CN111984617A - Internet-based quality tracing method for picture retrieval and associated accessories - Google Patents
Internet-based quality tracing method for picture retrieval and associated accessories Download PDFInfo
- Publication number
- CN111984617A CN111984617A CN202010844339.5A CN202010844339A CN111984617A CN 111984617 A CN111984617 A CN 111984617A CN 202010844339 A CN202010844339 A CN 202010844339A CN 111984617 A CN111984617 A CN 111984617A
- Authority
- CN
- China
- Prior art keywords
- module
- picture
- file
- information
- accessory
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000002159 abnormal effect Effects 0.000 claims description 37
- 239000011159 matrix material Substances 0.000 claims description 30
- 238000013145 classification model Methods 0.000 claims description 27
- 238000001514 detection method Methods 0.000 claims description 17
- 238000013461 design Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 15
- 230000008520 organization Effects 0.000 claims description 10
- 238000010801 machine learning Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000007689 inspection Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 230000000737 periodic effect Effects 0.000 claims description 3
- 230000017105 transposition Effects 0.000 claims description 3
- 230000006855 networking Effects 0.000 abstract description 4
- 238000010276 construction Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/17—Details of further file system functions
- G06F16/176—Support for shared access to files; File sharing support
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/55—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/587—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9532—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/10—Protecting distributed programs or content, e.g. vending or licensing of copyrighted material ; Digital rights management [DRM]
- G06F21/16—Program or content traceability, e.g. by watermarking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Library & Information Science (AREA)
- Computer Hardware Design (AREA)
- Mathematical Physics (AREA)
- Multimedia (AREA)
- Technology Law (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a picture retrieval and associated accessory quality tracing method based on the Internet, which comprises the following steps: establishing a tracing environment: establishing an engineering project information management platform, a tracing terminal and an inquiry terminal, wherein the tracing terminal and the inquiry terminal are respectively connected with the engineering project information management platform through a network; the identity authentication module, the information acquisition module, the sequence generation module, the picture/accessory uploading module, the time axis adding module and the associated accessory module are sequentially connected. According to the quality traceability method of the image retrieval and associated accessories based on the Internet, the engineering project information management platform, the traceability terminal and the query terminal are arranged, and the traceability terminal and the query terminal are respectively connected with the engineering project information management platform through a network, so that all technical data related to networking projects are efficiently shared in a simple image retrieval and super-large accessory mode, and work is cooperated.
Description
Technical Field
The invention relates to the technical field of construction engineering, in particular to a picture retrieval and associated accessory quality tracing method based on the Internet.
Background
The field of construction engineering is national cornerstone, the customs of the affairs is calculated by China, along with the continuous progress of social civilization and science and technology, the contradiction between the production relation and the productivity of the traditional construction industry is more and more prominent, the social development requirement cannot be met, the coordination and unification of all departments of the construction industry are urgently needed, and all mechanisms of construction, design, manufacturing cost, total package, subpackage, supervision and the like jointly and cooperatively promote the revolution and development of the construction industry.
The construction engineering starts from a design organization, particularly a medium-sized and small-sized design organization, and has the problems of few business opportunities, large competition, difficult bid winning, uncontrolled quality management of a hung design engineering project and the like, and engineers are used as basic construction elements of the project and lack effective matching and combination, namely, the engineers with different professional level characteristics cannot be effectively recombined to match a business task, the creativity of the engineers cannot be fully activated, and the management of engineering files is disordered. The method can not be used for sharing the ultra-clear (more than 3000dpi) picture encryption cloud which needs to be solved aiming at the construction engineering data of precise geographic coordinates (longitude and latitude), and sharing the ultra-large (more than 500M) accessory encryption cloud generated by various software associated with the high-definition picture.
Disclosure of Invention
The invention aims to provide an internet-based picture retrieval and associated accessory quality tracing method, which is characterized in that an engineering project information management platform, a tracing terminal and an inquiry terminal are arranged, the tracing terminal and the inquiry terminal are respectively connected with the engineering project information management platform in a network manner, all technical data related to networking projects are efficiently shared in a very simple picture retrieval and oversized accessory manner, and work is coordinated.
In order to achieve the purpose, the invention provides the following technical scheme: the quality tracing method for the picture retrieval and the associated accessories based on the Internet comprises the following steps:
s1: establishing a tracing environment: establishing an engineering project information management platform, a tracing terminal and an inquiry terminal, wherein the tracing terminal and the inquiry terminal are respectively connected with the engineering project information management platform through a network;
the tracing terminal comprises an identity authentication module, an information acquisition module, a sequence generation module, a picture/accessory uploading module, a time axis adding module and a related accessory module, wherein the identity authentication module, the information acquisition module, the sequence generation module, the related accessory module, the time axis adding module and the picture/accessory uploading module are sequentially connected;
the engineering project information management platform is provided with a file version library, a picture/accessory receiving module, a picture/accessory retrieval module and a feedback module, wherein the input end of the picture/accessory receiving module is connected with the picture/accessory uploading module, the output end of the picture/accessory receiving module is connected with the file version library, the file version library is electrically connected with the picture/accessory retrieval module, and the feedback module is connected with the file version library;
the query terminal is provided with a login module and a file retrieval module, the login module is connected with the file retrieval module, and the file retrieval module is connected with the file version library;
s2: file information preprocessing: establishing different project names according to design projects, establishing a file version library in an engineering project information management platform, wherein a time axis is used as a transverse coordinate in the file version library, the file names are used as a longitudinal coordinate, and different file versions are established by using the same time axis;
s3: uploading a new file: after a designer/contractor/design organization logs in a traceability terminal, uploading a new file to an engineering project information management platform;
s4: creating a new file: the image/attachment receiving module receives an image/attachment, creates a new file version in the file version library, receives the new file version in the file version library and automatically updates a historical file;
s5: retrieving the file: the searching personnel logs in at the inquiry terminal, inputs the name of the searching file after authenticating the identity information, the picture/attachment searching module searches for the corresponding file, the picture file divided by the time axis appears, the searching personnel opens the corresponding file, and the picture/attachment information can be obtained.
Preferably, the information acquisition module is provided with an information acquisition unit and a rechecking unit, the rechecking unit is provided with a database and a manual detection unit, and the database is divided into a numerical database and a character database;
numerical database: carrying out periodic calculation on data belonging to numerical types, modeling through a machine learning algorithm, establishing a numerical normal knowledge base and a numerical abnormal knowledge base, and storing corresponding numerical data into corresponding knowledge bases;
character type database: the method comprises the steps of carrying out word segmentation processing on data belonging to character types to judge character entropies, modeling through a machine learning algorithm, calculating outliers to distinguish abnormal data, simultaneously establishing a character normal knowledge base and a character abnormal knowledge base, and storing corresponding character type data into corresponding knowledge bases.
Preferably, the information acquisition unit is connected with the database, and the manual detection unit is respectively connected with the numerical value abnormal knowledge base and the character abnormal knowledge base.
Preferably, the time axis adding module is provided with an automatic adding unit and a detecting unit, and the automatic adding unit is connected with the checking unit.
Preferably, the uploading the new file comprises the following steps:
s301: the designer/contractor/design organization registers login information through the identity authentication module and performs identity authentication;
s302: uploading the picture/attachment of the new file to an information acquisition module, and acquiring time information, geographic information and picture characteristic information in the picture/attachment by the information acquisition module;
s303: the sequence generation module generates a picture serial number for the picture/accessory;
s304: the time axis adding module is used for carrying out time classification on the new pictures/accessories and adding an engineering time axis;
s305: and the associated attachment module generates associated attachments from the time information, the geographic information, the picture serial number and the engineering time axis, and the associated attachments are uploaded to the engineering project information management platform by the picture/attachment uploading module.
Preferably, the step of collecting information by the S302 information collecting module includes the steps of:
s3021: the information acquisition module respectively generates corresponding digital models and character models from the time information, the geographic information and the picture characteristic information, and the digital models and the character models are respectively corresponding to the numerical database and the character database for comparison;
s3022: when the digital model and the character model are both in the normal knowledge base, continuing to the next step, and generating a sequence by a sequence generation module; when one of the digital model or the character model is not in the normal knowledge base, the judgment result is pushed to the manual detection unit;
s3023: the manual detection unit is used for self-checking by an uploader, whether the picture/accessory information is wrong or not is judged, the information is wrong, the uploading is stopped, the information is correct, the uploading is continued, the feedback unit trains classification models by using sample data in the normal knowledge base and the abnormal knowledge base, and the classification models obtained by training are used for carrying out abnormal judgment on subsequent new sample data and storing the new data information into the normal knowledge base.
Preferably, the adding the time axis by the time axis adding module in S304 includes the following steps:
s3041: the automatic adding unit automatically judges the time shaft range to which the picture characteristic information belongs;
s3042: after classification, the information is automatically transmitted to an inspection unit for manual inspection, if the information is correct, the next step is carried out, and if the classification is wrong, the information is reclassified manually and uploaded.
Preferably, the creating of the new file includes the following steps:
s401: the picture/attachment receiving module receives a picture/attachment and creates a file name;
s402: according to the file name, the project time axis and the picture serial number on the picture/attachment, the file version library fills the corresponding picture/attachment file into the corresponding file version at the same time;
s403: the feedback module trains a classification model by using the sample data, and the classification model obtained by training is added into the file version library.
Preferably, the specific steps of performing anomaly determination on subsequent new sample data by using the trained classification model and storing new data information into the normal knowledge base in step S3023 are as follows:
step A1, carrying out exception judgment on the new sample data, converting the new sample data into a data matrix X, carrying out data normalization on the data matrix X to form a normalized data matrix X ', wherein each row of X ' represents a new sample data, and the normalized data matrix X ' has m rows in total, namely m new sample data;
step a2, a decision matrix corresponding to the data matrix X' is obtained according to the following formula:
wherein, X' represents a normalized data matrix, T represents a matrix transposition, ln represents a logarithm taking e as a base, sum () represents a summation, b represents a bias value of a classification model obtained by training, theta represents a weight value of the classification model obtained by training, and e represents a natural constant;
and A3, according to the judgment matrix h (X') obtained in the step A2, the matrix is m rows and 1 column, the m rows represent abnormal judgment values corresponding to m new sample data, when the judgment value is less than 0.5, the new sample data is abnormal, and when the judgment value is more than or equal to 0.5, the new sample data is normal.
Compared with the prior art, the invention has the beneficial effects that: the image retrieval and associated accessory quality tracing method based on the Internet is characterized in that an engineering project information management platform, a tracing terminal and an inquiry terminal are arranged, the tracing terminal and the inquiry terminal are respectively connected with the engineering project information management platform through a network, all technical data related to networking projects are efficiently shared in a very simple image retrieval and super-large accessory mode, and work is coordinated.
Drawings
FIG. 1 is a flow chart of the steps of the present invention;
FIG. 2 is a block diagram of the present invention;
FIG. 3 is a block diagram of an information collection module according to the present invention;
FIG. 4 is a flow chart of uploading a new file according to the present invention;
FIG. 5 is a flow chart of the information collection module of the present invention collecting information;
FIG. 6 is a flow chart of the timeline adding module of the present invention adding timeline;
FIG. 7 is a flow chart of the present invention for creating a new file;
fig. 8 is a functional diagram of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The first embodiment is as follows:
referring to fig. 1-8, the internet-based picture retrieval and associated attachment quality tracing method includes the following steps:
s1: establishing a tracing environment: establishing an engineering project information management platform, a tracing terminal and an inquiry terminal, wherein the tracing terminal and the inquiry terminal are respectively connected with the engineering project information management platform through a network;
the source tracing terminal comprises an identity authentication module, an information acquisition module, a sequence generation module, a picture/accessory uploading module, a time axis adding module and an associated accessory module, wherein the identity authentication module, the information acquisition module, the sequence generation module, the associated accessory module, the time axis adding module and the picture/accessory uploading module are sequentially connected;
numerical database: carrying out periodic calculation on data belonging to numerical types, modeling through a machine learning algorithm, establishing a numerical normal knowledge base and a numerical abnormal knowledge base, and storing corresponding numerical data into corresponding knowledge bases, wherein the numerical database is suitable for judging whether the date is correct or not;
character type database: performing word segmentation processing on data belonging to character types to judge character entropy, modeling through a machine learning algorithm, calculating outliers to distinguish abnormal data, establishing a character normal knowledge base and a character abnormal knowledge base at the same time, and storing corresponding character type data into corresponding knowledge bases, wherein the character type databases are suitable for judging geographic information and picture characteristic information;
the information acquisition unit is connected with the database, the manual detection unit is respectively connected with the numerical value abnormal knowledge base and the character abnormal knowledge base, when the numerical value is abnormal, the accuracy of uploading data can be improved through manual judgment, and the possibility of uploading wrong information is avoided or reduced;
the engineering project information management platform is provided with a file version library, a picture/accessory receiving module, a picture/accessory retrieval module and a feedback module, wherein the input end of the picture/accessory receiving module is connected with the picture/accessory uploading module and used for receiving pictures/accessories, the output end of the picture/accessory receiving module is connected with the file version library, the file version library is electrically connected with the picture/accessory retrieval module, the feedback module is connected with the file version library, and the feedback module adds a new version to the file version library;
the query terminal is provided with a login module and a file retrieval module, the login module is connected with the file retrieval module, the file retrieval module is connected with the file version library, and resource sharing can be provided for more personnel through the query terminal;
s2: file information preprocessing: establishing different project names according to design projects, establishing a file version library in an engineering project information management platform, wherein a time axis is used as a transverse coordinate in the file version library, the file names are used as a longitudinal coordinate, and different file versions are established by using the same time axis;
s3: uploading a new file: after a designer/manufacturer/design organization logs in a traceability terminal, a new file is uploaded to an engineering project information management platform, and the method specifically comprises the following steps:
s301: the designer/contractor/design organization registers login information through the identity authentication module and performs identity authentication;
s302: uploading the picture/attachment of the new file to an information acquisition module, wherein the information acquisition module acquires time information, geographic information and picture characteristic information in the picture/attachment, and the method specifically comprises the following steps:
s3021: the information acquisition module respectively generates corresponding digital models and character models from the time information, the geographic information and the picture characteristic information, and the digital models and the character models are respectively corresponding to the numerical database and the character database for comparison;
s3022: when the digital model and the character model are both in the normal knowledge base, continuing to the next step, and generating a sequence by a sequence generation module; when one of the digital model or the character model is not in the normal knowledge base, the judgment result is pushed to the manual detection unit;
s3023: the manual detection unit is self-checked by an uploader, whether picture/accessory information is wrong or not and the information is wrong are judged, the uploading is stopped, the information is correct, the uploading is continued, the feedback unit trains classification models by using sample data in a normal knowledge base and an abnormal knowledge base, the classification models obtained by training are used for carrying out abnormal judgment on subsequent new sample data, meanwhile, the new data information is stored in the normal knowledge base, the training and classification are carried out through various machine learning classification algorithms, the classification model with the highest accuracy can be selected, and in the later judgment, the classification model can be automatically updated along with the continuous updating of the data so as to adapt to the change of the data, and the adaptability is stronger;
in step S3023, the specific steps of performing anomaly determination on subsequent new sample data by using the trained classification model and storing new data information in the normal knowledge base are as follows:
step A1, carrying out exception judgment on the new sample data, converting the new sample data into a data matrix X, carrying out data normalization on the data matrix X to form a normalized data matrix X ', wherein each row of X ' represents a new sample data, and the normalized data matrix X ' has m rows in total, namely m new sample data;
step a2, a decision matrix corresponding to the data matrix X' is obtained according to the following formula:
wherein, X' represents a normalized data matrix, T represents a matrix transposition, ln represents a logarithm taking e as a base, sum () represents a summation, b represents a bias value of a classification model obtained by training, theta represents a weight value of the classification model obtained by training, and e represents a natural constant;
and A3, according to the judgment matrix h (X') obtained in the step A2, the matrix is m rows and 1 column, the m rows represent abnormal judgment values corresponding to m new sample data, when the judgment value is less than 0.5, the new sample data is abnormal, and when the judgment value is more than or equal to 0.5, the new sample data is normal.
Has the advantages that: by utilizing the technology, whether the data are abnormal or not is judged rapidly and accurately, in the judgment process, the result is judged by computer calculation without human intervention, so that the process is small in workload and strong in practicability, 2-class judgment is used, 0.5 is used as a boundary, new sample data is abnormal when the judgment value is less than 0.5, the new sample data is normal when the judgment value is greater than or equal to 0.5, the judgment value is calculated rapidly and effectively, all data are integrated together for abnormal judgment, the abnormal judgment speed is increased, the judgment result and the new data information are stored in a normal knowledge base conveniently, and the errors in the data are reduced.
S303: the sequence generation module generates a picture serial number for the picture/accessory;
s304: the time axis adding module is used for carrying out time classification on the new pictures/accessories and adding an engineering time axis; the method specifically comprises the following steps:
s3041: the automatic adding unit automatically judges the time shaft range to which the picture characteristic information belongs;
s3042: after classification is finished, the information is automatically transmitted to an inspection unit and is inspected manually, if the information is correct, the next step is carried out, and if the classification is wrong, the information is reclassified manually and uploaded;
s305: the associated attachment module generates associated attachments from the time information, the geographic information, the picture serial number and the engineering time axis, and the associated attachments are uploaded to the engineering project information management platform by the picture/attachment uploading module;
s4: creating a new file: the method comprises the following steps that an image/attachment receiving module receives an image/attachment, creates a new file version in a file version library, receives the new file version in the file version library, and automatically updates a history file, and specifically comprises the following steps:
s401: the picture/attachment receiving module receives a picture/attachment and creates a file name;
s402: according to the file name, the project time axis and the picture serial number on the picture/attachment, the file version library fills the corresponding picture/attachment file into the corresponding file version at the same time;
s403: the feedback module trains a classification model by using the sample data, and the classification model obtained by training is added to a file version library;
s5: retrieving the file: the searching personnel logs in at the inquiry terminal, inputs the name of the searching file after authenticating the identity information, the picture/attachment searching module searches for the corresponding file, the picture file divided by the time axis appears, the searching personnel opens the corresponding file, and the picture/attachment information can be obtained.
Example two:
the quality tracing method for the picture retrieval and the associated accessories based on the Internet comprises the following steps:
s1: establishing a tracing environment: establishing an engineering project information management platform, a tracing terminal and an inquiry terminal, wherein the tracing terminal and the inquiry terminal are respectively connected with the engineering project information management platform through a network;
the source tracing terminal comprises an identity authentication module, an information acquisition module, a sequence generation module, a picture/accessory uploading module, a time axis adding module and a related accessory module, wherein the identity authentication module, the information acquisition module, the sequence generation module, the related accessory module, the time axis adding module and the picture/accessory uploading module are sequentially connected, an information acquisition unit and a rechecking unit are arranged in the information acquisition module, a database and a manual detection unit are arranged in the rechecking unit, the database is divided into character type databases, an automatic adding unit and a detection unit are arranged in the time axis adding module, and the automatic adding unit is connected with the checking unit;
character type database: performing word segmentation processing on data belonging to character types to judge character entropy, modeling through a machine learning algorithm, calculating outliers to distinguish abnormal data, establishing a character normal knowledge base and a character abnormal knowledge base at the same time, and storing corresponding character type data into corresponding knowledge bases, wherein the character type databases are suitable for judging geographic information and picture characteristic information;
the information acquisition unit is connected with the database, the manual detection unit is connected with the character abnormity knowledge base, and when the numerical value is abnormal, the accuracy of uploading data can be improved and the possibility of uploading wrong information is avoided or reduced through manual judgment;
the engineering project information management platform is provided with a file version library, a picture/accessory receiving module, a picture/accessory retrieval module and a feedback module, wherein the input end of the picture/accessory receiving module is connected with the picture/accessory uploading module and used for receiving pictures/accessories, the output end of the picture/accessory receiving module is connected with the file version library, the file version library is electrically connected with the picture/accessory retrieval module, the feedback module is connected with the file version library, and the feedback module adds a new version to the file version library;
the query terminal is provided with a login module and a file retrieval module, the login module is connected with the file retrieval module, and the file retrieval module is connected with the file version library;
s2: file information preprocessing: establishing different project names according to design projects, establishing a file version library in an engineering project information management platform, wherein a time axis is used as a transverse coordinate in the file version library, the file names are used as a longitudinal coordinate, and different file versions are established by using the same time axis;
s3: uploading a new file: after a designer/manufacturer/design organization logs in a traceability terminal, a new file is uploaded to an engineering project information management platform, and the method specifically comprises the following steps:
s301: the designer/contractor/design organization registers login information through the identity authentication module and performs identity authentication;
s302: uploading the picture/attachment of the new file to an information acquisition module, wherein the information acquisition module acquires time information, geographic information and picture characteristic information in the picture/attachment, and the method specifically comprises the following steps:
s3021: the information acquisition module respectively generates corresponding character models from the geographic information and the picture characteristic information, and the character models are compared with the character type database;
s3022: when the character models are in the normal knowledge base, continuing the next step, generating a sequence by a sequence generation module, and if one of the character models is not in the normal knowledge base, pushing a judgment result to a manual detection unit;
s3023: the manual detection unit is used for self-checking by an uploader, whether the picture/accessory information is wrong or not is judged, the information is wrong, the uploading is stopped, the information is correct, the uploading is continued, the feedback unit trains classification models by using sample data in the normal knowledge base and the abnormal knowledge base, and the classification models obtained by training are used for carrying out abnormal judgment on subsequent new sample data and storing the new data information into the normal knowledge base;
s303: the sequence generation module generates a picture serial number for the picture/accessory;
s304: the time axis adding module is used for carrying out time classification on the new pictures/accessories and adding an engineering time axis; the method specifically comprises the following steps:
s3041: the automatic adding unit automatically judges the time shaft range to which the picture characteristic information belongs;
s3042: after classification is finished, the information is automatically transmitted to an inspection unit and is inspected manually, if the information is correct, the next step is carried out, and if the classification is wrong, the information is reclassified manually and uploaded;
s305: the associated attachment module generates associated attachments from the time information, the geographic information, the picture serial number and the engineering time axis, and the associated attachments are uploaded to the engineering project information management platform by the picture/attachment uploading module;
s4: creating a new file: the method comprises the following steps that an image/attachment receiving module receives an image/attachment, creates a new file version in a file version library, receives the new file version in the file version library, and automatically updates a history file, and specifically comprises the following steps:
s401: the picture/attachment receiving module receives a picture/attachment and creates a file name;
s402: the file version library simultaneously fills the corresponding picture/attachment file into the corresponding file version according to the name of the file on the picture/attachment, the engineering time axis and the picture serial number;
s403: the feedback module trains a classification model by using the sample data, and the classification model obtained by training is added to a file version library;
s5: retrieving the file: the searching personnel logs in at the inquiry terminal, inputs the name of the searching file after authenticating the identity information, the picture/attachment searching module searches for the corresponding file, the picture file divided by the time axis appears, the searching personnel opens the corresponding file, and the picture/attachment information can be obtained.
In this embodiment, only a single character-type database is provided, and compared with the first embodiment, in this embodiment, only a character model is established for geographic information and picture characteristic information, and comparison is performed, so that comparison of numerical models of time information is reduced, the time information is generally an uploading date of a picture, an error rate is a small-probability event, and generally no consideration can be given to the comparison, so that comparison of numerical models of time information is reduced, contents of manual review are reduced, and uploading speed can be increased.
In summary, the following steps: the image retrieval and associated accessory quality tracing method based on the Internet is characterized in that an engineering project information management platform, a tracing terminal and an inquiry terminal are arranged, the tracing terminal and the inquiry terminal are respectively connected with the engineering project information management platform through a network, all technical data related to networking projects are efficiently shared in a very simple image retrieval and super-large accessory mode, and work is coordinated.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to cover the technical solutions and the inventive concepts of the present invention within the technical scope of the present invention.
Claims (9)
1. The quality tracing method for the picture retrieval and the associated accessories based on the Internet is characterized by comprising the following steps:
s1: establishing a tracing environment: establishing an engineering project information management platform, a tracing terminal and an inquiry terminal, wherein the tracing terminal and the inquiry terminal are respectively connected with the engineering project information management platform through a network;
the tracing terminal comprises an identity authentication module, an information acquisition module, a sequence generation module, a picture/accessory uploading module, a time axis adding module and a related accessory module, wherein the identity authentication module, the information acquisition module, the sequence generation module, the related accessory module, the time axis adding module and the picture/accessory uploading module are sequentially connected;
the engineering project information management platform is provided with a file version library, a picture/accessory receiving module, a picture/accessory retrieval module and a feedback module, wherein the input end of the picture/accessory receiving module is connected with the picture/accessory uploading module, the output end of the picture/accessory receiving module is connected with the file version library, the file version library is electrically connected with the picture/accessory retrieval module, and the feedback module is connected with the file version library;
the query terminal is provided with a login module and a file retrieval module, the login module is connected with the file retrieval module, and the file retrieval module is connected with the file version library;
s2: file information preprocessing: establishing different project names according to design projects, establishing a file version library in an engineering project information management platform, wherein a time axis is used as a transverse coordinate in the file version library, the file names are used as a longitudinal coordinate, and different file versions are established by using the same time axis;
s3: uploading a new file: after a designer/contractor/design organization logs in a traceability terminal, uploading a new file to an engineering project information management platform;
s4: creating a new file: the image/attachment receiving module receives an image/attachment, creates a new file version in the file version library, receives the new file version in the file version library and automatically updates a historical file;
s5: retrieving the file: the searching personnel logs in at the inquiry terminal, inputs the name of the searching file after authenticating the identity information, the picture/attachment searching module searches for the corresponding file, the picture file divided by the time axis appears, the searching personnel opens the corresponding file, and the picture/attachment information can be obtained.
2. The internet-based picture retrieval and associated attachment quality tracing method of claim 1, wherein: the system comprises an information acquisition module, a manual detection unit, a numerical database and a character database, wherein the information acquisition module is internally provided with an information acquisition unit and a rechecking unit, the rechecking unit is internally provided with the database and the manual detection unit, and the database is divided into the numerical database and the character database;
numerical database: carrying out periodic calculation on data belonging to numerical types, modeling through a machine learning algorithm, establishing a numerical normal knowledge base and a numerical abnormal knowledge base, and storing corresponding numerical data into corresponding knowledge bases;
character type database: the method comprises the steps of carrying out word segmentation processing on data belonging to character types to judge character entropies, modeling through a machine learning algorithm, calculating outliers to distinguish abnormal data, simultaneously establishing a character normal knowledge base and a character abnormal knowledge base, and storing corresponding character type data into corresponding knowledge bases.
3. The internet-based picture retrieval and associated attachment quality tracing method of claim 2, wherein: the information acquisition unit is connected with the database, and the manual detection unit is respectively connected with the numerical value abnormal knowledge base and the character abnormal knowledge base.
4. The internet-based picture retrieval and associated attachment quality tracing method of claim 1, wherein: the time axis adding module is provided with an automatic adding unit and a detecting unit, and the automatic adding unit is connected with the checking unit.
5. The internet-based picture retrieval and associated attachment quality tracing method of claim 1, wherein: the uploading of the new file comprises the following steps:
s301: the designer/contractor/design organization registers login information through the identity authentication module and performs identity authentication;
s302: uploading the picture/attachment of the new file to an information acquisition module, and acquiring time information, geographic information and picture characteristic information in the picture/attachment by the information acquisition module;
s303: the sequence generation module generates a picture serial number for the picture/accessory;
s304: the time axis adding module is used for carrying out time classification on the new pictures/accessories and adding an engineering time axis;
s305: and the associated attachment module generates associated attachments from the time information, the geographic information, the picture serial number and the engineering time axis, and the associated attachments are uploaded to the engineering project information management platform by the picture/attachment uploading module.
6. The internet-based picture retrieval and associated attachment quality tracing method of claim 5, wherein: the step of collecting information by the S302 information collecting module comprises the following steps:
s3021: the information acquisition module respectively generates corresponding digital models and character models from the time information, the geographic information and the picture characteristic information, and the digital models and the character models are respectively corresponding to the numerical database and the character database for comparison;
s3022: when the digital model and the character model are both in the normal knowledge base, continuing to the next step, and generating a sequence by a sequence generation module; when one of the digital model or the character model is not in the normal knowledge base, the judgment result is pushed to the manual detection unit;
s3023: the manual detection unit is used for self-checking by an uploader, whether the picture/accessory information is wrong or not is judged, the information is wrong, the uploading is stopped, the information is correct, the uploading is continued, the feedback unit trains classification models by using sample data in the normal knowledge base and the abnormal knowledge base, and the classification models obtained by training are used for carrying out abnormal judgment on subsequent new sample data and storing the new data information into the normal knowledge base.
7. The internet-based picture retrieval and associated attachment quality tracing method of claim 5, wherein: the adding of the time axis by the time axis adding module in the S304 comprises the following steps:
s3041: the automatic adding unit automatically judges the time shaft range to which the picture characteristic information belongs;
s3042: after classification, the information is automatically transmitted to an inspection unit for manual inspection, if the information is correct, the next step is carried out, and if the classification is wrong, the information is reclassified manually and uploaded.
8. The internet-based picture retrieval and associated attachment quality tracing method of claim 1, wherein: the creating of the new file comprises the following steps:
s401: the picture/attachment receiving module receives a picture/attachment and creates a file name;
s402: according to the file name, the project time axis and the picture serial number on the picture/attachment, the file version library fills the corresponding picture/attachment file into the corresponding file version at the same time;
s403: the feedback module trains a classification model by using the sample data, and the classification model obtained by training is added into the file version library.
9. The internet-based trusted retrieval and associated attachment quality tracing method of claim 6, wherein: in step S3023, the specific steps of performing anomaly determination on subsequent new sample data by using the trained classification model and storing new data information in the normal knowledge base are as follows:
step A1, carrying out exception judgment on the new sample data, converting the new sample data into a data matrix X, carrying out data normalization on the data matrix X to form a normalized data matrix X ', wherein each row of X ' represents a new sample data, and the normalized data matrix X ' has m rows in total, namely m new sample data;
step a2, a decision matrix corresponding to the data matrix X' is obtained according to the following formula:
wherein, X' represents a normalized data matrix, T represents a matrix transposition, ln represents a logarithm taking e as a base, sum () represents a summation, b represents a bias value of a classification model obtained by training, theta represents a weight value of the classification model obtained by training, and e represents a natural constant;
and A3, according to the judgment matrix h (X') obtained in the step A2, the matrix is m rows and 1 column, the m rows represent abnormal judgment values corresponding to m new sample data, when the judgment value is less than 0.5, the new sample data is abnormal, and when the judgment value is more than or equal to 0.5, the new sample data is normal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010844339.5A CN111984617A (en) | 2020-08-20 | 2020-08-20 | Internet-based quality tracing method for picture retrieval and associated accessories |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010844339.5A CN111984617A (en) | 2020-08-20 | 2020-08-20 | Internet-based quality tracing method for picture retrieval and associated accessories |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111984617A true CN111984617A (en) | 2020-11-24 |
Family
ID=73442520
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010844339.5A Pending CN111984617A (en) | 2020-08-20 | 2020-08-20 | Internet-based quality tracing method for picture retrieval and associated accessories |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111984617A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114693098A (en) * | 2022-03-23 | 2022-07-01 | 江苏嘉裕工程管理咨询有限公司 | Engineering cost consultation management planning method |
| CN114983334A (en) * | 2022-01-13 | 2022-09-02 | 中山大学中山眼科中心 | Slit lamp self-adjustment control method based on machine vision and slit lamp |
| CN115578780A (en) * | 2022-12-07 | 2023-01-06 | 广东省科学院江门产业技术研究院有限公司 | Agricultural product and food cold chain traceability management system based on big data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103177308A (en) * | 2011-12-20 | 2013-06-26 | 中工国际工程股份有限公司 | Intelligent decision-making support system for project management |
| CN105096126A (en) * | 2014-05-07 | 2015-11-25 | 北京信威通信技术股份有限公司 | Product information tracing system, terminal and method |
| CN107846461A (en) * | 2017-10-31 | 2018-03-27 | 广州市新誉工程咨询有限公司 | File uploading method and management method and file designation method based on BIM models |
| CN110020798A (en) * | 2019-03-28 | 2019-07-16 | 上海荷福人工智能科技（集团）有限公司 | A kind of approaches to IM of tracing to the source of the project progress based on artificial intelligence |
-
2020
- 2020-08-20 CN CN202010844339.5A patent/CN111984617A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103177308A (en) * | 2011-12-20 | 2013-06-26 | 中工国际工程股份有限公司 | Intelligent decision-making support system for project management |
| CN105096126A (en) * | 2014-05-07 | 2015-11-25 | 北京信威通信技术股份有限公司 | Product information tracing system, terminal and method |
| CN107846461A (en) * | 2017-10-31 | 2018-03-27 | 广州市新誉工程咨询有限公司 | File uploading method and management method and file designation method based on BIM models |
| CN110020798A (en) * | 2019-03-28 | 2019-07-16 | 上海荷福人工智能科技（集团）有限公司 | A kind of approaches to IM of tracing to the source of the project progress based on artificial intelligence |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114983334A (en) * | 2022-01-13 | 2022-09-02 | 中山大学中山眼科中心 | Slit lamp self-adjustment control method based on machine vision and slit lamp |
| CN114693098A (en) * | 2022-03-23 | 2022-07-01 | 江苏嘉裕工程管理咨询有限公司 | Engineering cost consultation management planning method |
| CN115578780A (en) * | 2022-12-07 | 2023-01-06 | 广东省科学院江门产业技术研究院有限公司 | Agricultural product and food cold chain traceability management system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111984617A (en) | Internet-based quality tracing method for picture retrieval and associated accessories | |
| CN110442847B (en) | Code similarity detection method and device based on code warehouse process management | |
| CN108345658B (en) | Decomposition processing method of algorithm calculation track, server and storage medium | |
| WO2020215675A1 (en) | Method and apparatus for building medical treatment database, and computer device and storage medium | |
| US11966402B2 (en) | Context driven data profiling | |
| CN106485261A (en) | A kind of method and apparatus of image recognition | |
| US20150113008A1 (en) | Providing automatable units for infrastructure support | |
| CN111428095B (en) | Graph data quality verification method and graph data quality verification device | |
| CN111160783A (en) | Method and system for evaluating digital asset value and electronic equipment | |
| CN115879748A (en) | Enterprise informatization management integration platform based on big data | |
| CN115713404A (en) | Credit evaluation method for construction industry enterprises | |
| CN117829291B (en) | Whole-process consultation knowledge integrated management system and method | |
| Van Dang | Specification Case Studies in RAISE | |
| CN114862140A (en) | Behavior analysis-based potential evaluation method, device, equipment and storage medium | |
| US8935653B2 (en) | System advisor for requirements gathering and analysis in web solutions | |
| CN117370317A (en) | Data model quality auditing method, device, equipment and storage medium | |
| CN117093556A (en) | Log classification method, device, computer equipment and computer readable storage medium | |
| CN111241821B (en) | Method and device for determining behavior characteristics of user | |
| CN112052310A (en) | Information acquisition method, device, equipment and storage medium based on big data | |
| CN113779116B (en) | Object ordering method, related equipment and medium | |
| US7149739B1 (en) | System and method for performing ratio planning | |
| CN114186974A (en) | Multi-model fusion development task association method, device, equipment and medium | |
| CN114860851A (en) | Data processing method, device, equipment and storage medium | |
| CN112147974A (en) | Alarm root cause diagnosis method based on chemical process knowledge automation | |
| Gezan et al. | User’s manual for ASRgenomics v. 1.1. 0: An R package with complementary genomic functions |
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 |