtain a package monitoring image;
performing image analysis and feature extraction based on the package monitoring image to obtain monitoring feature data;
calculating and analyzing the monitoring feature data and M pieces of comparison feature data based on feature similarity, and marking the comparison feature data with the highest feature similarity to obtain first comparison feature data;
acquiring a combination angle corresponding to the first contrast characteristic data and recording the combination angle as a monitoring combination angle;
and analyzing the spatial position of the current package based on the monitoring combination angle, judging whether the spatial position accords with a preset position range or not based on the spatial position, and if not, generating logistics transportation early warning information.
The second aspect of the present invention also provides a data analysis system based on deep learning, the system comprising: the device comprises a memory and a processor, wherein the memory comprises a data analysis program based on deep learning, and the data analysis program based on deep learning realizes the following steps when being executed by the processor:
obtaining logistics package appearance data and transportation information of a target batch;
constructing a logistics prediction model based on deep learning, and importing historical logistics package data and historical logistics traffic into the logistics prediction model to perform model training;
the logistics package data and the transportation information are imported into a logistics prediction model to conduct package data prediction, and package prediction data are obtained;
acquiring logistics vehicle carrying capacity data, carrying out loading simulation analysis based on logistics package appearance data and logistics vehicle carrying capacity data, and obtaining optimal loading plan and transportation cost estimation information;
carrying out loading simulation evaluation based on package prediction data and logistics vehicle carrying capacity data to obtain human and material resource evaluation information;
performing feature analysis and extraction on the logistic package appearance data of the target batch to obtain appearance feature data, and acquiring monitoring video format information and monitoring video data of a plurality of logistics points on the basis of the transportation information;
And carrying out feature analysis and monitoring feature extraction based on the appearance feature data and the monitoring video format information to obtain contrast feature data, and carrying out real-time monitoring on the appearance of the package based on the contrast feature data.
The third aspect of the present invention also provides a computer-readable storage medium having embodied therein a deep learning-based data analysis program which, when executed by a processor, implements the steps of the deep learning-based data analysis method as set forth in any one of the above.
The invention discloses a data analysis method, a system and a storage medium based on deep learning, which are used for predicting package data based on a logistics prediction model to obtain package prediction data; carrying out loading simulation analysis based on the logistics package appearance data and the logistics vehicle carrying capacity data to obtain optimal loading plan and transportation cost estimated information; carrying out loading simulation evaluation based on package prediction data and logistics vehicle carrying capacity data to obtain human and material resource evaluation information; and carrying out feature analysis and monitoring feature extraction based on the appearance feature data and the monitoring video format information to obtain contrast feature data, and carrying out real-time monitoring on the appearance of the package based on the contrast feature data. By the method and the system, the logistics package can be reasonably predicted and the logistics resource can be analyzed. In addition, the invention can effectively improve the video monitoring and detecting efficiency of logistics goods, greatly improve the logistics stability and reduce the disorder condition of logistics data.
Drawings
FIG. 1 shows a flow chart of a data analysis method based on deep learning of the present invention;
FIG. 2 shows a flow chart for obtaining physical distribution package appearance data according to the present invention;
FIG. 3 illustrates a flow chart of the package forecast data acquisition of the present invention;
FIG. 4 shows a block diagram of a deep learning based data analysis system of the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
FIG. 1 shows a flow chart of a data analysis method based on deep learning of the present invention.
As shown in fig. 1, a first aspect of the present invention provides a data analysis method based on deep learning, including:
S102, obtaining logistics package appearance data and transportation information of a target batch;
s104, constructing a logistics prediction model based on deep learning, and importing historical logistics package data and historical logistics traffic into the logistics prediction model for model training;
s106, importing the logistics package data and the transportation information into a logistics prediction model to predict package data, so as to obtain package prediction data;
s108, acquiring logistics vehicle carrying capacity data, carrying out loading simulation analysis based on logistics package appearance data and logistics vehicle carrying capacity data, and obtaining optimal loading plan and transportation cost estimated information;
s110, carrying out loading simulation evaluation based on package prediction data and logistics vehicle carrying capacity data to obtain human and material resource evaluation information;
s112, carrying out feature analysis and extraction on the basis of the logistics package appearance data of the target batch to obtain appearance feature data, and obtaining monitoring video format information and monitoring video data of a plurality of logistics points on the basis of the transportation information;
and S114, carrying out feature analysis and monitoring feature extraction based on the appearance feature data and the monitoring video format information to obtain contrast feature data, and carrying out real-time monitoring on the appearance of the package based on the contrast feature data.
FIG. 2 shows a flow chart for obtaining physical package appearance data according to the present invention.
According to the embodiment of the invention, the obtaining of the physical distribution package appearance data and the transportation information of the target batch specifically includes:
s202, multi-angle image data of logistics packages are obtained, and package region identification and image extraction are carried out based on the multi-angle image data, so that multi-angle package image data are obtained;
s204, based on a three-dimensional scanning device, acquiring three-dimensional scanning data of the logistics package, and based on the three-dimensional scanning data, performing actual specification information analysis to obtain package specification information;
s206, integrating the multi-angle package image data, the package specification information and the three-dimensional scanning data to obtain logistic package appearance data.
The package specification information includes information such as length, width, height, volume, weight, etc. of the goods. In the multi-angle package image data, generally, 6 angles correspond to 6 surfaces of the package.
According to the embodiment of the invention, a logistics prediction model based on deep learning is constructed, and the historical logistics package data and the historical logistics traffic are imported into the logistics prediction model for model training, specifically:
constructing a logistics prediction model through a CNN network based on deep learning;
Acquiring historical logistics package data and historical logistics transportation quantity within a preset time period;
dividing the time into N periods based on preset time, and acquiring periodic package data corresponding to the N periods based on historical logistics package data;
based on the historical logistics transportation quantity, periodic logistics transportation quantity corresponding to N periods is obtained;
information extraction is carried out based on the periodic package data, so that package quantity and package specification information are obtained;
and importing the corresponding parcel quantity, parcel specification information and periodic logistics traffic into a logistics prediction model for carrying out periodic-based data prediction training, wherein the prediction training comprises parcel quantity analysis, parcel specification analysis, traffic prediction analysis and parcel data prediction analysis.
It should be noted that, in a logistics site, the number and specification of packages often show periodic variation within a certain preset time period, and the invention analyzes the package data variation therein by constructing a prediction model, and obtains a prediction model with certain predicted package data, where the predicted package data mainly includes predictions of package data and specifications within a certain period. The logistics transportation amount is information such as total transportation times of logistics cargoes, total transportation cargoes, demand of transportation trucks and the like.
FIG. 3 illustrates a flow chart of the package forecast data acquisition of the present invention.
According to the embodiment of the invention, the logistics package data and the transportation information are imported into a logistics prediction model for package data prediction, so as to obtain package prediction data, which is specifically as follows:
s302, carrying out data integration on logistics package data and transportation information to form logistics package and transportation data in a period;
s304, the logistics package and transportation data are imported into a logistics prediction model to conduct package data prediction, and package prediction data in the next period are obtained.
According to the embodiment of the invention, the logistics vehicle carrying capacity data is obtained, loading simulation analysis is carried out based on logistics package appearance data and logistics vehicle carrying capacity data, and optimal loading plan and transportation cost estimated information are obtained, specifically:
acquiring the capacity of a carrying space of a current carrying vehicle based on three dimensions based on the carrying capacity data of the logistics vehicles;
carrying out package three-dimensional space analysis based on the logistics package appearance data, and generating space capacity required by carrying each package based on three dimensions according to a preset space position;
taking the carrying space capacity as the total capacity, taking the space capacity required by carrying as the filling object capacity, carrying out loading simulation based on a three-tree algorithm, and obtaining a plurality of loading plans;
And carrying out traffic assessment and cost calculation according to the plurality of loading plans, and obtaining optimal loading plans and estimated transportation cost information based on cost constraint.
The logistics vehicle carrying capacity data comprise logistics truck types, carrying space volumes and the like. The lower cost plan is selected based on cost constraints.
According to the embodiment of the invention, the loading simulation evaluation is performed based on package prediction data and logistics vehicle carrying capacity data to obtain human and material resource evaluation information, which comprises the following specific steps:
generating a required space capacity of the package based on the package forecast data;
carrying out loading simulation evaluation based on the space capacity required by the package and the carrying space capacity to generate a predicted loading plan;
carrying out logistics resource assessment based on the predicted loading plan to obtain human and material resource assessment information;
and carrying out logistics task pre-allocation according to the human and material resource evaluation information to generate a logistics personnel task plan and a transportation vehicle task plan.
The distribution condition of manpower and material resources under the predicted data in the next prediction period can be mastered through the logistics personnel mission plan and the transportation vehicle mission plan, so that the logistics resource analysis is performed in advance, and the uncertain factors of the logistics resources are reduced.
According to the embodiment of the invention, the characteristic analysis and extraction are performed on the appearance data of the logistic package based on the target batch to obtain appearance characteristic data, and the monitoring video format information and the monitoring video data of a plurality of logistics points are obtained based on the transportation information, specifically:
acquiring multi-angle package image data and three-dimensional scanning data in the logistics package appearance data of the target batch;
extracting image characteristics based on the multi-angle package image data, and obtaining appearance characteristic data of each angle;
according to the three-dimensional scanning data, combining the package movement and transportation limitation, performing multi-angle continuous combination analysis on a package space to obtain M angle combinations;
and forming appearance characteristic fusion data corresponding to the M angle combinations based on the angle combinations and the appearance characteristic data of each angle.
The package movement and transportation restrictions include transportation restrictions such as turning and tilting of the package. And forming appearance characteristic fusion data corresponding to M angle combinations based on the angle combinations and the appearance characteristic data of each angle, specifically, carrying out data fusion on the appearance characteristic data of the angle corresponding to each angle combination, thereby forming appearance characteristic fusion data. One angle combination corresponds to one appearance feature fusion data. According to the invention, the image characteristic data of a plurality of angles are fused by reasonably analyzing the combination of a plurality of continuous angles of the package, and it is worth mentioning that in the logistics transportation, the video monitoring package can generate object pictures of a plurality of angles, such as the upper and the front two angles of the package, and the package combination angles of the monitoring logistics package can be predicted in advance in the logistics transportation process, so that the multi-angle appearance characteristic fusion data can be further obtained, the efficiency of the subsequent logistics cargo video monitoring detection can be effectively improved, the logistics stability is greatly improved, and the disorder condition of the logistics data is reduced.
In logistics transportation tasks, a plurality of logistics transfer stations, namely a plurality of logistics stations, are often present, and in the logistics stations, video detection authentication is required to be carried out on package goods, so that the record of packages in the logistics stations is determined, and due to equipment differences, the difference exists between monitoring video formats corresponding to different logistics stations. The shipping information includes a shipping logistics site through which the package passes.
According to the embodiment of the invention, the feature analysis and the monitoring feature extraction are performed based on the appearance feature data and the monitoring video format information to obtain the contrast feature data, and the real-time monitoring of the appearance of the package is performed based on the contrast feature data, specifically:
based on the monitoring video format information, analyzing a video frame image format and obtaining a corresponding image standard;
converting the appearance characteristic fusion data corresponding to the M angle combinations based on image standards to obtain M contrast characteristic data;
extracting key frames based on the monitoring video data to obtain a package monitoring image;
performing image analysis and feature extraction based on the package monitoring image to obtain monitoring feature data;
calculating and analyzing the monitoring feature data and M pieces of comparison feature data based on feature similarity, and marking the comparison feature data with the highest feature similarity to obtain first comparison feature data;
Acquiring a combination angle corresponding to the first contrast characteristic data and recording the combination angle as a monitoring combination angle;
and analyzing the spatial position of the current package based on the monitoring combination angle, judging whether the spatial position accords with a preset position range or not based on the spatial position, and if not, generating logistics transportation early warning information.
The image standard includes information such as resolution, picture scale, and color standard. The space position is the information of the position, the azimuth and the like of the package, and the transportation condition of the package, whether the package inclines, overturns and the like can be mastered in real time through the space position.
According to an embodiment of the present invention, further comprising:
acquiring monitoring video data of a logistics terminal station;
performing key frame extraction and package image recognition based on the logistics terminal station monitoring video data to obtain terminal station package image data;
extracting image features based on the terminal station package image data to obtain terminal station package feature data;
obtaining appearance characteristic data corresponding to each angle based on multi-angle package image data in the logistics package appearance data of the target batch;
calculating the characteristic difference degree of the terminal station parcel characteristic data and the angle appearance characteristic data, and marking the corresponding parcel as an abnormal parcel if the difference degree is larger than a preset difference degree;
Acquiring logistics transportation early warning information corresponding to a plurality of logistics points based on transportation information of abnormal packages;
carrying out package anomaly traceability analysis and transportation responsibility assessment on the logistics site based on the logistics transportation early warning information, and generating logistics site transportation assessment information;
and sending the transportation evaluation information to a preset terminal device.
It should be noted that, through the transportation evaluation information, the condition of the package at the transportation logistics site and the problem tracing and responsibility evaluation of each logistics site to the abnormal package can be mastered in real time, so that logistics enterprises can rapidly and real-timely carry out transportation management, analysis and correction of the logistics site, and the quality and efficiency of subsequent logistics are improved.
FIG. 4 shows a block diagram of a deep learning based data analysis system of the present invention.
The second aspect of the present invention also provides a data analysis system 4 based on deep learning, the system comprising: a memory 41, a processor 42, the memory comprising a deep learning based data analysis program, the deep learning based data analysis program when executed by the processor implementing the steps of:
obtaining logistics package appearance data and transportation information of a target batch;
Constructing a logistics prediction model based on deep learning, and importing historical logistics package data and historical logistics traffic into the logistics prediction model to perform model training;
the logistics package data and the transportation information are imported into a logistics prediction model to conduct package data prediction, and package prediction data are obtained;
acquiring logistics vehicle carrying capacity data, carrying out loading simulation analysis based on logistics package appearance data and logistics vehicle carrying capacity data, and obtaining optimal loading plan and transportation cost estimation information;
carrying out loading simulation evaluation based on package prediction data and logistics vehicle carrying capacity data to obtain human and material resource evaluation information;
performing feature analysis and extraction on the logistic package appearance data of the target batch to obtain appearance feature data, and acquiring monitoring video format information and monitoring video data of a plurality of logistics points on the basis of the transportation information;
and carrying out feature analysis and monitoring feature extraction based on the appearance feature data and the monitoring video format information to obtain contrast feature data, and carrying out real-time monitoring on the appearance of the package based on the contrast feature data.
According to the embodiment of the invention, the obtaining of the physical distribution package appearance data and the transportation information of the target batch specifically includes:
Acquiring multi-angle image data of logistics packages, and carrying out package region identification and image extraction based on the multi-angle image data to obtain multi-angle package image data;
based on a three-dimensional scanning device, acquiring three-dimensional scanning data of the logistics package, and analyzing actual specification information based on the three-dimensional scanning data to acquire package specification information;
and integrating the multi-angle package image data, the package specification information and the three-dimensional scanning data to obtain logistic package appearance data.
The package specification information includes information such as length, width, height, volume, weight, etc. of the goods. In the multi-angle package image data, generally, 6 angles correspond to 6 surfaces of the package.
According to the embodiment of the invention, a logistics prediction model based on deep learning is constructed, and the historical logistics package data and the historical logistics traffic are imported into the logistics prediction model for model training, specifically:
constructing a logistics prediction model through a CNN network based on deep learning;
acquiring historical logistics package data and historical logistics transportation quantity within a preset time period;
dividing the time into N periods based on preset time, and acquiring periodic package data corresponding to the N periods based on historical logistics package data;
Based on the historical logistics transportation quantity, periodic logistics transportation quantity corresponding to N periods is obtained;
information extraction is carried out based on the periodic package data, so that package quantity and package specification information are obtained;
and importing the corresponding parcel quantity, parcel specification information and periodic logistics traffic into a logistics prediction model for carrying out periodic-based data prediction training, wherein the prediction training comprises parcel quantity analysis, parcel specification analysis, traffic prediction analysis and parcel data prediction analysis.
It should be noted that, in the logistics site, the number and the specification of the packages often show periodic variation within a certain preset period of time, and the invention analyzes the package data variation therein by constructing a prediction model, and obtains a prediction model with certain predicted package data, where the predicted package data mainly includes predictions of package data and specifications within a certain period. The logistics transportation amount is information such as total transportation times of logistics cargoes, total transportation cargoes, demand of transportation trucks and the like.
According to the embodiment of the invention, the logistics package data and the transportation information are imported into a logistics prediction model for package data prediction, so as to obtain package prediction data, which is specifically as follows:
Carrying out data integration on the logistics package data and the transportation information to form logistics package and transportation data in a period;
and importing the logistics package and transportation data into a logistics prediction model to perform package data prediction, so as to obtain package prediction data in the next period.
According to the embodiment of the invention, the logistics vehicle carrying capacity data is obtained, loading simulation analysis is carried out based on logistics package appearance data and logistics vehicle carrying capacity data, and optimal loading plan and transportation cost estimated information are obtained, specifically:
acquiring the capacity of a carrying space of a current carrying vehicle based on three dimensions based on the carrying capacity data of the logistics vehicles;
carrying out package three-dimensional space analysis based on the logistics package appearance data, and generating space capacity required by carrying each package based on three dimensions according to a preset space position;
taking the carrying space capacity as the total capacity, taking the space capacity required by carrying as the filling object capacity, carrying out loading simulation based on a three-tree algorithm, and obtaining a plurality of loading plans;
and carrying out traffic assessment and cost calculation according to the plurality of loading plans, and obtaining optimal loading plans and estimated transportation cost information based on cost constraint.
The logistics vehicle carrying capacity data comprise logistics truck types, carrying space volumes and the like. The lower cost plan is selected based on cost constraints.
According to the embodiment of the invention, the loading simulation evaluation is performed based on package prediction data and logistics vehicle carrying capacity data to obtain human and material resource evaluation information, which comprises the following specific steps:
generating a required space capacity of the package based on the package forecast data;
carrying out loading simulation evaluation based on the space capacity required by the package and the carrying space capacity to generate a predicted loading plan;
carrying out logistics resource assessment based on the predicted loading plan to obtain human and material resource assessment information;
and carrying out logistics task pre-allocation according to the human and material resource evaluation information to generate a logistics personnel task plan and a transportation vehicle task plan.
The distribution condition of manpower and material resources under the predicted data in the next prediction period can be mastered through the logistics personnel mission plan and the transportation vehicle mission plan, so that the logistics resource analysis is performed in advance, and the uncertain factors of the logistics resources are reduced.
According to the embodiment of the invention, the characteristic analysis and extraction are performed on the appearance data of the logistic package based on the target batch to obtain appearance characteristic data, and the monitoring video format information and the monitoring video data of a plurality of logistics points are obtained based on the transportation information, specifically:
Acquiring multi-angle package image data and three-dimensional scanning data in the logistics package appearance data of the target batch;
extracting image characteristics based on the multi-angle package image data, and obtaining appearance characteristic data of each angle;
according to the three-dimensional scanning data, combining the package movement and transportation limitation, performing multi-angle continuous combination analysis on a package space to obtain M angle combinations;
and forming appearance characteristic fusion data corresponding to the M angle combinations based on the angle combinations and the appearance characteristic data of each angle.
The package movement and transportation restrictions include transportation restrictions such as turning and tilting of the package. And forming appearance characteristic fusion data corresponding to M angle combinations based on the angle combinations and the appearance characteristic data of each angle, specifically, carrying out data fusion on the appearance characteristic data of the angle corresponding to each angle combination, thereby forming appearance characteristic fusion data. One angle combination corresponds to one appearance feature fusion data. According to the invention, the image characteristic data of a plurality of angles are fused by reasonably analyzing the combination of a plurality of continuous angles of the package, and it is worth mentioning that in the logistics transportation, the video monitoring package can generate object pictures of a plurality of angles, such as the upper and the front two angles of the package, and the package combination angles of the monitoring logistics package can be predicted in advance in the logistics transportation process, so that the multi-angle appearance characteristic fusion data can be further obtained, the efficiency of the subsequent logistics cargo video monitoring detection can be effectively improved, the logistics stability is greatly improved, and the disorder condition of the logistics data is reduced.
In logistics transportation tasks, a plurality of logistics transfer stations, namely a plurality of logistics stations, are often present, and in the logistics stations, video detection authentication is required to be carried out on package goods, so that the record of packages in the logistics stations is determined, and due to equipment differences, the difference exists between monitoring video formats corresponding to different logistics stations. The shipping information includes a shipping logistics site through which the package passes.
According to the embodiment of the invention, the feature analysis and the monitoring feature extraction are performed based on the appearance feature data and the monitoring video format information to obtain the contrast feature data, and the real-time monitoring of the appearance of the package is performed based on the contrast feature data, specifically:
based on the monitoring video format information, analyzing a video frame image format and obtaining a corresponding image standard;
converting the appearance characteristic fusion data corresponding to the M angle combinations based on image standards to obtain M contrast characteristic data;
extracting key frames based on the monitoring video data to obtain a package monitoring image;
performing image analysis and feature extraction based on the package monitoring image to obtain monitoring feature data;
calculating and analyzing the monitoring feature data and M pieces of comparison feature data based on feature similarity, and marking the comparison feature data with the highest feature similarity to obtain first comparison feature data;
Acquiring a combination angle corresponding to the first contrast characteristic data and recording the combination angle as a monitoring combination angle;
and analyzing the spatial position of the current package based on the monitoring combination angle, judging whether the spatial position accords with a preset position range or not based on the spatial position, and if not, generating logistics transportation early warning information.
The image standard includes information such as resolution, picture scale, and color standard. The space position is the information of the position, the azimuth and the like of the package, and the transportation condition of the package, whether the package inclines, overturns and the like can be mastered in real time through the space position.
According to an embodiment of the present invention, further comprising:
acquiring monitoring video data of a logistics terminal station;
performing key frame extraction and package image recognition based on the logistics terminal station monitoring video data to obtain terminal station package image data;
extracting image features based on the terminal station package image data to obtain terminal station package feature data;
obtaining appearance characteristic data corresponding to each angle based on multi-angle package image data in the logistics package appearance data of the target batch;
calculating the characteristic difference degree of the terminal station parcel characteristic data and the angle appearance characteristic data, and marking the corresponding parcel as an abnormal parcel if the difference degree is larger than a preset difference degree;
Acquiring logistics transportation early warning information corresponding to a plurality of logistics points based on transportation information of abnormal packages;
carrying out package anomaly traceability analysis and transportation responsibility assessment on the logistics site based on the logistics transportation early warning information, and generating logistics site transportation assessment information;
and sending the transportation evaluation information to a preset terminal device.
It should be noted that, through the transportation evaluation information, the condition of the package at the transportation logistics site and the problem tracing and responsibility evaluation of each logistics site to the abnormal package can be mastered in real time, so that logistics enterprises can rapidly and real-timely carry out transportation management, analysis and correction of the logistics site, and the quality and efficiency of subsequent logistics are improved.
The third aspect of the present invention also provides a computer-readable storage medium having embodied therein a deep learning-based data analysis program which, when executed by a processor, implements the steps of the deep learning-based data analysis method as set forth in any one of the above.
The invention discloses a data analysis method, a system and a storage medium based on deep learning, which are used for predicting package data based on a logistics prediction model to obtain package prediction data; carrying out loading simulation analysis based on the logistics package appearance data and the logistics vehicle carrying capacity data to obtain optimal loading plan and transportation cost estimated information; carrying out loading simulation evaluation based on package prediction data and logistics vehicle carrying capacity data to obtain human and material resource evaluation information; and carrying out feature analysis and monitoring feature extraction based on the appearance feature data and the monitoring video format information to obtain contrast feature data, and carrying out real-time monitoring on the appearance of the package based on the contrast feature data. By the method and the system, the logistics package can be reasonably predicted and the logistics resource can be analyzed. In addition, the invention can effectively improve the video monitoring and detecting efficiency of logistics goods, greatly improve the logistics stability and reduce the disorder condition of logistics data.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (7)
1. A data analysis method based on deep learning, comprising:
obtaining logistics package appearance data and transportation information of a target batch;
constructing a logistics prediction model based on deep learning, and importing historical logistics package data and historical logistics traffic into the logistics prediction model to perform model training;
the logistics package data and the transportation information are imported into a logistics prediction model to conduct package data prediction, and package prediction data are obtained;
acquiring logistics vehicle carrying capacity data, carrying out loading simulation analysis based on logistics package appearance data and logistics vehicle carrying capacity data, and obtaining optimal loading plan and transportation cost estimation information;
carrying out loading simulation evaluation based on package prediction data and logistics vehicle carrying capacity data to obtain human and material resource evaluation information;
Performing feature analysis and extraction on the logistic package appearance data of the target batch to obtain appearance feature data, and acquiring monitoring video format information and monitoring video data of a plurality of logistics points on the basis of the transportation information;
performing feature analysis and monitoring feature extraction based on the appearance feature data and the monitoring video format information to obtain contrast feature data, and performing real-time monitoring on the appearance of the package based on the contrast feature data;
the method comprises the steps of carrying out loading simulation evaluation based on package prediction data and logistics vehicle carrying capacity data to obtain human and material resource evaluation information, wherein the method comprises the following steps of:
generating a required space capacity of the package based on the package forecast data;
carrying out loading simulation evaluation based on the space capacity required by the package and the carrying space capacity to generate a predicted loading plan;
carrying out logistics resource assessment based on the predicted loading plan to obtain human and material resource assessment information;
carrying out logistics task pre-allocation according to the human and material resource evaluation information to generate a logistics personnel task plan and a transportation vehicle task plan;
the feature analysis and extraction are performed on the logistic package appearance data based on the target batch to obtain appearance feature data, and the monitoring video format information and the monitoring video data of a plurality of logistics points are obtained based on the transportation information, specifically:
Acquiring multi-angle package image data and three-dimensional scanning data in the logistics package appearance data of the target batch;
extracting image characteristics based on the multi-angle package image data, and obtaining appearance characteristic data of each angle;
according to the three-dimensional scanning data, combining the package movement and transportation limitation, performing multi-angle continuous combination analysis on a package space to obtain M angle combinations;
forming appearance characteristic fusion data corresponding to M angle combinations based on the angle combinations and the appearance characteristic data of each angle;
the method comprises the steps of carrying out feature analysis and monitoring feature extraction based on appearance feature data and monitoring video format information to obtain contrast feature data, and carrying out real-time monitoring on package appearance based on the contrast feature data, wherein the method specifically comprises the following steps:
based on the monitoring video format information, analyzing a video frame image format and obtaining a corresponding image standard;
converting the appearance characteristic fusion data corresponding to the M angle combinations based on image standards to obtain M contrast characteristic data;
extracting key frames based on the monitoring video data to obtain a package monitoring image;
performing image analysis and feature extraction based on the package monitoring image to obtain monitoring feature data;
Calculating and analyzing the monitoring feature data and M pieces of comparison feature data based on feature similarity, and marking the comparison feature data with the highest feature similarity to obtain first comparison feature data;
acquiring a combination angle corresponding to the first contrast characteristic data and recording the combination angle as a monitoring combination angle;
and analyzing the spatial position of the current package based on the monitoring combination angle, judging whether the spatial position accords with a preset position range or not based on the spatial position, and if not, generating logistics transportation early warning information.
2. The deep learning-based data analysis method according to claim 1, wherein the obtaining of the logistic package appearance data and the transportation information of the target lot specifically includes:
acquiring multi-angle image data of logistics packages, and carrying out package region identification and image extraction based on the multi-angle image data to obtain multi-angle package image data;
based on a three-dimensional scanning device, acquiring three-dimensional scanning data of the logistics package, and analyzing actual specification information based on the three-dimensional scanning data to acquire package specification information;
and integrating the multi-angle package image data, the package specification information and the three-dimensional scanning data to obtain logistic package appearance data.
3. The data analysis method based on deep learning according to claim 1, wherein the building of the logistic prediction model based on deep learning, the importing of the historical logistic package data and the historical logistic traffic into the logistic prediction model for model training, specifically comprises:
constructing a logistics prediction model through a CNN network based on deep learning;
acquiring historical logistics package data and historical logistics transportation quantity within a preset time period;
dividing the time into N periods based on preset time, and acquiring periodic package data corresponding to the N periods based on historical logistics package data;
based on the historical logistics transportation quantity, periodic logistics transportation quantity corresponding to N periods is obtained;
information extraction is carried out based on the periodic package data, so that package quantity and package specification information are obtained;
and importing the corresponding parcel quantity, parcel specification information and periodic logistics traffic into a logistics prediction model for carrying out periodic-based data prediction training, wherein the prediction training comprises parcel quantity analysis, parcel specification analysis, traffic prediction analysis and parcel data prediction analysis.
4. The data analysis method based on deep learning of claim 3, wherein the step of importing the logistics package data and the transportation information into a logistics prediction model to perform package data prediction, and obtaining package prediction data specifically comprises the following steps:
Carrying out data integration on the logistics package data and the transportation information to form logistics package and transportation data in a period;
and importing the logistics package and transportation data into a logistics prediction model to perform package data prediction, so as to obtain package prediction data in the next period.
5. The deep learning-based data analysis method according to claim 4, wherein the obtaining logistics vehicle capacity data, carrying out loading simulation analysis based on logistics package appearance data and logistics vehicle capacity data, and obtaining preferable loading plan and transportation cost estimated information comprises:
acquiring the capacity of a carrying space of a current carrying vehicle based on three dimensions based on the carrying capacity data of the logistics vehicles;
carrying out package three-dimensional space analysis based on the logistics package appearance data, and generating space capacity required by carrying each package based on three dimensions according to a preset space position;
taking the carrying space capacity as the total capacity, taking the space capacity required by carrying as the filling object capacity, carrying out loading simulation based on a three-tree algorithm, and obtaining a plurality of loading plans;
and carrying out traffic assessment and cost calculation according to the plurality of loading plans, and obtaining optimal loading plans and estimated transportation cost information based on cost constraint.
6. A data analysis system based on deep learning, the system comprising: the device comprises a memory and a processor, wherein the memory comprises a data analysis program based on deep learning, and the data analysis program based on deep learning realizes the following steps when being executed by the processor:
obtaining logistics package appearance data and transportation information of a target batch;
constructing a logistics prediction model based on deep learning, and importing historical logistics package data and historical logistics traffic into the logistics prediction model to perform model training;
the logistics package data and the transportation information are imported into a logistics prediction model to conduct package data prediction, and package prediction data are obtained;
acquiring logistics vehicle carrying capacity data, carrying out loading simulation analysis based on logistics package appearance data and logistics vehicle carrying capacity data, and obtaining optimal loading plan and transportation cost estimation information;
carrying out loading simulation evaluation based on package prediction data and logistics vehicle carrying capacity data to obtain human and material resource evaluation information;
performing feature analysis and extraction on the logistic package appearance data of the target batch to obtain appearance feature data, and acquiring monitoring video format information and monitoring video data of a plurality of logistics points on the basis of the transportation information;
Performing feature analysis and monitoring feature extraction based on the appearance feature data and the monitoring video format information to obtain contrast feature data, and performing real-time monitoring on the appearance of the package based on the contrast feature data;
the method comprises the steps of carrying out loading simulation evaluation based on package prediction data and logistics vehicle carrying capacity data to obtain human and material resource evaluation information, wherein the method comprises the following steps of:
generating a required space capacity of the package based on the package forecast data;
carrying out loading simulation evaluation based on the space capacity required by the package and the carrying space capacity to generate a predicted loading plan;
carrying out logistics resource assessment based on the predicted loading plan to obtain human and material resource assessment information;
carrying out logistics task pre-allocation according to the human and material resource evaluation information to generate a logistics personnel task plan and a transportation vehicle task plan;
the feature analysis and extraction are performed on the logistic package appearance data based on the target batch to obtain appearance feature data, and the monitoring video format information and the monitoring video data of a plurality of logistics points are obtained based on the transportation information, specifically:
acquiring multi-angle package image data and three-dimensional scanning data in the logistics package appearance data of the target batch;
Extracting image characteristics based on the multi-angle package image data, and obtaining appearance characteristic data of each angle;
according to the three-dimensional scanning data, combining the package movement and transportation limitation, performing multi-angle continuous combination analysis on a package space to obtain M angle combinations;
forming appearance characteristic fusion data corresponding to M angle combinations based on the angle combinations and the appearance characteristic data of each angle;
the method comprises the steps of carrying out feature analysis and monitoring feature extraction based on appearance feature data and monitoring video format information to obtain contrast feature data, and carrying out real-time monitoring on package appearance based on the contrast feature data, wherein the method specifically comprises the following steps:
based on the monitoring video format information, analyzing a video frame image format and obtaining a corresponding image standard;
converting the appearance characteristic fusion data corresponding to the M angle combinations based on image standards to obtain M contrast characteristic data;
extracting key frames based on the monitoring video data to obtain a package monitoring image;
performing image analysis and feature extraction based on the package monitoring image to obtain monitoring feature data;
calculating and analyzing the monitoring feature data and M pieces of comparison feature data based on feature similarity, and marking the comparison feature data with the highest feature similarity to obtain first comparison feature data;
Acquiring a combination angle corresponding to the first contrast characteristic data and recording the combination angle as a monitoring combination angle;
and analyzing the spatial position of the current package based on the monitoring combination angle, judging whether the spatial position accords with a preset position range or not based on the spatial position, and if not, generating logistics transportation early warning information.
7. A computer readable storage medium, characterized in that the computer readable storage medium comprises a deep learning based data analysis program, which, when executed by a processor, implements the steps of the deep learning based data analysis method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311172088.0A CN116911470B (en) | 2023-09-12 | 2023-09-12 | Data analysis method, system and storage medium based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311172088.0A CN116911470B (en) | 2023-09-12 | 2023-09-12 | Data analysis method, system and storage medium based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116911470A CN116911470A (en) | 2023-10-20 |
| CN116911470B true CN116911470B (en) | 2024-01-02 |
Family
ID=88351469
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311172088.0A Active CN116911470B (en) | 2023-09-12 | 2023-09-12 | Data analysis method, system and storage medium based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116911470B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106203700A (en) * | 2016-07-11 | 2016-12-07 | 中联物流（中国）有限公司 | The logistics transportation scheme of logistic management system determines method and system |
| CN110111036A (en) * | 2019-03-28 | 2019-08-09 | 跨越速运集团有限公司 | Logistics goods amount prediction technique and system based on LSTM Model Fusion |
| CN111882117A (en) * | 2020-07-07 | 2020-11-03 | 上海中通吉网络技术有限公司 | Express trunk route line flow prediction method, device and equipment |
| CN115204028A (en) * | 2022-04-13 | 2022-10-18 | 赣南师范大学 | Three-dimensional packing optimization method and system applying differential evolution method |
| CN115511875A (en) * | 2022-10-28 | 2022-12-23 | 上海东普信息科技有限公司 | Cargo accumulation detection method, device, equipment and storage medium |
| CN116167596A (en) * | 2023-04-25 | 2023-05-26 | 深圳市宏大供应链服务有限公司 | Distribution path analysis method and system based on big data |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111784246B (en) * | 2020-07-01 | 2023-04-07 | 深圳市检验检疫科学研究院 | Logistics path estimation method |
-
2023
- 2023-09-12 CN CN202311172088.0A patent/CN116911470B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106203700A (en) * | 2016-07-11 | 2016-12-07 | 中联物流（中国）有限公司 | The logistics transportation scheme of logistic management system determines method and system |
| CN110111036A (en) * | 2019-03-28 | 2019-08-09 | 跨越速运集团有限公司 | Logistics goods amount prediction technique and system based on LSTM Model Fusion |
| CN111882117A (en) * | 2020-07-07 | 2020-11-03 | 上海中通吉网络技术有限公司 | Express trunk route line flow prediction method, device and equipment |
| CN115204028A (en) * | 2022-04-13 | 2022-10-18 | 赣南师范大学 | Three-dimensional packing optimization method and system applying differential evolution method |
| CN115511875A (en) * | 2022-10-28 | 2022-12-23 | 上海东普信息科技有限公司 | Cargo accumulation detection method, device, equipment and storage medium |
| CN116167596A (en) * | 2023-04-25 | 2023-05-26 | 深圳市宏大供应链服务有限公司 | Distribution path analysis method and system based on big data |
Non-Patent Citations (1)
| Title |
|---|
| 三维多箱异构货物装载优化及其可视化;那日萨;韩琪玮;林正奎;;运筹与管理(04);第76-82页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116911470A (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220084186A1 (en) | Automated inspection system and associated method for assessing the condition of shipping containers | |
| US9830704B1 (en) | Predicting performance metrics for algorithms | |
| US9262681B1 (en) | Probabilistic registration of interactions, actions or activities from multiple views | |
| CN116167596B (en) | Distribution path analysis method and system based on big data | |
| CN110057292B (en) | Method and device for determining carriage loading rate | |
| CN108579094B (en) | User interface detection method, related device, system and storage medium | |
| US8295583B2 (en) | System and method for automatic recognition of undetected assets | |
| US10373316B2 (en) | Images background subtraction for dynamic lighting scenarios | |
| CN111626277A (en) | Vehicle tracking method and device based on over-station inter-modulation index analysis | |
| CN111814739B (en) | Method, device, equipment and storage medium for detecting express package volume | |
| CN112766069A (en) | Vehicle illegal parking detection method and device based on deep learning and electronic equipment | |
| CN114022537B (en) | Method for analyzing loading rate and unbalanced loading rate of vehicle in dynamic weighing area | |
| CN115860645A (en) | Logistics storage management method and system based on big data | |
| CN115456474A (en) | Port operation scheduling method and system based on artificial intelligence | |
| CN115272234A (en) | Bottle cap quality detection method and device, computer equipment and storage medium | |
| CN116911470B (en) | Data analysis method, system and storage medium based on deep learning | |
| CN114283383A (en) | Smart city highway maintenance method, computer equipment and medium | |
| CN113825225B (en) | Roaming registration method, AMF network element, equipment and system of private network | |
| CN114049575A (en) | Intelligent detection method and system for contraband of security check machine and electronic equipment | |
| US20230114688A1 (en) | Edge computing device and system for vehicle, container, railcar, trailer, and driver verification | |
| CN115018433B (en) | Wine supply chain monitoring method, device, equipment and medium | |
| CN113496212A (en) | Text recognition method and device for box-type structure and electronic equipment | |
| CN111507119A (en) | Identification code identification method and device, electronic equipment and computer readable storage medium | |
| CN114399671A (en) | Target identification method and device | |
| CN114596033A (en) | Intelligent logistics planning monitoring method and system based on deep learning |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240326 Address after: 518000 Room 301, building B, floor 3, coastal future incubation center, Longyuan community, Longhua street, Longhua District, Shenzhen, Guangdong Province Patentee after: Shenzhen Zhiyang culture media Co.,Ltd. Country or region after: China Address before: 518000 Room 2705, Baofa Building, Shatoujiao Bonded Zone, Yantian District, Shenzhen, Guangdong Province Patentee before: SHENZHEN HONGDA SUPPLY CHAIN SERVICE Co.,Ltd. Country or region before: China |
|
| TR01 | Transfer of patent right |