CN117910008A - File decryption method, device, computer equipment and storage medium - Google Patents
File decryption method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117910008A CN117910008A CN202410021145.3A CN202410021145A CN117910008A CN 117910008 A CN117910008 A CN 117910008A CN 202410021145 A CN202410021145 A CN 202410021145A CN 117910008 A CN117910008 A CN 117910008A
- Authority
- CN
- China
- Prior art keywords
- file
- target
- decrypted
- position information
- image
- 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 46
- 238000001514 detection method Methods 0.000 claims abstract description 70
- 230000006870 function Effects 0.000 claims description 55
- 238000004590 computer program Methods 0.000 claims description 39
- 238000012545 processing Methods 0.000 claims description 11
- 125000004122 cyclic group Chemical group 0.000 claims description 10
- 230000004927 fusion Effects 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000010845 search algorithm Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 11
- 238000005070 sampling Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000001960 triggered effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance 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
- 230000003287 optical effect Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000002103 transcriptional effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Abstract
The application relates to a file decryption method, a file decryption device, computer equipment and a storage medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: detecting the file position of a scanned image of a target directory through a trained target detection model so as to acquire file position information corresponding to a file in the scanned image; performing text recognition on the image area corresponding to the file position information to obtain an alternative file name corresponding to the file position information; determining a file name to be decrypted from the candidate file names according to the file suffix names; and decrypting the file corresponding to the file name to be decrypted according to the file position information corresponding to the file name to be decrypted. By adopting the method, the file decryption efficiency can be improved.
Description
Technical Field
The present application relates to the field of artificial intelligence technology, and in particular, to a file decryption method, apparatus, computer device, storage medium, and computer program product.
Background
With the continuous development of information technology, the digitization of information has become a common way of storing and transmitting information. Digital storage is convenient and also poses a threat to the security of large amounts of important information. Encrypting files is a common means for protecting data security and information security.
In the related art, the encrypted files need to be decrypted manually through operations such as searching, positioning and decrypting, and when the number of the encrypted files is large, the decrypting operation needs to be repeated for a plurality of times, so that the decrypting efficiency of the files is low.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a file decrypting method, apparatus, computer device, computer readable storage medium, and computer program product that can improve the efficiency of file decryption.
In a first aspect, the present application provides a file decryption method, including:
detecting file positions of scanned images of the target catalogue through the trained target detection model so as to obtain file position information corresponding to files in the scanned images;
Performing text recognition on the image area corresponding to the file position information to obtain an alternative file name corresponding to the file position information;
determining the file name to be decrypted from the candidate file names according to the file suffix names;
And decrypting the file corresponding to the file name to be decrypted according to the file position information corresponding to the file name to be decrypted.
In one embodiment, the detecting the file position of the scanned image of the target directory through the trained target detection model to obtain the file position information corresponding to the file in the scanned image includes:
performing image preprocessing on the scanned image to obtain a target image;
Extracting features of the target image through the trained target detection model to obtain feature images with different scales;
generating a plurality of file prediction frames on feature graphs with different scales by taking grids as centers;
And determining a target prediction frame from the file prediction frames according to the confidence, and taking coordinate information of the target prediction frame as file position information.
In one embodiment, the trained object detection model includes a convolutional layer network and an upsampling layer network; extracting features of the target image through the trained target detection model to obtain feature images with different scales, wherein the feature images comprise:
Extracting features of the target image through a bottom-up convolution layer network to obtain a first feature pyramid;
Extracting features of the target image through a top-down upsampling layer network to obtain a second feature pyramid;
And carrying out feature fusion on the first feature pyramid and the second feature pyramid to obtain feature graphs with different scales.
In one embodiment, performing text recognition on an image area corresponding to the file location information to obtain an alternative file name corresponding to the file location information, including:
Performing character recognition on the image area through a convolutional cyclic neural network to obtain a first recognition result;
re-identifying the characters with the identification accuracy lower than the accuracy threshold in the first identification result through an optimal priority search algorithm to obtain a character identification result;
According to the character recognition result, replacing the characters at the corresponding positions in the first recognition result to obtain a second recognition result;
And processing the first identification result and the second identification result through a global optimal solution algorithm to obtain the candidate file names.
In one embodiment, decrypting the file corresponding to the file name to be decrypted according to the file location information corresponding to the file name to be decrypted includes:
Triggering a file security function entry according to the file position information to open a function window corresponding to the file security function entry;
And triggering a file decryption function in the function window, and decrypting the file corresponding to the file name to be decrypted.
In one embodiment, the target directory is obtained according to information to be decrypted, and the information to be decrypted further includes a target user identifier; before the file position detection is performed on the scanned image of the target directory through the trained target detection model, the method further comprises the following steps:
matching the target user identifier with the authority user table to obtain a matching result;
And determining the file decryption permission of the target user according to the matching result.
In a second aspect, the present application further provides a file decrypting apparatus, including:
The detection module is used for detecting the file position of the scanned image of the target directory through the trained target detection model so as to acquire file position information corresponding to the file in the scanned image;
the identification module is used for carrying out character identification on the image area corresponding to the file position information and obtaining an alternative file name corresponding to the file position information;
The classification module is used for determining the file name to be decrypted from the candidate file names according to the file suffix names;
And the decryption module is used for decrypting the file corresponding to the file name to be decrypted according to the file position information corresponding to the file name to be decrypted.
In a third aspect, the present application also provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
detecting file positions of scanned images of the target catalogue through the trained target detection model so as to obtain file position information corresponding to files in the scanned images;
Performing text recognition on the image area corresponding to the file position information to obtain an alternative file name corresponding to the file position information;
determining the file name to be decrypted from the candidate file names according to the file suffix names;
And decrypting the file corresponding to the file name to be decrypted according to the file position information corresponding to the file name to be decrypted.
In a fourth aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
detecting file positions of scanned images of the target catalogue through the trained target detection model so as to obtain file position information corresponding to files in the scanned images;
Performing text recognition on the image area corresponding to the file position information to obtain an alternative file name corresponding to the file position information;
determining the file name to be decrypted from the candidate file names according to the file suffix names;
And decrypting the file corresponding to the file name to be decrypted according to the file position information corresponding to the file name to be decrypted.
In a fifth aspect, the application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of:
detecting file positions of scanned images of the target catalogue through the trained target detection model so as to obtain file position information corresponding to files in the scanned images;
Performing text recognition on the image area corresponding to the file position information to obtain an alternative file name corresponding to the file position information;
determining the file name to be decrypted from the candidate file names according to the file suffix names;
And decrypting the file corresponding to the file name to be decrypted according to the file position information corresponding to the file name to be decrypted.
According to the file decryption method, device, computer equipment, storage medium and computer program product, firstly, the file position detection is carried out on the scanned image of the target directory through the trained target detection model so as to obtain the file position information corresponding to the file in the scanned image, thus, the file can be automatically positioned, position parameters are provided for subsequent decryption operation, further, text recognition is carried out on the image area corresponding to the file position information, the candidate file name corresponding to the file position information is obtained, the file name to be decrypted is determined from the candidate file names according to the file suffix name, thus, the file to be decrypted can be automatically obtained, finally, the file corresponding to the file name to be decrypted is decrypted according to the file position information corresponding to the file name to be decrypted, and thus, the file to be decrypted under the target directory can be automatically decrypted in batches, and the file decryption efficiency is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for those skilled in the art.
FIG. 1 is an application environment diagram of a file decryption method in one embodiment;
FIG. 2 is a flow diagram of a file decryption method in one embodiment;
FIG. 3 is a schematic diagram of a trained object detection model in one embodiment;
FIG. 4 is a flow diagram of an embodiment of obtaining an alternate filename;
FIG. 5 is a flow chart of a file decryption method according to another embodiment;
FIG. 6 is a block diagram of a file decryption device in one embodiment;
fig. 7 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
In one embodiment, as shown in fig. 1, a file decryption method is provided, where this embodiment is applied to a computer device for illustration, and it is understood that in an application environment as shown in fig. 1, the computer device may specifically be a terminal 102 or a server 104. The terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, which may be smart watches, smart bracelets, headsets, etc. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
In an exemplary embodiment, as shown in fig. 2, a file decryption method is provided, and the method is applied to the terminal 102 in fig. 1 for illustration, and includes the following steps:
S202: and detecting the file position of the scanned image of the target directory through the trained target detection model so as to acquire file position information corresponding to the file in the scanned image.
The target directory refers to a file storage directory that the target user wants to decrypt, and the number of target directories may be determined according to the decryption requirement of the target user, or may be one or more. The file location information refers to coordinate information of an area where the file name is located in the scanned image.
Optionally, in the file decryption process, the terminal first acquires the target directory input by the target user, and performs batch decryption on all the encrypted files under the target directory through subsequent operations. And then, entering the target directory according to the directory path of the target directory, and scanning all files under the target directory to obtain a scanned image. And inputting the scanned image into a trained target detection model to detect the file position so as to obtain file position information corresponding to each file in the scanned image.
S204: and carrying out character recognition on the image area corresponding to the file position information to obtain an alternative file name corresponding to the file position information.
Optionally, after acquiring the file position information corresponding to each file in the scanned image, the terminal intercepts the scanned image according to the file position information to obtain the file image corresponding to each file in the scanned image, further performs text recognition on each file image, acquires the candidate file name corresponding to each file image, and binds the file position information and the candidate file name.
S206: and determining the file name to be decrypted from the candidate file names according to the file suffix names.
The file suffix name refers to a file extension name, and can be used for identifying a file type, and an encrypted file and an unencrypted file have different file suffix names.
Optionally, after obtaining the candidate file names of the files in the scanned image, the terminal first determines the file name to be decrypted from the candidate file names through a matching algorithm according to the suffix names of the encrypted files, for example, determines the file name to be decrypted with the file suffix name dsps from the candidate file names through a KMP matching algorithm.
Further, directory information and file location information corresponding to the file name to be decrypted are stored in the encrypted file table in the form of a character string. In addition, directory information and file location information corresponding to the unencrypted file may also be stored in the unencrypted file table in the form of a string.
S208: and decrypting the file corresponding to the file name to be decrypted according to the file position information corresponding to the file name to be decrypted.
Optionally, after finishing information input of the encrypted file list, the terminal sequentially acquires directory information and file position information from the encrypted file list, and opens a corresponding original directory according to the directory information, and further, in the original directory, a mouse click operation and a keyboard typing operation in a manual decryption process are simulated on a region corresponding to the file position information, and files to be decrypted under the target directory are selected one by one for decryption.
In the file decryption method, firstly, the file position detection is performed on the scanned image of the target directory through the trained target detection model to obtain the file position information corresponding to the file in the scanned image, so that the file can be automatically positioned, position parameters are provided for subsequent decryption operation, further, text recognition is performed on the image area corresponding to the file position information, the candidate file name corresponding to the file position information is obtained, the file name to be decrypted is determined from the candidate file names according to the file suffix name, so that the file to be decrypted can be automatically obtained, and finally, the file corresponding to the file name to be decrypted is decrypted according to the file position information corresponding to the file name to be decrypted, so that the files to be decrypted under the target directory can be automatically decrypted in batches, and the file decryption efficiency is improved.
In one embodiment, performing file location detection on a scanned image of a target directory through a trained target detection model to obtain file location information corresponding to a file in the scanned image, including: performing image preprocessing on the scanned image to obtain a target image; extracting features of the target image through the trained target detection model to obtain feature images with different scales; generating a plurality of file prediction frames on feature graphs with different scales by taking grids as centers; and determining a target prediction frame from the file prediction frames according to the confidence, and taking coordinate information of the target prediction frame as file position information.
Optionally, in the process of detecting the file position, the terminal performs image preprocessing on the scanned image first, and adjusts the format and size of the scanned image to obtain the target image. And then inputting the target image into a trained convolutional neural network to perform feature extraction, and obtaining feature graphs with different scales. And generating a plurality of file prediction frames on feature graphs with different scales by taking the grid as a center, screening the file prediction frames through a non-Maximum Suppression (NMS) algorithm, reserving the file prediction frame with the highest confidence as a target prediction frame, and outputting coordinate information of the target prediction frame as file position information.
In this embodiment, by acquiring feature maps of different scales, determining the target prediction frame according to the feature maps of different scales, and taking coordinate information of the target prediction frame as file position information, accuracy of the file position information can be improved.
In one embodiment, the trained object detection model includes a convolutional layer network and an upsampling layer network; extracting features of the target image through the trained target detection model to obtain feature images with different scales, wherein the feature images comprise: extracting features of the target image through a bottom-up convolution layer network to obtain a first feature pyramid; extracting features of the target image through a top-down upsampling layer network to obtain a second feature pyramid; and carrying out feature fusion on the first feature pyramid and the second feature pyramid to obtain feature graphs with different scales.
The convolution layer network is formed by cascading a plurality of convolution layers, and the size of the output characteristic diagram is reduced from top to bottom for each convolution layer in the convolution layer network. The feature graphs in the first feature pyramid are feature graphs output by each convolution layer of the convolution layer network and are arranged according to a certain sequence.
The up-sampling layer network is formed by a plurality of up-sampling layers in a cascading way, and the size of the output characteristic diagram is sequentially increased from top to bottom for each up-sampling layer in the up-sampling layer network. The feature graphs in the second feature pyramid are the feature graphs output by each up-sampling layer of the up-sampling layer network and are arranged according to a certain sequence.
The feature fusion method includes splicing, adding, multiplying, and the like, and is not particularly limited herein.
Alternatively, since files of various different formats are typically present in a computer directory and are typically closely adjacent, the corresponding pixels of each file region in a scanned image are relatively small. Therefore, the detection of each file area belongs to typical small target detection, and the conventional target detection algorithm is mainly used for detecting targets with larger pixels, and the detection effect is not ideal in a file positioning scene. In order to solve the problem, in this embodiment, a multi-scale file detection network with a multi-layer object detector is pertinently constructed, and compared with a conventional object detection algorithm, the detection accuracy of a small object can be improved.
In an alternative implementation manner, fig. 3 is a schematic structural diagram of a trained object detection model, as shown in fig. 3, a terminal first splices object image slices with a size of 576×576×3 into feature images of 238×238×12, performs a convolution operation once through 32 convolution kernels by combining a residual network structure and an activation function in Darknet, generates feature images of 238×238×32, acquires deep space attention feature images and channel attention feature images through an attention module, and performs multi-scale feature fusion through different-scale maximum pooling modes.
And then, the fused semantic features are transferred, the feature transfer from the deep layer to the shallow layer is finished firstly, then the feature transfer from the shallow layer to the deep layer is realized, the feature fusion of each layer is realized, the up-sampling operation is mainly carried out by adopting a path from top to bottom, the shallow layer sub-features are segmented, and feature graphs with different feature scales are generated through 4 detection layers respectively. For example, the feature map generated by 1×1 convolution of the C2 layer and the feature map generated by up-sampling of the P3 layer are added to obtain a P2 feature map, the features generated by the P3 feature layer and the features generated by 3×3 convolution of the N3 layer are added to obtain N4, and so on, the detection layers of different scales of N3, N4, N5 are respectively generated, the N3, N4, N5 layers can detect targets of different scales of large size, medium size and small size, and the N6 detection layer fully utilizes the top layer information of C4 and P4, firstly down-sampling of C4 to obtain C5 and up-sampling of P4 to obtain P5, splicing of C5 and P5, and adding the down-sampled features of N5 to obtain N6, which can be used for detecting targets of smaller size.
In this embodiment, since files with various different formats are usually present in the computer directory and each file is usually adjacent and close, pixel information in the scanned image of each file area is less, which belongs to small target detection. Whereas conventional target detection algorithms are typically used for detection of larger targets, information is easily lost during detection of small targets. Therefore, the detection effect of the conventional target detection algorithm in the file positioning scene is not ideal. Therefore, the embodiment constructs the multi-scale file detection network with the multi-layer target detector for scale change enhancement, so that the detection precision of the file position can be improved.
In one embodiment, performing text recognition on an image area corresponding to the file location information to obtain an alternative file name corresponding to the file location information, including: performing character recognition on the image area through a convolutional cyclic neural network to obtain a first recognition result; re-identifying the characters with the identification accuracy lower than the accuracy threshold in the first identification result through an optimal priority search algorithm to obtain a character identification result; according to the character recognition result, replacing the characters at the corresponding positions in the first recognition result to obtain a second recognition result; and processing the first identification result and the second identification result through a global optimal solution algorithm to obtain the candidate file names.
Optionally, fig. 4 is a schematic flow chart of obtaining the candidate file name, and as shown in fig. 4, the terminal first performs page layout analysis on the preprocessed file image to obtain an accurate area of each character in the file image. And sequentially inputting character images in the file images into a convolutional cyclic neural network, extracting features of the character images through the convolutional neural network, converting the feature images extracted by the convolutional layer through a cyclic layer by utilizing a bidirectional long-short-time memory network, predicting the converted feature sequences to obtain the distribution of predicted labels, calculating the predicted labels through the transcriptional layer, and outputting the sequence with the highest score to obtain a first recognition result, so that the recognition can be performed according to the sequences formed by the characters instead of only recognizing single characters in each region.
Under the condition that the score of the first recognition result is larger than the score threshold value, directly taking the first recognition result as an alternative file name, and not carrying out subsequent recognition; and under the condition that the score of the first recognition result is not greater than the score threshold value, compensating the first recognition result, performing secondary scanning on the characters with the recognition accuracy lower than the accuracy threshold value by using an optimal priority searching method, recombining the segmented character fragments in the original image to obtain a second recognition result with higher recognition accuracy, comparing the first recognition result with the second recognition result, obtaining a recognition combination of a single character and a character sequence by adopting a global optimal solution algorithm, and taking the combination with the highest score as an alternative file name.
In this embodiment, aiming at the problems of poor long-sequence character recognition effect and high error rate of the conventional character recognition method, a compensation mechanism of a convolutional cyclic neural network algorithm is integrated in the file name recognition process, so that the recognition accuracy of the file name can be effectively improved under the condition of ensuring the recognition speed.
In one embodiment, decrypting the file corresponding to the file name to be decrypted according to the file location information corresponding to the file name to be decrypted includes: triggering a file security function entry according to the file position information to open a function window corresponding to the file security function entry; and triggering a file decryption function in the function window, and decrypting the file corresponding to the file name to be decrypted.
Optionally, in the process of decrypting the file to be decrypted, the terminal may simulate right click operation of the mouse on the area corresponding to the file position information under the original directory, and open a function selection window, and in the function selection window, simulate left click operation of the mouse to trigger a file security function entry, and open a file security function window. It should be understood that the file security function entry is only a reference name, and the actual function entry may be a name such as "file security" or "file decryption", which are not specifically limited herein.
Further, in the file security function window, a file decryption function is triggered, for example, a "restore file" function tab is clicked, and the file to be decrypted is decrypted. The operation performed in the window may calculate the corresponding operation position based on the file position information and the actual window information.
In this embodiment, the file security function entry is triggered according to the file location information to open a function window corresponding to the file security function entry, and in the function window, a file decryption function is triggered to decrypt a file corresponding to a file name to be decrypted, so that an automatic decryption process can be simulated to decrypt the file to be decrypted, thereby improving the file decryption efficiency.
In one embodiment, the target directory is obtained according to information to be decrypted, and the information to be decrypted further comprises a target user identifier; before the file position detection is performed on the scanned image of the target directory through the trained target detection model, the method further comprises the following steps: matching the target user identifier with the authority user table to obtain a matching result; and determining the file decryption permission of the target user according to the matching result.
The authority user table stores user identifiers capable of performing file decryption operation, and the user identifiers can be user names or unique identity numbers, and the like, which are not particularly limited herein.
Optionally, before starting file decryption, in order to ensure data security, the terminal first obtains a target user identifier of the target user from the information to be decrypted, and then matches the target user identifier in the user authority table. If the same user identifier is matched in the user authority list, the target user is indicated to have file decryption authority, and subsequent decryption operation can be performed; if the same user identifier is not matched in the user authority list, the user does not have the file decryption authority, does not carry out subsequent operation, and pushes prompt information which does not have the decryption authority to the target user, for example, pushes prompt information of 'do not have the file decryption authority, please contact an administrator'.
In this embodiment, before file decryption is started, the target user identifier and the authority user table are matched to obtain a matching result, and the file decryption authority of the target user is determined according to the matching result, so that data security can be improved.
In one embodiment, as shown in fig. 5, there is provided a file decrypting method, the method comprising the steps of:
and obtaining information to be decrypted, wherein the information to be decrypted comprises the target directory and the target user identification.
Matching the target user identifier with the authority user table to obtain a matching result; and determining the file decryption permission of the target user according to the matching result.
Under the condition that a target user has file decryption authority, performing image preprocessing on a scanned image to acquire a target image; extracting features of the target image through a bottom-up convolution layer network to obtain a first feature pyramid; extracting features of the target image through a top-down upsampling layer network to obtain a second feature pyramid; performing feature fusion on the first feature pyramid and the second feature pyramid to obtain feature graphs with different scales; generating a plurality of file prediction frames on feature graphs with different scales by taking grids as centers; and determining a target prediction frame from the file prediction frames according to the confidence, and taking coordinate information of the target prediction frame as file position information.
Performing character recognition on an image area corresponding to the file position information through a convolutional cyclic neural network to obtain a first recognition result; re-identifying the characters with the identification accuracy lower than the accuracy threshold in the first identification result through an optimal priority search algorithm to obtain a character identification result; according to the character recognition result, replacing the characters at the corresponding positions in the first recognition result to obtain a second recognition result; and processing the first identification result and the second identification result through a global optimal solution algorithm to obtain the candidate file names.
And determining the file name to be decrypted from the candidate file names according to the file suffix names.
Triggering a file security function entry according to the file position information to open a function window corresponding to the file security function entry; and triggering a file decryption function in the function window, and decrypting the file corresponding to the file name to be decrypted.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a file decryption device for realizing the above related file decryption method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the file decrypting device provided in the following may be referred to the limitation of the file decrypting method hereinabove, and will not be repeated here.
In an exemplary embodiment, as shown in fig. 6, there is provided a file decrypting apparatus including: a detection module 610, an identification module 620, a classification module 630, and a decryption module 640, wherein:
the detection module 610 is configured to perform file position detection on a scanned image of the target directory through a trained target detection model, so as to obtain file position information corresponding to a file in the scanned image;
the recognition module 620 is configured to perform text recognition on an image area corresponding to the file location information, and obtain an alternative file name corresponding to the file location information;
The classification module 630 is configured to determine a file name to be decrypted from the candidate file names according to the file suffix names;
And the decryption module 640 is configured to decrypt the file corresponding to the file name to be decrypted according to the file location information corresponding to the file name to be decrypted.
In one embodiment, the detection module 610 is further configured to perform image preprocessing on the scanned image to obtain a target image; extracting features of the target image through the trained target detection model to obtain feature images with different scales; generating a plurality of file prediction frames on feature graphs with different scales by taking grids as centers; and determining a target prediction frame from the file prediction frames according to the confidence, and taking coordinate information of the target prediction frame as file position information.
In one embodiment, the detection module 610 is further configured to perform feature extraction on the target image through a bottom-up convolutional layer network, to obtain a first feature pyramid; extracting features of the target image through a top-down upsampling layer network to obtain a second feature pyramid; and carrying out feature fusion on the first feature pyramid and the second feature pyramid to obtain feature graphs with different scales.
In one embodiment, the recognition module 620 is further configured to perform text recognition on the image area through a convolutional neural network, to obtain a first recognition result; re-identifying the characters with the identification accuracy lower than the accuracy threshold in the first identification result through an optimal priority search algorithm to obtain a character identification result; according to the character recognition result, replacing the characters at the corresponding positions in the first recognition result to obtain a second recognition result; and processing the first identification result and the second identification result through a global optimal solution algorithm to obtain the candidate file names.
In one embodiment, the decryption module 640 is further configured to trigger a file security function entry according to the file location information, so as to open a function window corresponding to the file security function entry; and triggering a file decryption function in the function window, and decrypting the file corresponding to the file name to be decrypted.
In one embodiment, the detection module 610 is further configured to match the target user identifier with the permission user table, and obtain a matching result; and determining the file decryption permission of the target user according to the matching result.
The respective modules in the above-described file decrypting apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one exemplary embodiment, a computer device is provided, which may be a terminal, and an internal structure diagram thereof may be as shown in fig. 7. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a file decryption method. The display unit of the computer device is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in FIG. 7 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one exemplary embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of: detecting file positions of scanned images of the target catalogue through the trained target detection model so as to obtain file position information corresponding to files in the scanned images; performing text recognition on the image area corresponding to the file position information to obtain an alternative file name corresponding to the file position information; determining the file name to be decrypted from the candidate file names according to the file suffix names; and decrypting the file corresponding to the file name to be decrypted according to the file position information corresponding to the file name to be decrypted.
In one embodiment, the processor when executing the computer program further performs the steps of: performing image preprocessing on the scanned image to obtain a target image; extracting features of the target image through the trained target detection model to obtain feature images with different scales; generating a plurality of file prediction frames on feature graphs with different scales by taking grids as centers; and determining a target prediction frame from the file prediction frames according to the confidence, and taking coordinate information of the target prediction frame as file position information.
In one embodiment, the processor when executing the computer program further performs the steps of: extracting features of the target image through a bottom-up convolution layer network to obtain a first feature pyramid; extracting features of the target image through a top-down upsampling layer network to obtain a second feature pyramid; and carrying out feature fusion on the first feature pyramid and the second feature pyramid to obtain feature graphs with different scales.
In one embodiment, the processor when executing the computer program further performs the steps of: performing character recognition on the image area through a convolutional cyclic neural network to obtain a first recognition result; re-identifying the characters with the identification accuracy lower than the accuracy threshold in the first identification result through an optimal priority search algorithm to obtain a character identification result; according to the character recognition result, replacing the characters at the corresponding positions in the first recognition result to obtain a second recognition result; and processing the first identification result and the second identification result through a global optimal solution algorithm to obtain the candidate file names.
In one embodiment, the processor when executing the computer program further performs the steps of: triggering a file security function entry according to the file position information to open a function window corresponding to the file security function entry; and triggering a file decryption function in the function window, and decrypting the file corresponding to the file name to be decrypted.
In one embodiment, the processor when executing the computer program further performs the steps of: matching the target user identifier with the authority user table to obtain a matching result; and determining the file decryption permission of the target user according to the matching result.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of: detecting file positions of scanned images of the target catalogue through the trained target detection model so as to obtain file position information corresponding to files in the scanned images; performing text recognition on the image area corresponding to the file position information to obtain an alternative file name corresponding to the file position information; determining the file name to be decrypted from the candidate file names according to the file suffix names; and decrypting the file corresponding to the file name to be decrypted according to the file position information corresponding to the file name to be decrypted.
In one embodiment, the computer program when executed by the processor further performs the steps of: performing image preprocessing on the scanned image to obtain a target image; extracting features of the target image through the trained target detection model to obtain feature images with different scales; generating a plurality of file prediction frames on feature graphs with different scales by taking grids as centers; and determining a target prediction frame from the file prediction frames according to the confidence, and taking coordinate information of the target prediction frame as file position information.
In one embodiment, the computer program when executed by the processor further performs the steps of: extracting features of the target image through a bottom-up convolution layer network to obtain a first feature pyramid; extracting features of the target image through a top-down upsampling layer network to obtain a second feature pyramid; and carrying out feature fusion on the first feature pyramid and the second feature pyramid to obtain feature graphs with different scales.
In one embodiment, the computer program when executed by the processor further performs the steps of: performing character recognition on the image area through a convolutional cyclic neural network to obtain a first recognition result; re-identifying the characters with the identification accuracy lower than the accuracy threshold in the first identification result through an optimal priority search algorithm to obtain a character identification result; according to the character recognition result, replacing the characters at the corresponding positions in the first recognition result to obtain a second recognition result; and processing the first identification result and the second identification result through a global optimal solution algorithm to obtain the candidate file names.
In one embodiment, the computer program when executed by the processor further performs the steps of: triggering a file security function entry according to the file position information to open a function window corresponding to the file security function entry; and triggering a file decryption function in the function window, and decrypting the file corresponding to the file name to be decrypted.
In one embodiment, the computer program when executed by the processor further performs the steps of: matching the target user identifier with the authority user table to obtain a matching result; and determining the file decryption permission of the target user according to the matching result.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of: detecting file positions of scanned images of the target catalogue through the trained target detection model so as to obtain file position information corresponding to files in the scanned images; performing text recognition on the image area corresponding to the file position information to obtain an alternative file name corresponding to the file position information; determining the file name to be decrypted from the candidate file names according to the file suffix names; and decrypting the file corresponding to the file name to be decrypted according to the file position information corresponding to the file name to be decrypted.
In one embodiment, the computer program when executed by the processor further performs the steps of: performing image preprocessing on the scanned image to obtain a target image; extracting features of the target image through the trained target detection model to obtain feature images with different scales; generating a plurality of file prediction frames on feature graphs with different scales by taking grids as centers; and determining a target prediction frame from the file prediction frames according to the confidence, and taking coordinate information of the target prediction frame as file position information.
In one embodiment, the computer program when executed by the processor further performs the steps of: extracting features of the target image through a bottom-up convolution layer network to obtain a first feature pyramid; extracting features of the target image through a top-down upsampling layer network to obtain a second feature pyramid; and carrying out feature fusion on the first feature pyramid and the second feature pyramid to obtain feature graphs with different scales.
In one embodiment, the computer program when executed by the processor further performs the steps of: performing character recognition on the image area through a convolutional cyclic neural network to obtain a first recognition result; re-identifying the characters with the identification accuracy lower than the accuracy threshold in the first identification result through an optimal priority search algorithm to obtain a character identification result; according to the character recognition result, replacing the characters at the corresponding positions in the first recognition result to obtain a second recognition result; and processing the first identification result and the second identification result through a global optimal solution algorithm to obtain the candidate file names.
In one embodiment, the computer program when executed by the processor further performs the steps of: triggering a file security function entry according to the file position information to open a function window corresponding to the file security function entry; and triggering a file decryption function in the function window, and decrypting the file corresponding to the file name to be decrypted.
In one embodiment, the computer program when executed by the processor further performs the steps of: matching the target user identifier with the authority user table to obtain a matching result; and determining the file decryption permission of the target user according to the matching result.
It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are both information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to meet the related regulations.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high density embedded nonvolatile memory, resistive random access memory (ReRAM), magneto-resistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (PHASE CHANGE memory, PCM), graphene memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in various forms such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (10)
1. A method of decrypting a file, the method comprising:
detecting the file position of a scanned image of a target directory through a trained target detection model so as to acquire file position information corresponding to a file in the scanned image;
Performing text recognition on the image area corresponding to the file position information to obtain an alternative file name corresponding to the file position information;
determining a file name to be decrypted from the candidate file names according to the file suffix names;
And decrypting the file corresponding to the file name to be decrypted according to the file position information corresponding to the file name to be decrypted.
2. The method according to claim 1, wherein the performing file location detection on the scanned image of the target directory by the trained target detection model to obtain file location information corresponding to a file in the scanned image includes:
Performing image preprocessing on the scanned image to obtain a target image;
extracting features of the target image through the trained target detection model to obtain feature images with different scales;
generating a plurality of file prediction frames on the feature graphs with different scales by taking the grids as centers;
and determining a target prediction frame from the file prediction frames according to the confidence, and taking the coordinate information of the target prediction frame as the file position information.
3. The method of claim 2, wherein the trained object detection model comprises a convolutional layer network and an upsampling layer network; the feature extraction is performed on the target image through the trained target detection model, and feature graphs with different scales are obtained, including:
extracting features of the target image through a bottom-up convolution layer network to obtain a first feature pyramid;
extracting features of the target image through a top-down upsampling layer network to obtain a second feature pyramid;
And carrying out feature fusion on the first feature pyramid and the second feature pyramid to obtain feature graphs with different scales.
4. The method of claim 1, wherein the performing text recognition on the image area corresponding to the file location information to obtain the candidate file name corresponding to the file location information includes:
Performing character recognition on the image area through a convolutional cyclic neural network to obtain a first recognition result;
re-identifying the characters with the identification accuracy lower than the accuracy threshold in the first identification result through an optimal priority search algorithm to obtain a character identification result;
According to the character recognition result, replacing the character at the corresponding position in the first recognition result to obtain a second recognition result;
And processing the first identification result and the second identification result through a global optimal solution algorithm to obtain the candidate file names.
5. The method according to claim 1, wherein decrypting the file corresponding to the file name to be decrypted according to the file location information corresponding to the file name to be decrypted includes:
Triggering a file security function entry according to the file position information so as to open a function window corresponding to the file security function entry;
And triggering a file decryption function in the function window, and decrypting the file corresponding to the file name to be decrypted.
6. The method of claim 1, wherein the target directory is obtained from information to be decrypted, the information to be decrypted further comprising a target user identification; before the file position detection is performed on the scanned image of the target directory through the trained target detection model, the method further comprises:
Matching the target user identifier with the authority user table to obtain a matching result;
And determining the file decryption permission of the target user according to the matching result.
7. A document decryption apparatus, the apparatus comprising:
the detection module is used for detecting the file position of the scanned image of the target directory through the trained target detection model so as to acquire file position information corresponding to the file in the scanned image;
The identification module is used for carrying out character identification on the image area corresponding to the file position information and obtaining an alternative file name corresponding to the file position information;
The classification module is used for determining the file name to be decrypted from the candidate file names according to the file suffix names;
And the decryption module is used for decrypting the file corresponding to the file name to be decrypted according to the file position information corresponding to the file name to be decrypted.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410021145.3A CN117910008A (en) | 2024-01-08 | 2024-01-08 | File decryption method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410021145.3A CN117910008A (en) | 2024-01-08 | 2024-01-08 | File decryption method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117910008A true CN117910008A (en) | 2024-04-19 |
Family
ID=90694577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410021145.3A Pending CN117910008A (en) | 2024-01-08 | 2024-01-08 | File decryption method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117910008A (en) |
-
2024
- 2024-01-08 CN CN202410021145.3A patent/CN117910008A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11709823B2 (en) | Real time visual validation of digital content using a distributed ledger | |
| Xia et al. | EPCBIR: An efficient and privacy-preserving content-based image retrieval scheme in cloud computing | |
| WO2016077834A1 (en) | Systems and methods of building and using an image catalog | |
| US10154041B2 (en) | Website access control | |
| JP2019520662A (en) | Content-based search and retrieval of trademark images | |
| US11500992B2 (en) | Trusted execution environment-based model training methods and apparatuses | |
| US20180307399A1 (en) | Dynamic Thumbnails | |
| CN112163428A (en) | Semantic tag acquisition method and device, node equipment and storage medium | |
| US10504289B2 (en) | Method and apparatus for securely displaying private information using an augmented reality headset | |
| US9785724B2 (en) | Secondary queue for index process | |
| CN117275138A (en) | Identity authentication method, device, equipment and storage medium based on automatic teller machine | |
| CN105354506B (en) | The method and apparatus of hidden file | |
| US20230222762A1 (en) | Adversarially robust visual fingerprinting and image provenance models | |
| CN115731442A (en) | Image processing method, image processing device, computer equipment and storage medium | |
| CN117910008A (en) | File decryption method, device, computer equipment and storage medium | |
| KR20150135059A (en) | Method for Searching and Device Thereof | |
| US11574456B2 (en) | Processing irregularly arranged characters | |
| CN114282019A (en) | Target multimedia data searching method and device, computer equipment and storage medium | |
| Bhardwaj et al. | An efficient comparison of two indexing-based deep learning models for the formation of a web-application based IoT-cloud network | |
| US11315297B2 (en) | Electronic key photo album, program for creating electronic key photo album, and method for creating electronic key photo album | |
| US20230386054A1 (en) | Identifying and localizing editorial changes to images utilizing deep learning | |
| US20240073478A1 (en) | Determining video provenance utilizing deep learning | |
| US20240029262A1 (en) | System and method for storage management of images | |
| WO2024088291A1 (en) | Form filling method and apparatus, electronic device, and medium | |
| CN117238017A (en) | Face recognition method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication |