CN116450575A - File informatization management archiving system based on deep learning network - Google Patents
File informatization management archiving system based on deep learning network Download PDFInfo
- Publication number
- CN116450575A CN116450575A CN202310316036.XA CN202310316036A CN116450575A CN 116450575 A CN116450575 A CN 116450575A CN 202310316036 A CN202310316036 A CN 202310316036A CN 116450575 A CN116450575 A CN 116450575A
- Authority
- CN
- China
- Prior art keywords
- unit
- deep learning
- archive
- management
- archiving
- 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
- 238000013135 deep learning Methods 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 claims abstract description 18
- 239000000284 extract Substances 0.000 claims description 5
- 239000003086 colorant Substances 0.000 claims description 3
- 238000013075 data extraction Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000003442 weekly effect Effects 0.000 claims description 3
- 238000007726 management method Methods 0.000 description 42
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06F16/11—File system administration, e.g. details of archiving or snapshots
- G06F16/113—Details of archiving
-
- 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
- G06F16/11—File system administration, e.g. details of archiving or snapshots
- G06F16/122—File system administration, e.g. details of archiving or snapshots using management policies
-
- 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
- G06F16/16—File or folder operations, e.g. details of user interfaces specifically adapted to file systems
-
- 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
- G06F16/16—File or folder operations, e.g. details of user interfaces specifically adapted to file systems
- G06F16/168—Details of user interfaces specifically adapted to file systems, e.g. browsing and visualisation, 2d or 3d GUIs
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a file informatization management filing system based on a deep learning network, which belongs to the technical field of informatization file management, and comprises a deep learning unit, a file management filing unit, a user login unit and an administrator login unit; the user login unit is used for archivally extracting user access archives, and comprises user name and password information; the archive management and archiving unit is used for archiving and managing the uploaded archives, electronically classifying the archives and marking the classified archives in sequence; the deep learning unit is used for automatically classifying the files uploaded by the file management archiving unit by adopting a deep learning method; the manager login unit is used for the manager to log in the system, and the manager can check the non-manager login information after logging in; the system combines the file management by utilizing the deep learning method, can automatically classify the files, greatly ensures the safety of the file flow direction, and can realize the dynamic record of the file flow direction.
Description
Technical Field
The invention belongs to the technical field of informationized archive management, and particularly relates to an archive informationized management archiving system based on a deep learning network.
Background
File management is also called file work, and is a general term for business works in which file offices directly manage file entities and file information and provide services. With the development of paperless office work, file management is not limited to the management of paper files, but also includes the management of electronic files.
In the existing file management system, a manager needs to collect the content of a paper file by using a collection device, such as a high-speed camera, then produce an electronic file, store the electronic file in the management system, and provide the file name or number of the electronic file to the manager when the borrower borrows the electronic file, so that the manager can retrieve the electronic file from the management system by the file name or number provided by the borrower. However, when the borrower does not know the determined file name or number, the manager is required to browse a large number of electronic files and find the electronic files which the borrower wants to borrow from the electronic files, so that the searching time is too long, the efficiency of the borrowing work is reduced, and the management work is not utilized. The archives are original records with preservation value, which are directly formed by people in various social activities, and the archives management is necessary work for maintaining and maintaining the authenticity of the history records, the archives record the development history of growth, record accurate and rich information, collect a large amount of resources and provide effective and precious materials for the development and management work in future;
under the new historical period, the same as other works, the archive management work also follows the pace of time development, the informationized management of archives is realized under the assistance of an Internet platform, the informationized management promotes archive construction, but in the process of archive circulation, the security of archive flow direction is difficult to ensure, the dynamic record of archive flow direction is more difficult to realize, the fluidity of archive flow direction cannot be estimated, and the construction of archive informationized management is greatly hindered.
Deep learning originates from neural networks, but this framework is now being exceeded. Several deep learning frameworks such as deep neural networks, convolutional neural networks, deep belief networks, recurrent neural networks, etc. have been applied to the fields of computer vision, speech recognition, natural language processing, audio recognition, bioinformatics, etc. and have achieved excellent results.
The motivation for deep learning is to build a neural network that can simulate the human brain for analysis learning, which mimics the mechanisms of the human brain to interpret data, such as images, text, sounds, and the like. The deep learning is realized by learning a deep nonlinear network structure, the approximation of complex functions can be realized by only a simple network structure, and the strong capability of learning the essential characteristics of the data set from a large number of unlabeled sample sets is shown. Deep learning can obtain features that better represent data, and has the ability to represent large-scale data because of the deep hierarchy of the model (usually 5, 6, and even 10 hidden nodes, the "deep" benefit is that the number of hidden nodes can be controlled to be polynomial times, rather than up to exponential times, the number of input nodes), and the strong expressive power.
Therefore, in the research of the applicant, it is found that the deep learning method can be used for combining with file management, so that file classification can be automatically performed, the safety of file flow direction is greatly ensured, and the dynamic record of file flow direction can be realized.
Disclosure of Invention
The invention aims to provide a file informatization management filing system based on a deep learning network, which combines file management by using a deep learning method, can automatically classify files, greatly ensures the safety of file flow direction and can realize dynamic record of file flow direction.
In order to achieve the above purpose, the present invention provides the following technical solutions: the archive information management and archiving system based on the deep learning network comprises a deep learning unit, an archive management and archiving unit, a user login unit and an administrator login unit;
the user login unit is used for archivally extracting user access archives, and comprises user name and password information;
the archive management and archiving unit is used for archiving and managing the uploaded archives, electronically classifying the archives and marking the classified archives in sequence;
the deep learning unit is used for automatically classifying the files uploaded by the file management archiving unit by adopting a deep learning method;
the administrator login unit is used for logging in the system by an administrator, and after the administrator logs in, non-administrator login information can be checked;
the user login unit is connected with the deep learning unit, the deep learning unit is connected with the archive management unit, and the administrator login unit can extract user login unit login information.
Preferably, the archive management and archiving unit includes an archive upload port, the archive upload port inputs archive archiving time information when uploading the archive, and the archive upload port is presented after the user logs in.
Preferably, the archive method adopted by the archive management archive unit includes the following steps:
(1) each month is divided into five weeks for management, the last week covers 0-3 days, and five types of folders which are W1/W2/W3/W4/W5 are reflected in the archive management unit;
(2) the weekly time is marked by adopting color classification, and the first to fifth weeks are respectively marked by adopting five colors of red, orange, yellow, green and blue.
Preferably, the deep learning unit includes the steps of: before the deep learning method is used, firstly, image extraction is carried out on uploaded archival data, time information obtained by image data extraction is classified according to months, the number of days in the month in the image is further read, the date is converted into two-dimensional data, fourier transformation is carried out on each frame of image data, days and five weeks of the month obtained by recognition are taken as two dimensions of the data, and each point in the data corresponds to different color identifications.
Preferably, the non-administrator information includes login time, login stay system time, and history click document.
Preferably, the method further comprises the steps of: when the newly uploaded files are classified, the color points are read internally according to the two-dimensional data image, and the classification can be completed.
Preferably, the administrator login unit further comprises a popup window module, and when the login residence time is monitored to be more than 30-60 min, popup window reminding occurs.
Preferably, the method further comprises the steps of: when the month is identified, the month is directly identified by adopting identification information, and the month is established at the upper position of the day data.
The beneficial effects of the invention are as follows:
1. the files are uploaded through different user logins, the files are automatically classified, the files can be managed by the files in different places such as institutions and schools, after the user logins, the files are uploaded to the system, the system firstly performs image scanning identification on the files through a deep learning unit and extracts time information for establishing the internal files, the files can be automatically archived and classified through a deep learning method, and the files are classified according to established time of the files, so that the files are convenient to search.
2. The administrator login unit is arranged, so that an administrator can monitor the system in real time, user login information can be collected in the administrator login unit, the administrator can search user side login information in the system, accurately and quickly search targets, loss is avoided, further, in background data, the administrator side logs in real time through the administrator login unit and monitors the user information, when the residence time of a user exceeds 30min, the administrator side has a popup prompt, and after the prompt, the administrator can automatically close the system, so that file loss is avoided.
Drawings
Fig. 1 is a schematic structural diagram of an archive information management and archiving system based on a deep learning network.
Detailed Description
For a further understanding of the invention, its features and advantages, reference is now made to the following examples, which are illustrated in the accompanying drawings.
Referring to fig. 1, a detailed description will be given of a deep learning network-based archive information management system according to an embodiment of the present invention with reference to the accompanying drawings.
As shown in fig. 1, the archive information management and archiving system based on the deep learning network comprises a deep learning unit, an archive management and archiving unit, a user login unit and an administrator login unit;
the user login unit is used for archivally extracting user access archives, and comprises user name and password information;
the archive management and archiving unit is used for archiving and managing the uploaded archives, electronically classifying the archives and marking the classified archives in sequence;
the deep learning unit is used for automatically classifying the files uploaded by the file management archiving unit by adopting a deep learning method;
the administrator login unit is used for logging in the system by an administrator, and after the administrator logs in, non-administrator login information can be checked;
the user login unit is connected with the deep learning unit, the deep learning unit is connected with the archive management unit, and the administrator login unit can extract user login unit login information.
The archive management archiving unit comprises an archive uploading port, the archive uploading port inputs archive archiving time information when uploading the archive, and the archive uploading port is presented after the user logs in.
Specifically, the archive method adopted by the archive management archive unit includes the following steps:
(1) each month is divided into five weeks for management, the last week covers 0-3 days, and five types of folders which are W1/W2/W3/W4/W5 are reflected in the archive management unit;
(2) the weekly time is marked by adopting color classification, and the first to fifth weeks are respectively marked by adopting five colors of red, orange, yellow, green and blue.
Specifically, the deep learning unit includes the steps of: before the deep learning method is used, firstly, image extraction is carried out on uploaded archival data, time information obtained by image data extraction is classified according to months, the number of days in the month in an image is further read, the date is converted into two-dimensional data, fourier transformation is carried out on each frame of image data, days and five weeks of the number of the month obtained by identification are taken as two dimensions of the data, each point in the data corresponds to different color identifications, meanwhile, when the month is obtained by identification, identification information is directly adopted for identification of the month, and the upper position of the day data is established.
When the newly uploaded files are classified, the color points are read internally according to the two-dimensional data image, and the classification can be completed.
The deep learning units are all provided with image recognition and capturing modules, and when the new archive file is obtained, the time displayed on the first page of the archive file is recognized by the image recognition and capturing modules, and the number of months and the number of days are recognized, and as the number of days corresponding to each month is different, the number of months is firstly recognized to correspond to different two-dimensional images, namely, the last week is classified into different categories covering 0-3 days. And further searching the corresponding color points in the corresponding two-dimensional image according to the number of days obtained by recognition.
Specifically, the non-administrator information includes login time, login stay system time, and history click document.
Specifically, the manager login unit further comprises a popup window module, and when the login residence time is monitored to be more than 30-60 min, popup window reminding occurs.
The file management method comprises the following specific implementation processes that uploading of files is completed through different user logins, meanwhile, files are automatically classified, users can cover different places such as institutions and schools and use file management, after the users log in, the files are uploaded to the inside of a system, and the inside of the system firstly performs image scanning identification on the files through a deep learning unit and extracts time information for establishing the internal files.
Further, after time information is obtained through recognition, data are substituted into a two-dimensional model established according to deep learning, color identification of the archive is obtained, and then the archive is classified into archive folders under target months according to month data at a first-level position, and meanwhile the archive is further classified into the archive folders under the target months by utilizing the correspondence between the five folders and color points according to W1/W2/W3/W4/W5, so that archiving is completed.
When a user logs in to inquire a file or calls out the file, the user logs in again, enters the system to search the file, can quickly search according to the filing time of the file, and simultaneously in background data, an administrator logs in real time through an administrator login unit and monitors user information, when the residence time of the user is 30min, the administrator has a popup prompt, and after the prompt, the administrator can automatically close the system to avoid file loss.
Meanwhile, if the file is lost and damaged, an administrator can search the login information of the user side in the system, accurately and quickly search the target, and avoid the loss.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. The archive information management and archiving system based on the deep learning network is characterized by comprising a deep learning unit, an archive management and archiving unit, a user login unit and an administrator login unit;
the user login unit is used for archivally extracting user access archives, and comprises user name and password information;
the archive management and archiving unit is used for archiving and managing the uploaded archives, electronically classifying the archives and marking the classified archives in sequence;
the deep learning unit is used for automatically classifying the files uploaded by the file management archiving unit by adopting a deep learning method;
the administrator login unit is used for logging in the system by an administrator, and after the administrator logs in, non-administrator login information can be checked;
the user login unit is connected with the deep learning unit, the deep learning unit is connected with the archive management unit, and the administrator login unit can extract user login unit login information.
2. The archive information management and archiving system based on the deep learning network of claim 1, wherein the archive management and archiving unit includes an archive upload port, the archive upload port inputs archive time information when uploading the archive, and the archive upload port is presented after the user logs in.
3. The archive information management archiving system based on the deep learning network according to claim 2, wherein the archive management archiving unit adopts an archiving method comprising the steps of:
(1) each month is divided into five weeks for management, the last week covers 0-3 days, and five types of folders which are W1/W2/W3/W4/W5 are reflected in the archive management unit;
(2) the weekly time is marked by adopting color classification, and the first to fifth weeks are respectively marked by adopting five colors of red, orange, yellow, green and blue.
4. The archive information management archiving system based on the deep learning network of claim 1, wherein the deep learning unit comprises the following steps: before the deep learning method is used, firstly, image extraction is carried out on uploaded archival data, time information obtained by image data extraction is classified according to months, the number of days in the month in the image is further read, the date is converted into two-dimensional data, fourier transformation is carried out on each frame of image data, days and five weeks of the month obtained by recognition are taken as two dimensions of the data, and each point in the data corresponds to different color identifications.
5. The deep learning network based archive informationized management archiving system of claim 1, wherein the non-administrator information comprises login time, login stay system time, and historical click document.
6. The deep learning network based archive informatization management archiving system of claim 4, further comprising the steps of: when the newly uploaded files are classified, the color points are read internally according to the two-dimensional data image, and the classification can be completed.
7. The archive information management and archiving system based on the deep learning network of claim 5, wherein the administrator login unit further comprises a popup module, and the popup prompt occurs when the login residence system time is monitored to be more than 30-60 min.
8. The deep learning network based archive informatization management archiving system of claim 4, further comprising the steps of: when the month is identified, the month is directly identified by adopting identification information, and the month is established at the upper position of the day data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310316036.XA CN116450575A (en) | 2023-03-29 | 2023-03-29 | File informatization management archiving system based on deep learning network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310316036.XA CN116450575A (en) | 2023-03-29 | 2023-03-29 | File informatization management archiving system based on deep learning network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116450575A true CN116450575A (en) | 2023-07-18 |
Family
ID=87129433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310316036.XA Pending CN116450575A (en) | 2023-03-29 | 2023-03-29 | File informatization management archiving system based on deep learning network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116450575A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116719956A (en) * | 2023-08-08 | 2023-09-08 | 东莞市铁石文档科技有限公司 | File classification management system and method based on big data |
-
2023
- 2023-03-29 CN CN202310316036.XA patent/CN116450575A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116719956A (en) * | 2023-08-08 | 2023-09-08 | 东莞市铁石文档科技有限公司 | File classification management system and method based on big data |
| CN116719956B (en) * | 2023-08-08 | 2024-01-26 | 东莞市铁石文档科技有限公司 | File classification management system and method based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109767255B (en) | Method for realizing intelligent operation and accurate marketing through big data modeling | |
| US10896288B1 (en) | Systems, devices, and methods for software coding | |
| Pan et al. | A smart mobile diagnosis system for citrus diseases based on densely connected convolutional networks | |
| Nelson et al. | Five task clusters that enable efficient and effective digitization of biological collections | |
| CN105809606A (en) | Big data application platform system | |
| CN107730430A (en) | Production, teaching ＆ research public service system based on big data | |
| CN109658062A (en) | A kind of electronic record intelligent processing method based on deep learning | |
| WO2017000880A1 (en) | Information processing method, information processing device and video monitoring system | |
| CN116450575A (en) | File informatization management archiving system based on deep learning network | |
| CN111813763A (en) | Fusion sharing platform based on diversified data | |
| CN105956125A (en) | Patent monitoring system and method | |
| US20220050867A1 (en) | Image management with region-based metadata indexing | |
| CN112348003A (en) | Airplane refueling scene recognition method and system based on deep convolutional neural network | |
| CN111723239A (en) | Multi-mode-based video annotation method | |
| Zhou | Application research of face recognition technology in smart campus | |
| CN111814200A (en) | Automatic digital government affair service system based on block chain technology | |
| CN112560411A (en) | Intelligent personnel information input method and system | |
| DE112021003964T5 (en) | RECOMMEND LOCATION AND CONTENT AWARENESS FILTERS FOR DIGITAL PHOTOS | |
| CN110457505A (en) | The method and apparatus for carrying out relation excavation based on chart database | |
| Sivčević et al. | Possibilities of used intelligence based agents in instant messaging on e-government services | |
| CN106844393A (en) | A kind of method for building up in video image information storehouse | |
| Cho | Designing smart cities: Security issues | |
| Cunha et al. | Peritus Framework: Towards multimedia evidence analysis uniformization in brazilian distributed forensic model | |
| CN111291376B (en) | Web vulnerability verification method based on crowdsourcing and machine learning | |
| CN106569819A (en) | Automatic screenshot method applied to video monitoring platform |
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 |