CN112749379A - Deep learning-based project declaration system and method - Google Patents
Deep learning-based project declaration system and method Download PDFInfo
- Publication number
- CN112749379A CN112749379A CN202110193205.6A CN202110193205A CN112749379A CN 112749379 A CN112749379 A CN 112749379A CN 202110193205 A CN202110193205 A CN 202110193205A CN 112749379 A CN112749379 A CN 112749379A
- Authority
- CN
- China
- Prior art keywords
- module
- declaration
- information
- uploading
- auditing
- 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
Images
Classifications
-
- 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
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- 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
- G06F21/60—Protecting data
- G06F21/64—Protecting data integrity, e.g. using checksums, certificates or signatures
-
- 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
Abstract
The invention discloses a deep learning-based project declaration system and method. The image acquisition module is connected with the identity authentication module through an image acquisition module, the auditing module is respectively connected with the identity authentication module and the declaration module through a server module, and the auditing module is also connected with the feedback module; the method comprises the steps of reporting information through a reporting module, checking, integrating and uploading the reporting information to an auditing module, acquiring an auditing note and a signature image by an image acquisition module, uploading the acquired auditing note and signature image to an identity authentication module to authenticate identity, and auditing the reporting information after an expert is selected by the auditing module, wherein the result of the expert is an auditing result. According to the method and the system, the identity of the expert is verified through the information verification module, so that economic loss caused by utilization of an adversary due to loss of the account number and the password of the evaluation expert is avoided.
Description
Technical Field
The invention relates to the technical field of online project declaration, in particular to a project declaration system and method based on deep learning.
Background
With the rapid development of information technology, information management is taking an increasingly important place in people's lives. Among them, the popularity of e-government becomes an important standard for measuring an information change of a region, and the online declaration is a key element for the e-government.
Compared with the traditional (manual filling and paper declaration data submission) declaration mode, the online declaration system has the advantages of no substitution. The online declaration system can simplify project declaration processes and improve project declaration efficiency.
Although developed and practiced over the years, the functionality and performance of the online declaration system is satisfactory for normal use. However, the security of the online declaration system is still a great hidden danger. In the process of project audit, if the user name and the password of a system participant are stolen, an attacker conducts improper review on projects participating in declaration, and huge loss is brought to the society.
Disclosure of Invention
The invention provides an online project declaration system based on deep learning and a method thereof aiming at the defects of the conventional declaration system, so as to overcome the safety problem in the project declaration process at present.
In order to achieve the purpose, the invention provides the following scheme:
the invention provides an online project declaration system based on deep learning, which comprises a real-time system and a real-time system, wherein the real-time system comprises: the system comprises an image acquisition module (3), an image acquisition module (4), an identity authentication module (5), a declaration module (1), a server module (2), an auditing module (6) and a feedback module (7);
the image acquisition module (3) is used for acquiring a review picture and transmitting the picture to the image acquisition module (4);
the image acquisition module (4) is used for acquiring the pictures acquired by the image acquisition module (3), reading and processing the pictures, and uploading the processed pictures to the identity authentication module (5);
the identity authentication module (5) is used for acquiring the picture and authenticating the picture, and uploading a result to the server module (2) after the authentication is finished;
the declaration module (1) is used for collecting project declaration information, processing the collected project declaration information, finally summarizing the collected project declaration information into a project declaration book, and compressing and uploading the project declaration book to the server module (2);
the server module (2) is used for receiving the project declaration of the declaration module (1) and the authentication result of the identity authentication module (5), and uploading the project declaration to an auditing module (6);
the auditing module (6) is used for auditing the project declaration uploaded by the server side and uploading the audited data to the feedback module (7);
the feedback module (7) is used for feeding back the result after the audit to the user and providing a data basis for the later declaration process;
the image acquisition module (3) is connected with the identity authentication module (5) through the image acquisition module (4), the auditing module (6) is respectively connected with the identity authentication module (5) and the declaration module (1) through the server module (2), and the auditing module (6) is also connected with the feedback module (7).
Further, the review pictures comprise a review picture, a note picture and a signature picture of the reviewer.
Further, the image acquisition module (4) comprises: the image processing device comprises an image processing module (401), an image encryption module (402) and an image uploading module (403);
the image processing module (401) is used for processing the image uploaded by the image acquisition module (3), and acquiring processed information based on the image processing module (401), wherein the processed information comprises comment text information, note text information and signature text information;
the image encryption module (402) is used for encrypting the processed information and uploading the information to the image uploading module (403);
the image uploading module (403) is used for uploading the encrypted processed information to the identity authentication module (5).
Further, the identity authentication module (5) comprises a data extraction module (501), an information verification module (502) and a data uploading module (503);
the data extraction module (501) is used for extracting the encrypted processed information uploaded by the image uploading module (403) and uploading the processed information to the information verification module (502);
the information verification module (502) is used for comparing the signature text information in the processed information with the recorded signature as the result of expert identity identification;
the data uploading module (503) is used for uploading the identification result to the server (2).
Further, the declaration module (1) comprises: the system comprises a declaration information collection module (101), a data duplication checking module (102), a data integration module (103) and a data uploading module (104);
the declaration information collection module (101) is used for collecting project declaration information filled by project declaration personnel;
the data duplication checking module (102) is used for checking the repetition rate of the project declaration information;
the data integration module (103) is used for integrating the project declaration information and integrating the project declaration information into a project declaration book;
the data uploading module (104) is used for uploading the project declaration compression to the server module (2).
Further, the auditing module (6) comprises a director auditing module (601), an expert distributing module (602) and an expert auditing module (603);
the checking module (601) of the administrative unit is used for acquiring the data of the server module (2), performing preliminary checking on items in the acquired data, and uploading the items passing the checking to the expert distribution module (602);
the expert distribution module (602) is used for distributing according to project types and expert excellence fields;
the expert auditing module (603) is used for auditing the items audited by the director, and the result audited by the expert is used as the final result.
Further, the feedback module (7) comprises a project schedule module (701) and an information exchange module (702);
the project progress module (701) is used for recording and feeding back project development progress to users at all levels;
the communication module is used for communication among all system users.
8. A deep learning-based project declaration method comprises the following steps:
s1, collecting declaration information, checking the declaration information for duplication, judging whether novelty exists or not, if not, refuting the declaration information, otherwise, integrating the declaration information into a project declaration book, and uploading the project declaration book to a server;
s2, recording the signature of the reviewer, collecting the signature image, the comment image and the note image of the reviewer, processing the image to obtain processed information, and encrypting the processed information, wherein the processed information comprises: signature text information, comment text information and note text information;
s3, constructing a model, wherein the note text information forms a training set and a verification set, the comment text information forms a test set, the training set is trained by using a convolutional neural network, the verification set is used for verification in the training process, the test set is used for evaluating the effect, and the model is used for identity authentication after the training is finished, wherein the identity authentication comprises: identifying the signature text information by using the model, and comparing the signature text information with the recorded signature as an identity authentication result;
s4, after the authentication is successful, auditing is started, the project declaration book is obtained from the server, preliminary auditing of a supervisor unit is carried out, and after the preliminary auditing is passed, experts in related fields are distributed for auditing, wherein the auditing result of the experts is taken as a final result;
and S5, opening the audit result and the declaration progress to users at all levels, wherein the users at all levels can communicate with each other.
Further, the processing method in S2 is:
(1) extracting corresponding characteristics from the picture through texture making and Gabor conversion;
(2) and processing the Gabor conversion result to generate a text format which accords with the processing specification of the Support Vector Machine (SVM).
The invention discloses the following technical effects:
the invention can well verify the identity of the expert by using the information verification module, and reduces the possibility of economic loss caused by utilization of adversaries due to the loss of account numbers and passwords of the appraisal experts. The expert distribution module is used for reasonably distributing experts for each project so as to ensure that each project can be approved by experts in the field, and each project can be reasonably evaluated. The reporting module can make the reported and audited data more accurate, and can improve the reporting success rate. The data duplicate checking module can avoid the situation of repeated application of the same project and ensure that each newly applied project has novelty, namely the data duplicate checking module can improve the success rate of project declaration.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a schematic diagram of a deep learning based project declaration system;
the system comprises a declaration module, a declaration information collection module 101, a data duplication checking module 102, a data integration module 103, a data uploading module 104, a server module 2, an image acquisition module 3, an image acquisition module 4, an image processing module 401, an image encryption module 402, an image uploading module 403, an identity authentication module 5, a data extraction module 501, an information verification module 502, a data uploading module 503, an audit module 6, a master unit audit module 601, an expert allocation module 602, an expert audit module 603, a feedback module 7, a project progress module 701 and an information exchange module 702.
Detailed Description
Reference will now be made in detail to various exemplary embodiments of the invention, the detailed description should not be construed as limiting the invention but as a more detailed description of certain aspects, features and embodiments of the invention.
It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. Further, for numerical ranges in this disclosure, it is understood that each intervening value, between the upper and lower limit of that range, is also specifically disclosed. Every smaller range between any stated value or intervening value in a stated range and any other stated or intervening value in a stated range is encompassed within the invention. The upper and lower limits of these smaller ranges may independently be included or excluded in the range.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Although only preferred methods and materials are described herein, any methods and materials similar or equivalent to those described herein can be used in the practice or testing of the present invention. All documents mentioned in this specification are incorporated by reference herein for the purpose of disclosing and describing the methods and/or materials associated with the documents. In case of conflict with any incorporated document, the present specification will control.
It will be apparent to those skilled in the art that various modifications and variations can be made in the specific embodiments of the present disclosure without departing from the scope or spirit of the disclosure. Other embodiments will be apparent to those skilled in the art from consideration of the specification. The specification and examples are exemplary only.
As used herein, the terms "comprising," "including," "having," "containing," and the like are open-ended terms that mean including, but not limited to.
The "parts" in the present invention are all parts by mass unless otherwise specified.
The invention provides an online project declaring system based on deep learning, which comprises a declaring module 1, an identity authentication module 5, a server module 2, an image acquisition module 4, an auditing module 6, a feedback module 7 and an image acquisition module 3.
The declaration module 1 is used for collecting project declaration information filled by a project declaration member, processing the collected declaration information, finally compiling the declaration information into a PDF document, and uploading the document to the server module 2;
the server module 2 is used for receiving the data of the declaration module 1 and the data of the image acquisition module 4;
the image acquisition module 3 is used for acquiring the pictures generated in the evaluation process and transmitting the pictures to the image acquisition module 4;
the image acquisition module 4 is configured to perform reading processing on the acquired image in the image acquisition module 3, generate preliminary processing data, and upload the generated image data to the identity authentication module 5;
the identity authentication module 5 is used for acquiring the image data, authenticating the image data, and feeding back a result to the server module 2 after the authentication is finished;
the auditing module 6 is used for auditing the declaration data from the server side and uploading the audited data to the feedback module 7;
and the feedback module 7 is used for feeding back the checked result to the user. Meanwhile, a data basis is provided for the later declaration process.
The declaration module 1 comprises a declaration information collection module 101, a data duplication checking module 102, a data integration module 103 and a data uploading module 104;
the declaration information collecting module 101 is used for collecting project declaration information filled by project declaration personnel;
the data duplication checking module 102 is used for avoiding repeated application of projects, ensuring that the projects have advancement and novelty, and improving the success rate of project declaration, and the data duplication checking module 102 comprises the following steps;
and acquiring the project declaration information of the past year from the declaration database, and storing the declaration information to the server side.
And (4) crawling project declaration information of related fields on the network by using a python crawler technology, and storing the related declaration information to a server side.
And comparing the pre-declared project with the data stored in the server side to avoid repeated application of the project, ensure the accuracy and novelty of the project and improve the success rate of project declaration.
The data integration module 103 is used for integrating the project declaration information filled by the project declaration persons and integrating the project declaration information into a project declaration book;
the data uploading module 104 is used for uploading the project declaration compression to the server module 2;
further, the image obtaining module 4 includes an image processing module 401, an image encrypting module 402 and an image uploading module 403;
the image processing module 401 is configured to process the image acquired from the image acquisition module 3, so that features of the image can be better extracted;
the image encryption module 402 is used to encrypt the image.
A deep learning-based project declaration method is characterized in that: the method comprises the following steps:
s1, constructing a receipt database, collecting the project declaration information through the declaration information collection module 101 in the declaration module 1, checking the duplicate by the data checking module 102, integrating the qualified project declaration information into a project declaration book by the data integration module 103, and compressing and uploading the project declaration book to the server module 2;
s2, acquiring images through the image acquisition module 3 and uploading the images to the image acquisition module 4, wherein the image acquisition module 4 processes the images according to the acquired images and uploads the processed images to the identity authentication module 5;
s3, the identity authentication module 5 performs data extraction on the processed image through the data extraction module 501, performs information verification on the extracted information through the information verification module 502, and uploads the verification result to the server module 2;
s4, the audit module 6 obtains the project declaration from the server module 2, sends the project declaration to the audit module 601 of the administrative unit for preliminary audit, uploads the approved project to the expert allocation module 602 for allocation, and finally enters the expert audit module 603 for audit and outputs the result, where the result of the expert audit is used as the final result, and uploads the final result to the feedback module 7;
and S5, performing project progress display and information communication through the feedback module 7.
The image acquisition module 3 is also used for collecting the notes of the review experts and uploading the notes to the image acquisition module 4;
the image acquisition module 4 comprises an image processing module 401, an image encryption module 402 and an image uploading module 403;
the image processing module 401 is configured to perform relevant processing on the image acquired by the image acquisition module 3, so that features of the image can be better extracted;
the processing method comprises the following steps:
(1) extracting corresponding characteristics of the note through texture making and Gabor conversion;
(2) processing the Gabor conversion result to generate a text format which accords with the SVM processing specification;
(3) and acquiring the picture uploaded by the image processing module 401, and preprocessing the picture to a picture format suitable for handwriting recognition.
The resolution of the picture is set to 224 × 224, and the format of the picture is set to Joint Photographic Experts Group (JPEG) format;
the image uploading module 403 is configured to upload the picture in the image processing to the server module 2 after being encrypted by the image encryption module 402;
the image encryption module 402 is configured to encrypt an image, so as to prevent the image from being intercepted by an adversary in a public channel transmission process to cause information leakage, where the image encryption includes the following steps:
firstly, selecting an image encryption algorithm, wherein two common encryption algorithms are available at present:
firstly, generating 2 Logistic chaotic sequences based on a chaotic image encryption method, transforming the 2 Logistic chaotic sequences to obtain two y sequences, and performing value substitution encryption on an original image by a yl sequence and a y2 sequence, wherein a secret key is an initial state value of the chaotic system;
secondly, a method for scrambling row and column pixel points is used, and pixel information in the original image is rearranged and scrambled one by one. The original image can be restored through the one-to-one correspondence relationship, and the secret keys at the time are the mapping vectors Mchannel and Nchannel of the row-column transformation.
Step two, acquiring a secret key according to an algorithm;
and step three, decrypting according to the stored secret key.
Further, the identity authentication module 5 includes a data extraction module 501, an information verification module 502 and a data uploading module 503;
the data extraction module 501 is configured to perform data extraction on the image uploaded by the image acquisition module 4, store an expert comment portion in the extracted result in the server module 2, and upload an expert signature portion to the information verification module 502, and includes the following steps:
the data extraction flow designed for information extraction:
step one, acquiring a picture uploaded by the image processing module 401;
step two, predicting the acquired picture by using a pre-trained handwritten Chinese character model, wherein the predicting process comprises the following steps:
firstly, a system administrator collects a data set, wherein the data set comprises a training set, a verification set and a test set, the training set and the verification set are composed of notes of review experts, the proportion of the training set to the verification set is 7:3, and the test set is composed of review images of reviewers;
secondly, training the training set by using a convolutional neural network, and evaluating the effect of model training by using a verification set in the training process;
and thirdly, testing the model by using the test set, returning to the second step again if the recognition accuracy is low, and finishing the training if the recognition accuracy is high.
The information verification module 502 is configured to compare the data extracted by the data extraction module 501 with data in a database;
and the picture processing module converts the signed electronic picture image into a document, further judges the converted picture data, verifies whether the picture data is a legal user, and uploads the result data to the server end as the result of expert identity identification.
Further, the auditing module 6 includes a director auditing module 601, an expert allocating module 602 and an expert auditing module 603;
the auditing module 601 of the director is used for performing preliminary auditing on the project and uploading the project which passes the auditing to the expert distribution module 602;
the expert allocation module 602 is configured to allocate according to the project type and the expert excellence field, match the declared project type with the field of the expert in the expert database, and if the result cannot be obtained by accurate matching, match the declared project type with the large category of the expert, thereby ensuring that each project can be allocated to the expert in the related field.
The expert auditing module 603 is used for auditing the items audited by the director, and the result audited by the expert is used as the final result;
further, the feedback module 7 includes a project schedule module 701 and an information exchange module 702;
the project progress module 701 is used for recording and feeding back project development progress to users at all levels;
the information exchange module 702 is used for exchanging and communicating among the system users.
The above-described embodiments are merely illustrative of the preferred embodiments of the present invention, and do not limit the scope of the present invention, and various modifications and improvements of the technical solutions of the present invention can be made by those skilled in the art without departing from the spirit of the present invention, and the technical solutions of the present invention are within the scope of the present invention defined by the claims.
Claims (9)
1. A deep learning-based project declaration system is characterized in that: the system comprises an image acquisition module (3), an image acquisition module (4), an identity authentication module (5), a declaration module (1), a server module (2), an auditing module (6) and a feedback module (7);
the image acquisition module (3) is used for acquiring a review picture and transmitting the picture to the image acquisition module (4);
the image acquisition module (4) is used for acquiring the pictures acquired by the image acquisition module (3), reading and processing the pictures, and uploading the processed pictures to the identity authentication module (5);
the identity authentication module (5) is used for acquiring the picture and authenticating the picture, and uploading a result to the server module (2) after the authentication is finished;
the declaration module (1) is used for collecting project declaration information, processing the collected project declaration information, finally summarizing the collected project declaration information into a project declaration book, and compressing and uploading the project declaration book to the server module (2);
the server module (2) is used for receiving the project declaration of the declaration module (1) and the authentication result of the identity authentication module (5), and uploading the project declaration to an auditing module (6);
the auditing module (6) is used for auditing the project declaration uploaded by the server side and uploading the audited data to the feedback module (7);
the feedback module (7) is used for feeding back the result after the audit to the user and providing a data basis for the later declaration process;
the image acquisition module (3) is connected with the identity authentication module (5) through the image acquisition module (4), the auditing module (6) is respectively connected with the identity authentication module (5) and the declaration module (1) through the server module (2), and the auditing module (6) is also connected with the feedback module (7).
2. The deep learning-based project declaration system of claim 1, wherein: the review pictures comprise a review picture, a note picture and a signature picture of the reviewer.
3. The deep learning-based project declaration system of claim 1, wherein: the image acquisition module (4) comprises: the image processing device comprises an image processing module (401), an image encryption module (402) and an image uploading module (403);
the image processing module (401) is used for processing the image uploaded by the image acquisition module (3), and acquiring processed information based on the image processing module (401), wherein the processed information comprises comment text information, note text information and signature text information;
the image encryption module (402) is used for encrypting the processed information and uploading the information to the image uploading module (403);
the image uploading module (403) is used for uploading the encrypted processed information to the identity authentication module (5).
4. The deep learning-based project declaration system of claim 1, wherein: the identity authentication module (5) comprises a data extraction module (501), an information verification module (502) and a data uploading module (503);
the data extraction module (501) is used for extracting the encrypted processed information uploaded by the image uploading module (403) and uploading the processed information to the information verification module (502);
the information verification module (502) is used for comparing the signature text information in the processed information with the recorded signature as the result of expert identity identification;
the data uploading module (503) is used for uploading the identification result to the server (2).
5. The deep learning-based project declaration system of claim 1, wherein: the declaration module (1) comprises: the system comprises a declaration information collection module (101), a data duplication checking module (102), a data integration module (103) and a data uploading module (104);
the declaration information collection module (101) is used for collecting project declaration information filled by project declaration personnel;
the data duplication checking module (102) is used for checking the repetition rate of the project declaration information;
the data integration module (103) is used for integrating the project declaration information and integrating the project declaration information into a project declaration book;
the data uploading module (104) is used for uploading the project declaration compression to the server module (2).
6. The deep learning-based project declaration system of claim 1, wherein: the auditing module (6) comprises a director auditing module (601), an expert distributing module (602) and an expert auditing module (603);
the checking module (601) of the administrative unit is used for acquiring the data of the server module (2), performing preliminary checking on items in the acquired data, and uploading the items passing the checking to the expert distribution module (602);
the expert distribution module (602) is used for distributing according to project types and expert excellence fields;
the expert auditing module (603) is used for auditing the items audited by the director, and the result audited by the expert is used as the final result.
7. The deep learning-based project declaration system of claim 1, wherein: the feedback module (7) comprises a project progress module (701) and an information exchange module (702);
the project progress module (701) is used for recording and feeding back project development progress to users at all levels;
the communication module is used for communication among all system users.
8. A deep learning-based project declaration method is characterized in that: the method comprises the following steps:
s1, collecting declaration information, checking the declaration information for duplication, judging whether novelty exists or not, if not, refuting the declaration information, otherwise, integrating the declaration information into a project declaration book, and uploading the project declaration book to a server;
s2, recording the signature of the reviewer, collecting the signature image, the comment image and the note image of the reviewer, processing the image to obtain processed information, and encrypting the processed information, wherein the processed information comprises: signature text information, comment text information and note text information;
s3, constructing a model, wherein the note text information forms a training set and a verification set, the comment text information forms a test set, the training set is trained by using a convolutional neural network, the verification set is used for verification in the training process, the test set is used for evaluating the effect, and the model is used for identity authentication after the training is finished, wherein the identity authentication comprises: identifying the signature text information by using the model, and comparing the signature text information with the recorded signature as an identity authentication result;
s4, after the authentication is successful, auditing is started, the project declaration book is obtained from the server, preliminary auditing of a supervisor unit is carried out, and after the preliminary auditing is passed, experts in related fields are distributed for auditing, wherein the auditing result of the experts is taken as a final result;
and S5, opening the audit result and the declaration progress to users at all levels, wherein the users at all levels can communicate with each other.
9. The deep learning-based project declaration method of claim 8, wherein: the processing method in S2 is:
(1) extracting corresponding characteristics from the picture through texture making and Gabor conversion;
(2) and processing the Gabor conversion result to generate a text format which accords with the processing specification of the Support Vector Machine (SVM).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110193205.6A CN112749379A (en) | 2021-02-20 | 2021-02-20 | Deep learning-based project declaration system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110193205.6A CN112749379A (en) | 2021-02-20 | 2021-02-20 | Deep learning-based project declaration system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112749379A true CN112749379A (en) | 2021-05-04 |
Family
ID=75651414
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110193205.6A Pending CN112749379A (en) | 2021-02-20 | 2021-02-20 | Deep learning-based project declaration system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112749379A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104754058A (en) * | 2015-04-16 | 2015-07-01 | 贝才禾兑网络科技南京有限公司 | Intelligent finance and tax service platform based on SaaS platform |
| CN107610764A (en) * | 2017-07-26 | 2018-01-19 | 佛山科学技术学院 | A kind of internet medical identity authorization system and method online |
| CN108038657A (en) * | 2017-11-07 | 2018-05-15 | 广东电网有限责任公司 | A kind of method and system of the above-the-line project application approval based on wechat public platform |
| CN108388996A (en) * | 2018-03-08 | 2018-08-10 | 青岛东方深蓝信息科技股份有限公司 | A kind of scientific research service integration management system |
| CN109767376A (en) * | 2018-12-13 | 2019-05-17 | 平安科技（深圳）有限公司 | Image authentication method, device, computer equipment and storage medium |
| CN110852725A (en) * | 2019-11-19 | 2020-02-28 | 青岛思科万方经济信息咨询有限公司 | Project declaration system based on big data |
| CN112287724A (en) * | 2019-07-24 | 2021-01-29 | 邹伟 | Finger vein identity recognition system based on transfer learning and GAN network |
-
2021
- 2021-02-20 CN CN202110193205.6A patent/CN112749379A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104754058A (en) * | 2015-04-16 | 2015-07-01 | 贝才禾兑网络科技南京有限公司 | Intelligent finance and tax service platform based on SaaS platform |
| CN107610764A (en) * | 2017-07-26 | 2018-01-19 | 佛山科学技术学院 | A kind of internet medical identity authorization system and method online |
| CN108038657A (en) * | 2017-11-07 | 2018-05-15 | 广东电网有限责任公司 | A kind of method and system of the above-the-line project application approval based on wechat public platform |
| CN108388996A (en) * | 2018-03-08 | 2018-08-10 | 青岛东方深蓝信息科技股份有限公司 | A kind of scientific research service integration management system |
| CN109767376A (en) * | 2018-12-13 | 2019-05-17 | 平安科技（深圳）有限公司 | Image authentication method, device, computer equipment and storage medium |
| CN112287724A (en) * | 2019-07-24 | 2021-01-29 | 邹伟 | Finger vein identity recognition system based on transfer learning and GAN network |
| CN110852725A (en) * | 2019-11-19 | 2020-02-28 | 青岛思科万方经济信息咨询有限公司 | Project declaration system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103679436B (en) | A kind of electronic contract security system and method based on biological information identification | |
| CN101159554B (en) | Biometric authentication system, enrollment terminal, authentication terminal and authentication server | |
| US7130452B2 (en) | System and method for multi-party validation, authentication and/or authorization via biometrics | |
| CA2840171C (en) | System and method for user enrollment in a secure biometric verification system | |
| Katiyar et al. | Online voting system powered by biometric security using steganography | |
| EP1879127A1 (en) | User authentication method and system and password management system | |
| CN107209821A (en) | For the method and authentication method being digitally signed to e-file | |
| CN1281608A (en) | Cryptographic key generation using biometric data | |
| US20070031009A1 (en) | Method and system for string-based biometric authentication | |
| JPWO2003069489A1 (en) | Identification method | |
| JP2010146245A (en) | Biometric authentication system and method therefor | |
| Olaniyi et al. | Design of secure electronic voting system using fingerprint biometrics and cryto-watermarking approach | |
| WO1999012144A1 (en) | Digital signature generating server and digital signature generating method | |
| Sheng et al. | Template-free biometric-key generation by means of fuzzy genetic clustering | |
| Gandhi et al. | Study on security of online voting system using biometrics and steganography | |
| US7272245B1 (en) | Method of biometric authentication | |
| CN108733783A (en) | A kind of student status information management system based on privately owned block chain | |
| US11688194B2 (en) | Method of authentication of an identity document of an individual and optionally authentication of said individual | |
| Aeloor et al. | Securing biometric data with visual cryptography and steganography | |
| CA2854481C (en) | System and method for a financial transaction system having a secure biometric verification system | |
| WO2023036143A1 (en) | Decentralized zero-trust identity verification and authentication system and method | |
| Ameh et al. | Securing cardless automated teller machine transactions using bimodal authentication system | |
| CN112749379A (en) | Deep learning-based project declaration system and method | |
| CN113487323B (en) | Campus payment method and system based on face data recognition record carrier | |
| TIWARI et al. | Secure online voting system using visual cryptography |
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 |