CN115391751A - Infringement determination method - Google Patents
Infringement determination method Download PDFInfo
- Publication number
- CN115391751A CN115391751A CN202211341213.1A CN202211341213A CN115391751A CN 115391751 A CN115391751 A CN 115391751A CN 202211341213 A CN202211341213 A CN 202211341213A CN 115391751 A CN115391751 A CN 115391751A
- Authority
- CN
- China
- Prior art keywords
- data
- file data
- original
- value
- target file
- 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 76
- 238000013475 authorization Methods 0.000 claims abstract description 41
- 238000005516 engineering process Methods 0.000 claims abstract description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 38
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000006243 chemical reaction Methods 0.000 claims description 16
- 239000012634 fragment Substances 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 description 12
- 241000282414 Homo sapiens Species 0.000 description 8
- 238000004590 computer program Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000013256 coordination polymer Substances 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000037303 wrinkles Effects 0.000 description 1
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
- G06F21/10—Protecting distributed programs or content, e.g. vending or licensing of copyrighted material ; Digital rights management [DRM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Technology Law (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Image Analysis (AREA)
Abstract
According to the infringement judgment method provided by the embodiment of the application, the characteristic value of original file data and authorization chain information are subjected to uplink registration by adopting a block chain technology to generate uplink registration information, the characteristic value of target file data to be judged is finally compared with the characteristic value of uplink registration, and whether the target file data is infringement data is determined according to the comparison result. The block chain technology has the characteristics of being unforgeable, untrustable and traceable, so that the accuracy of the characteristic value after uplink registration is ensured, the accuracy is higher when whether the target file data is infringing data or not is judged through the characteristic value finally, the uplink registration information comprises the characteristic value and authorization chain information, and the uplink of the authorization chain information provides a trusted certificate for copyright tracing of the original file. The original file data can comprise movie file data and IP derivative file data, so that copyright protection of the movie and the IP derivative can be realized.
Description
Technical Field
The application relates to the technical field of computers, in particular to an infringement judgment method.
Background
Copyright is the legal property of the right to copy computer programs, literary works, musical works, photographs, games, movies, etc., which can be used to express the rights the creator enjoys with their literary, artistic works. Copyright generally belongs to the author of the creation, and stealing copyright constitutes the act of infringement.
The IP derivatives refer to works such as movies, literature, novels, cartoons and the like which are rearranged by original works, and a series of articles for daily use, stationery, clothes which can be sold according to images, scenes and props in the works, even products or services which are closely related to our life, such as theme parks, theme catering and the like.
At present, when copyright of film and television or IP derivatives is protected, for example, the copyright of film and television needs to be judged whether infringement exists manually, and when the copyright of film and television is judged whether infringement exists manually, the related technology of the interactive network television and corresponding legal knowledge need to be fully known manually, so that whether infringement exists can be judged correctly.
However, the method for judging infringement has the problem of low accuracy.
Disclosure of Invention
The invention provides an infringement judgment method which is used for improving the accuracy of infringement judgment. Specifically, the embodiment of the application discloses the following technical scheme:
in a first aspect, an embodiment of the present application provides an infringement determination method, including: acquiring a characteristic value of original file data;
performing uplink registration on the characteristic value by adopting a block chain technology to generate uplink registration information corresponding to the original file data; the ul registration information includes a characteristic value of the ul registration;
and comparing the characteristic value of the target file data to be determined with the characteristic value of the uplink registration, and determining whether the target file data is infringement data according to the comparison result.
With reference to the first aspect, in a possible implementation manner of the first aspect, before comparing the characteristic value of the target file data to be determined with the characteristic value of the uplink registration, and determining whether the target file data is infringing data according to a comparison result, the method further includes:
obtaining authorization chain information of target file data to be judged;
performing uplink registration on the authorization chain information by adopting a block chain technology to generate uplink registration information corresponding to the target file data; the uplink registration information includes grant chain information for uplink registration;
comparing the authorization chain information of the target file data with reference authorization chain information of original file data prestored in a database;
determining whether the target file data is infringement data according to the comparison result, wherein the step of:
if the authorization chain information of the target file data is consistent with the reference authorization chain information, comparing the characteristic value of the target file data to be judged with the characteristic value of the uplink registration, and determining whether the target file data is infringing data according to the comparison result.
With reference to the first aspect, in a possible implementation manner of the first aspect, based on content division of original file data, the original file data includes: copyrighted-file data and derivative data of the copyrighted-file data;
the original file data is divided based on the type of the original file data, and the original file data comprises at least one of original video data, original image data and original audio data.
With reference to the first aspect, in a possible implementation manner of the first aspect, the obtaining a feature value of original file data includes:
if the original file data comprises original video data, acquiring an image group corresponding to at least one video clip in the original video data, and respectively calculating the hash value of each frame of original image in the image group by adopting a hash algorithm, wherein the characteristic value of the original video data comprises the hash value of each frame of original image;
if the original file data comprises original image data, calculating a hash value of the original image data by adopting a hash algorithm, wherein the characteristic value of the original image data comprises the hash value of each original image data;
if the original file data comprises original audio data, at least one audio fragment in the original audio data is obtained, a hash algorithm is adopted to calculate the hash value of the original audio fragment, and the characteristic value of the original audio data comprises the hash of each original audio fragment.
With reference to the first aspect, in a possible implementation manner of the first aspect, calculating a hash value of an original image by using a hash algorithm for each frame of the original image in the image group to obtain a feature value of the original video data includes:
aiming at each frame of original image in the image group, carrying out gray level conversion on the original image to generate a gray level image group;
and calculating the hash value of the gray image by adopting a hash algorithm aiming at each frame of gray image in the gray image group to obtain the characteristic value of the original video data.
With reference to the first aspect, in a possible implementation manner of the first aspect, the method further includes:
inputting original file data into a preset multi-mode recognition model for calculation to generate first multi-mode information corresponding to the original file data, and inputting target file data to be judged into the preset multi-mode recognition model for calculation to generate second multi-mode information corresponding to the target file data; the preset multi-modal recognition model is obtained by training based on a character multi-modal feature data set, and the character multi-modal feature data set comprises at least one of face feature data, head feature data, body feature data and sound feature data;
calculating the similarity between the first multi-modal information and the second multi-modal information;
acquiring a characteristic value of original file data, wherein the characteristic value comprises the following steps:
and if the similarity is greater than a preset similarity threshold, acquiring a characteristic value of the original file data.
With reference to the first aspect, in a possible implementation manner of the first aspect, performing grayscale conversion on an original image for each frame of the original image in an image group to generate a grayscale image group includes:
aiming at each frame of original image in the image group, adjusting the image resolution of the original image to a preset resolution, and generating an adjusted image group;
and performing gray level conversion on the adjusted image group to generate a gray level image group.
With reference to the first aspect, in a possible implementation manner of the first aspect, the comparing a characteristic value of target file data to be determined with a characteristic value of uplink registration, and determining whether the target file data is infringing data according to a comparison result includes:
sequentially calculating the distance value between the characteristic value of the target file data and each characteristic value in the characteristic values of the uplink registration;
based on the distance value, it is determined whether the target file data is infringing data.
With reference to the first aspect, in a possible implementation manner of the first aspect, determining whether the target file data is infringement data based on the distance value includes:
and if the distance value is smaller than the preset distance threshold value, determining at least part of data in the target file data as infringing data.
With reference to the first aspect, in a possible implementation manner of the first aspect, determining whether the target file data is infringing data based on the distance value further includes:
acquiring the times that the distance value is smaller than a preset distance threshold value, and acquiring the number of characteristic values of original file data;
and if the times that the distance value is smaller than the preset distance threshold value are equal to the number of the characteristic values of the original file data, determining all data of the target file data as infringement data.
In a second aspect, an embodiment of the present application further provides an infringement determination device, where the device includes:
the acquisition module is used for acquiring the characteristic value of the original file data;
a generating module, configured to perform uplink registration on the feature value by using a block chain technique, and generate uplink registration information corresponding to the original file data; the uplink registration information comprises a characteristic value of uplink registration;
and the determining module is used for comparing the characteristic value of the target file data to be determined with the characteristic value of the uplink registration and determining whether the target file data is infringing data according to a comparison result.
In a third aspect, an embodiment of the present application provides an electronic device, including: a processor and a memory, the memory for storing computer executable instructions; and a processor configured to read instructions from the memory and execute the instructions to implement the method of any implementation manner of the first aspect and the first aspect.
In a fourth aspect, the present application also provides a computer-readable storage medium storing computer instructions for causing a computer to execute the method in any implementation manner of the foregoing first aspect and first aspect.
In addition, the present application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium, where the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes the method in any implementation manner of the foregoing first aspect.
The method for determining infringement provided by the embodiment of the application comprises the steps of obtaining a characteristic value of original file data, performing uplink registration on the characteristic value by adopting a block chain technology, generating uplink registration information corresponding to the original file data, comparing the characteristic value of target file data to be determined with the characteristic value of the uplink registration, and determining whether the target file data is infringement data according to a comparison result, wherein the uplink registration information comprises the characteristic value of the uplink registration. The block chain technology has the characteristics of being incapable of being forged, falsified and traced, so that after the characteristic value is subjected to uplink registration, the accuracy of the characteristic value is ensured, and the accuracy is higher when whether the target file data is infringement data or not is judged through the characteristic value finally.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used 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 based on these drawings without creative efforts.
Fig. 1 is a flowchart of an infringement determination method according to an embodiment of the present application;
fig. 2 is a flowchart of generating feature values of original video data according to an embodiment of the present disclosure;
fig. 3 is a flowchart of generating a gray-scale image group according to an embodiment of the present application;
FIG. 4 is a flow chart of determining infringement data according to an embodiment of the present disclosure;
fig. 5 is a flowchart of acquiring a feature value of original file data according to an embodiment of the present application;
fig. 6 is an overall flowchart of an infringement determination method according to an embodiment of the present application;
fig. 7 is an overall flowchart of another infringement determination method provided by the embodiment of the present application;
fig. 8 is a schematic structural diagram of an infringement determination apparatus according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions in the embodiments of the present application better understood and make the above objects, features and advantages of the embodiments of the present application more comprehensible, the technical solutions in the embodiments of the present application are described in further detail below with reference to the accompanying drawings.
At present, various copyright transactions lack a public and transparent supervision mechanism, and infringement litigation events are more and more, the aimed program broadcasting modes are also spread to the review of the television channels from on-demand types, and become main complained types gradually, and the latest condition is that the live broadcast transmission of the television channels is also infringed on the network information transmission right. In the prior art, when infringement judgment is carried out, whether infringement exists needs to be judged manually, and when the infringement exists is judged manually, the related technologies of the interactive network television and corresponding legal knowledge need to be fully known manually, so that whether infringement exists can be judged correctly. However, when some copyright litigation cases are processed, new media units of all provinces and broadspectrum and television do not know related laws and litigation in place, the adopted coping strategies and measures are unreasonable, and the selected personnel participating in litigation are not professional enough for related technologies and laws of the interactive network television, so that the accuracy and efficiency of infringement judgment are low.
In addition, the authorization chain refers to an authorization relationship that can be traced back to the copyright owner as a source. At present, a large number of authorization chains exist, and the authenticity of the authorization chains is difficult to distinguish. Content providers (CP for short) of each platform side are numerous and complicated, authorization chains are complex and different in length, authorization areas and authorization subdivisions (sub-operators, sub-large screens, sub-resolutions, sub-public and private networks) are involved, and the like, and the authorization part is complex and difficult to identify true and false, so that the problems of copyright infringement and many complaints are frequent.
Currently, non-homogeneous Rights (NFR) is a new digital transaction mode and path proposed to solve the domestic technical and legal problems of multi-domain digital transactions represented by artworks, and can be applied to film and television digital collections, IP derivatives (film peripheral offices) and the like.
In view of this, an embodiment of the present application provides an infringement determination method, which includes obtaining a feature value of original file data, performing uplink registration on the feature value by using a block chain technique, generating uplink registration information corresponding to the original file data, where the uplink registration information includes a feature value of the uplink registration, finally comparing the feature value of target file data to be determined with the feature value of the uplink registration, and determining whether the target file data is infringement data according to a comparison result. The block chain technology has the characteristics of being incapable of being forged, falsified and traced, so that after the characteristic value is subjected to uplink registration, the accuracy of the characteristic value is ensured, and the accuracy is higher when whether the target file data is infringement data or not is judged through the characteristic value finally.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings. Fig. 1 is a flowchart of an infringement determination method provided in an embodiment of the present application, where the method includes the following steps:
and 102, acquiring a characteristic value of original file data.
The original file data is copyrighted data, and the original file data may include copyrighted file data and derivative data of the copyrighted file data based on content division of the original file data. The original file data may include at least one of original video data, original image data, and original audio data based on the type division of the original file data. The derivative data of the copyrighted file data may be derivative data such as a classic frame digital collection, a derivative doll based on a movie character, and the like.
The characteristic value of the original file data is equivalent to the fingerprint information of the original file data, and when the characteristic value of the original file data is obtained, the abstract algorithm can be adopted to calculate the original file data, so that the corresponding characteristic value is generated. The digest algorithm is also called hash algorithm or hash algorithm, and is capable of mapping binary data information of any length into a short binary value of fixed length, i.e. a hash value, and different plain texts are difficult to map into the same hash value. The same data can obtain the same digest through the same hash calculation, so that a data receiver can verify the integrity of the original data through the same hash calculation. The digest Algorithm may use a Message-digest Algorithm (MD 5), a key-dependent Hash Authentication Code (HMAC), a Secure Hash Algorithm (SHA), and a secret SM3 Algorithm, but other types of digest algorithms may also be used, which is not limited in this embodiment.
In the actual calculation process, for example, an img _ hash module in a conttrib Library of an Open Source Computer Vision Library (OpenCV for short) of a cross-platform may also be directly called, so that a hash value of the original file data is directly calculated and obtained as a feature value.
In some embodiments, if the original file data includes original image data, a hash value of the original image data is calculated using a hash algorithm, and the feature value of the original image data includes the hash value of each original image data. If the original file data comprises original audio data, at least one audio segment in the original audio data is obtained, a hash algorithm is adopted to calculate the hash value of the original audio segment, and the characteristic value of the original audio data comprises the hash value of each original audio segment.
In other embodiments, if the original file data includes original video data, an image group corresponding to at least one video clip in the original video data is obtained, and a hash value of each frame of original image in the image group is calculated respectively by using a hash algorithm, and the feature value of the original video data includes the hash value of each frame of original image.
In the Motion Picture Experts Group (MPEG) video coding standard, a Group of pictures (GOP) is a Group of continuous images in a video coded by MPEG, each video coded by MPEG is composed of a plurality of continuous image sets, and the length of an image set is the number of frames between one I frame and the next I frame.
Optionally, an ffmpeg tool may be used to extract an image group corresponding to at least one video segment in the original video data, so that a hash algorithm may be directly used to calculate a hash value of each frame of original image in the image group; the hash value of each frame of original image in the image group may also be calculated by using a hash algorithm after each frame of original image in the image group is preprocessed, which is not specifically limited in this embodiment of the present application.
In some optional embodiments, as shown in fig. 2, fig. 2 is a flowchart of an infringement determination method provided in the embodiment of the present application, and specifically relates to a possible process of generating a feature value of original video data, where the method includes the following steps:
And 204, calculating the hash value of the gray image by adopting a hash algorithm aiming at each frame of gray image in the gray image group to obtain the characteristic value of the original video data.
The original image of each frame in the image group is a color image, and the gray level of the original image can be converted based on a color space conversion function to generate a gray level image group. Illustratively, the color space conversion function may be based on the color space conversion function CvtColor in Opencv. By performing gray scale conversion on the original image, picture processing can be performed on the original video, for example, color saturation, contrast and the like are adjusted, and further, the effectiveness of the feature value obtained by subsequent calculation can be ensured.
Optionally, when generating the grayscale image group, as shown in fig. 3, fig. 3 is a flowchart of an infringement determination method provided in an embodiment of the application, and specifically relates to a possible process for generating the grayscale image group, where the method includes the following steps:
And 304, performing gray level conversion on the adjusted image group to generate a gray level image group.
The image resolution of the original image may be adjusted to a preset resolution by using a downsampling algorithm, where the preset resolution may be 1080p. In the process of reducing the image by performing downsampling processing on the original image, for a local area of the original image, the value of a certain pixel point in the area can be used for representing the scaled pixel value of the local area, and the value obtained by weighting and averaging the pixel points in the local area can also be used for representing the scaled value.
In addition, in order to avoid the wrinkle phenomenon when the image is reduced, the original image can be processed by adopting a region interpolation algorithm. The area interpolation algorithm is a simple area weighted average, which is equivalent to filtering and then down-sampling the area. Further, the adjusted image group may be subjected to gradation conversion to generate a gradation image group.
And 104, performing uplink registration on the characteristic value by adopting a block chain technology to generate uplink registration information corresponding to the original file data.
Wherein the uplink registration information includes a characteristic value of the uplink registration and grant chain information. The block chain technology is adopted, namely the hash value of the previous block containing the timestamp information is placed into the next block to form a block chain which is connected in series according to the time sequence, and the summary algorithm technology ensures that the integrity of the block chain ledger is not damaged. A blockchain is defined as a distributed book consisting of digitally recorded data arranged in a chain of successively increasing blocks, each block being cryptographically connected and secured against tampering and revision.
When the characteristic value and the authorization chain information are subjected to uplink registration by adopting a block chain technology to generate uplink registration information corresponding to original file data, a client can be added into an application channel in a fabric block chain network after acquiring a legal identity certificate from a certificate node, wherein the channel is mainly used for realizing service isolation in the block chain network, each channel represents a service, corresponds to a set of account book, and calls a software development kit fabric SDK provided by a block chain official to send a proposal of characteristic value registration to an endorsement node appointed in a configuration file.
The endorsement node (also called a bookkeeping node) is responsible for storing complete book data, namely block chain data, and is also responsible for completing endorsement processing of a registration proposal, checking whether the book is legal or not, calling an intelligent contract to simulate running registration and endorse state change caused by registration if the book is legal, and returning a result to the client. The business process of the intelligent contract comprises the following steps: and generating corresponding authorization chain copyright certificates of the ultra high definition films and checking basic information of the authorization chain copyright certificates according to the authorization chain information of the ultra high definition films.
After checking the received proposal response and checking the agreement, the client initiates registration, submits the registration to the endorsement node, and the endorsement node forwards the registration to the sequencing node.
The sorting node generally does not need to directly deal with the ledger and the transaction content, and is only responsible for performing global sorting (according to a Byzantine Fault-Tolerant algorithm (PBFT for short) consensus algorithm or a Kafka consensus algorithm) for all legal transactions in the network so as to ensure data consistency on each node, and generating a block structure by combining a batch of sorted registrations and sending the block structure to the ledger node.
The accounting node periodically acquires the sorted batch registration block structure from the sorting node, and performs final check before posting on the registrations. Wherein the registration structural integrity, signatures, duplicates can be checked; verifying whether the transaction conforms to an endorsement policy; and checking whether the version in the read set is consistent with the book.
And after the check is passed, legal registration is executed to write the characteristic value of the original video data into an account book, and meanwhile, a new block is constructed and synchronized to other accounting nodes.
The cochain registration information contains the characteristic value of the original video data and the corresponding time information, so that the purpose of registering the copyright of the original file data can be achieved completely, and the transaction of copyright ownership can be carried out.
Optionally, fig. 4 is a flowchart of an infringement determination method provided in an embodiment of the present application, and specifically relates to a possible process of determining infringement data, where the method includes the following steps:
And step 404, determining whether the target file data is infringing data or not based on the distance value.
The feature value of the original video data registered on the block chain may be called first, and the feature value of the target file data may be calculated by a process similar to the process of calculating the feature value of the original video data. And then, starting from the 1 st characteristic value of the target file data and each characteristic value of the original video data, traversing and comparing, and sequentially calculating the distance value between the characteristic value of the target file data and each characteristic value in the characteristic values of the uplink registration. For example, the distance value may be a hamming distance value, and the specific calculation method may refer to an existing calculation method of hamming distance, which is not described herein again. The smaller the hamming distance, the closer the two images are represented.
In some optional embodiments, if the distance value is smaller than the preset distance threshold, at least part of the target file data is determined to be infringing data.
For example, the preset distance threshold may be set empirically, for example, the preset distance threshold may be set to 5, and if the calculated hamming distance value is less than 5, at least a part of the data in the target file data is determined as infringing data.
In addition, the number of times that the distance value is smaller than the preset distance threshold value can be obtained, and the number of characteristic values of the original file data can be obtained. And if the times that the distance value is smaller than the preset distance threshold value are equal to the number of the characteristic values of the original file data, determining all data of the target file data as infringement data.
Exemplarily, if the number of times that the hamming distance is less than 5 is equal to the number of feature values of the original video data, it is determined that all data of the target file data are infringement data, that is, the complete video is stolen, and meanwhile, an infringement detection result can be submitted to a copyright party as a right-keeping evidence. For example, if the number of times the distance value is less than 5 is 6 and the number of feature values of the original file data is 6, all the data of the target file data may be determined as infringement data.
By adopting the determining mode, the method is not only suitable for stealing scenes of complete videos, but also suitable for scenes of mixed cutting, videos with advertisements inserted into the head and the tail of the film and the like, and the infringement judgment flexibility is improved.
Fig. 5 is a flowchart of an infringement determination method provided in an embodiment of the present application, and specifically relates to a possible process of obtaining a feature value of original file data, where the method includes the following steps:
And step 504, calculating the similarity between the first multi-modal information and the second multi-modal information.
The preset multi-modal recognition model is obtained by training based on a multi-modal character data set of the character, and the multi-modal character data set of the character comprises at least one of face feature data, head feature data, body feature data and sound feature data.
Illustratively, the set of multimodal character feature data for a person can be divided into a training set and a test set. The method comprises the steps that a multi-modal feature data set of the human beings can be preprocessed according to types, and the multi-modal feature data set of the human beings can be divided into human face detection data and human face attribute data, wherein the human faces in images can be detected through image analysis, rectangular coordinates are generated for each detected human face, and the detected human face is the human face detection data; the face attribute data is a series of biological characteristics for representing face features, has strong self-stability and individual difference, and identifies the identity of a person, including gender, skin color, age, expression and the like. And then, manually labeling the preprocessed data, carrying out weighted average and denoising processing on the training samples based on the preprocessed data on the training data set, pre-training an initial multi-modal recognition model by using a noise-free sample, storing model parameters after the initial multi-modal recognition model is converged, and generating a preset multi-modal recognition model based on the model parameters. And finally, respectively calculating first multi-modal information corresponding to the original file data and second multi-modal information corresponding to the target file data by adopting a preset multi-modal recognition model.
Furthermore, the similarity between the first multi-modal information and the second multi-modal information can be calculated, the greater the similarity is, the greater the possibility that the target file data contains infringement data is, and the target file data which is likely to have infringement can be preliminarily screened out, so that the characteristic value of the original file data can be obtained under the condition that the similarity is greater than a preset similarity threshold, infringement judgment is further carried out according to the characteristic value, and the infringement judgment efficiency and accuracy are improved.
In addition, if it is determined through the operation of step 504 that the similarity between the first multi-modal information and the second multi-modal information is not greater than the preset similarity threshold, it generally indicates that the difference between the original document data and the target document data is large, and the target document data has a low possibility of infringing the original document data, in which case, the obtaining of the characteristic value of the original document data may be terminated to reduce the computation amount in the infringement determination process.
In some embodiments, before comparing the characteristic value of the target file data to be determined with the characteristic value of the uplink registration and determining whether the target file data is infringing data according to the comparison result, the method further comprises: and acquiring authorization chain information of the target file data to be judged. And performing uplink registration on the grant chain information by adopting a block chain technology, and generating uplink registration information corresponding to the target file data, wherein the uplink registration information comprises the uplink-registered grant chain information. And comparing the authorization chain information of the target file data with the reference authorization chain information of the original file data prestored in the database.
Further, determining whether the target file data is infringement data according to the comparison result may include: if the authorization chain information of the target file data is consistent with the reference authorization chain information, comparing the characteristic value of the target file data to be judged with the characteristic value of the uplink registration, and determining whether the target file data is infringing data according to the comparison result.
In this case, for example, the target file data and the original file data are file data corresponding to the video a, the reference grant chain information of the original file data pre-stored in the database is 1-2-3, and the grant chain information of the uplink-registered target file data is also 1-2-3, but actually, 3 of the uplink-registered grant chain information may be forged. Therefore, the eigenvalue of the target file data can be further compared with the eigenvalue of the uplink registration, so as to determine whether the target file data is infringing data according to the comparison result of the eigenvalues.
In addition, under the condition that the target file data and the original file data are both file data corresponding to the video A, if the authorization chain information of the target file data is inconsistent with the reference authorization chain information, the video A corresponding to the target file data has no copyright, so that the target file data can be directly determined to be infringement data, and the infringement judgment can be more accurately and efficiently carried out by adopting the method.
Fig. 6 is an overall flowchart of a method for determining infringement of data of a movie file according to an embodiment of the present application, where the method includes the following steps:
And step 602, performing gray level conversion on the adjusted image group to generate a gray level image group.
In this embodiment, the characteristic value of the original file data is obtained, and then the block chain technology is adopted to perform uplink registration on the characteristic value, so as to generate uplink registration information corresponding to the original file data, where the uplink registration information includes the characteristic value of the uplink registration, and finally the characteristic value of the target file data to be determined is compared with the characteristic value of the uplink registration, and whether the target file data is infringing data is determined according to the comparison result. The block chain technology has the characteristics of being unforgeable, untrustworthy and traceable, so that after the characteristic values are subjected to uplink registration, the accuracy of the characteristic values is ensured, and the accuracy is higher when whether the target file data is infringement data or not is judged through the characteristic values finally.
Fig. 7 is an overall flowchart of another infringement determination method for IP derivative data according to an embodiment of the present application, where the method includes the following steps:
And step 702, calculating the similarity between the first multi-modal information and the second multi-modal information.
And 703, if the similarity is greater than a preset similarity threshold, calculating a characteristic value of the derivative data by using a hash algorithm.
And 707, acquiring the times that the distance value is smaller than the preset distance threshold, and acquiring the number of the characteristic values of the derivative data.
In the embodiment, after the multi-mode information of the derivative data is calculated by using the preset multi-mode recognition model, the similarity between the derivative data and the target file data to be judged is calculated according to the multi-mode information, the derivative data which is possibly infringed is preliminarily screened out based on the similarity, and then infringement judgment is further performed according to the characteristic value, so that the infringement judgment efficiency and accuracy are improved.
Embodiments of the apparatus corresponding to the embodiments of the method described above are described below.
The embodiment of the present application further provides an infringement determination apparatus 800, configured to execute the infringement determination method in the foregoing embodiment.
Specifically, as shown in fig. 8, the apparatus includes: an acquisition module 801, a generation module 802 and a determination module 803. Furthermore, the apparatus may also comprise other more or less units/modules, such as a storage unit, a transmitting unit, etc.
An obtaining module 801, configured to obtain a feature value of original file data.
A generating module 802, configured to perform uplink registration on the feature value by using a block chain technique, and generate uplink registration information corresponding to the original file data; the ul registration information includes a characteristic value of the ul registration.
The determining module 803 is configured to compare the characteristic value of the target file data to be determined with the characteristic value of the uplink registration, and determine whether the target file data is infringing data according to the comparison result.
Optionally, in a specific implementation manner of the embodiment of the present application, the infringement determination device is further configured to obtain authorization chain information of target file data to be determined. And performing uplink registration on the authorization chain information by adopting a block chain technology, and generating uplink registration information corresponding to the target file data, wherein the uplink registration information comprises the uplink-registered authorization chain information. And comparing the authorization chain information of the target file data with the reference authorization chain information of the original file data prestored in the database. The determining module 803 is specifically configured to, if the authorization chain information of the target file data is consistent with the reference authorization chain information, compare the characteristic value of the target file data to be determined with the characteristic value of the uplink registration, and determine whether the target file data is infringing data according to the comparison result.
Optionally, in a specific implementation manner of the embodiment of the present application, based on content division of original file data, the original file data includes: copyrighted file data and derivative data of the copyrighted file data; the original file data is divided based on the type of the original file data, and the original file data comprises at least one of original video data, original image data and original audio data.
Optionally, in a specific implementation manner of the embodiment of the present application, the obtaining module 801 is specifically configured to, if the original file data includes original video data, obtain an image group corresponding to at least one video clip in the original video data, and respectively calculate a hash value of each frame of original image in the image group by using a hash algorithm, where a feature value of the original video data includes the hash value of each frame of original image; if the original file data comprises original image data, calculating a hash value of the original image data by adopting a hash algorithm, wherein the characteristic value of the original image data comprises the hash value of each original image data; if the original file data comprises original audio data, at least one audio fragment in the original audio data is obtained, a hash algorithm is adopted to calculate the hash value of the original audio fragment, and the characteristic value of the original audio data comprises the hash of each original audio fragment.
Optionally, in a specific implementation manner of the embodiment of the present application, the obtaining module 801 is further configured to perform gray level conversion on each frame of original image in the image group, so as to generate a gray level image group; and calculating the hash value of the gray image by adopting a hash algorithm aiming at each frame of gray image in the gray image group to obtain the characteristic value of the original video data.
Optionally, in a specific implementation manner of the embodiment of the application, the infringement determination device 800 is further configured to input the original file data into a preset multi-modal recognition model for calculation, so as to generate first multi-modal information corresponding to the original file data, input the target file data to be determined into the preset multi-modal recognition model for calculation, and generate second multi-modal information corresponding to the target file data; the preset multi-modal recognition model is obtained by training based on a multi-modal character data set of a character, wherein the multi-modal character data set of the character comprises at least one of face feature data, head feature data, body feature data and sound feature data; calculating the similarity between the first multi-modal information and the second multi-modal information;
the obtaining module 801 is further configured to obtain a feature value of the original file data if the similarity is greater than a preset similarity threshold.
Optionally, in a specific implementation manner of the embodiment of the present application, the obtaining module 801 is further configured to adjust, for each frame of original image in the image group, an image resolution of the original image to a preset resolution, and generate an adjusted image group; and performing gray level conversion on the adjusted image group to generate a gray level image group.
Optionally, in a specific implementation manner of the embodiment of the present application, the determining module 803 is specifically configured to sequentially calculate distance values between the feature value of the target file data and each of the feature values of the uplink registration; based on the distance value, it is determined whether the target file data is infringing data.
Optionally, in a specific implementation manner of the embodiment of the present application, the determining module 803 is further configured to determine that at least part of the data in the target file data is infringing data if the distance value is smaller than a preset distance threshold.
Optionally, in a specific implementation manner of the embodiment of the present application, the determining module 803 is further configured to obtain the number of times that the distance value is smaller than the preset distance threshold, and obtain the number of feature values of the original file data; and if the times that the distance value is smaller than the preset distance threshold value are equal to the number of the characteristic values of the original file data, determining all data of the target file data as infringement data.
In a specific implementation, an embodiment of the present application further provides an electronic device, which may be the server in the foregoing embodiment, and is configured to implement all or part of the foregoing infringement determination method steps.
Fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The method comprises the following steps: at least one processor, a memory, and at least one interface, and may further include a communication bus for connecting the above components.
Wherein, at least one processor may be a CPU or a processing chip, which is used to read and execute the computer program instructions stored in the memory, so that the at least one processor can execute the method flows in the foregoing embodiments.
The Memory may be a non-transitory Memory (non-transitory Memory), which may include volatile Memory, such as a high-speed Random Access Memory (RAM), or may include non-volatile Memory, such as at least one disk Memory.
The at least one interface comprises an input and output interface and a communication interface, wherein the communication interface can be a wired or wireless interface, so that the communication connection between the electronic device and other devices is realized. The input and output interface can be used for connecting peripheral devices such as a display screen, a keyboard and the like.
In some embodiments, the memory stores computer-readable program instructions that, when read and executed by the processor, implement an infringement determination method of the preceding embodiments.
Furthermore, a computer program product is provided in an embodiment of the present application, and is configured to store computer readable program instructions, where the instructions, when executed by a processor, may implement an infringement determination method in the foregoing embodiment.
It is noted that, in the application, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. The term "comprising" is used to specify the presence of stated features, integers, steps, operations, elements, components, and/or groups thereof, but does not exclude the presence of other similar features, integers, steps, operations, components, or groups thereof.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on differences from other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions.
For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM).
Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory. It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof.
In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
The above embodiments of the present invention do not limit the scope of the present invention.
Claims (10)
1. An infringement determination method characterized by comprising:
acquiring a characteristic value of original file data;
performing uplink registration on the characteristic value by adopting a block chain technology to generate uplink registration information corresponding to the original file data; the uplink registration information comprises a characteristic value of uplink registration;
and comparing the characteristic value of the target file data to be judged with the characteristic value of the uplink registration, and determining whether the target file data is infringing data according to a comparison result.
2. The infringement determination method as claimed in claim 1, wherein before the comparing the eigenvalue of the target file data to be determined with the uplink-registered eigenvalue and determining whether the target file data is infringement data according to the comparison result, the method further comprises:
obtaining authorization chain information of the target file data to be judged;
performing uplink registration on the authorization chain information by adopting the block chain technology to generate uplink registration information corresponding to the target file data; the uplink registration information comprises grant chain information of uplink registration;
comparing the authorization chain information of the target file data with reference authorization chain information of the original file data stored in a database in advance;
determining whether the target file data is infringement data according to the comparison result includes:
if the authorization chain information of the target file data is consistent with the reference authorization chain information, comparing the characteristic value of the target file data to be judged with the characteristic value of the uplink registration, and determining whether the target file data is infringing data according to a comparison result.
3. The infringement determination method according to claim 1, wherein the original file data is divided based on a content of the original file data, and the original file data includes: copyrighted file data and derivative data of the copyrighted file data;
the original file data is divided based on the type of the original file data, and the original file data comprises at least one of original video data, original image data and original audio data.
4. The infringement determination method according to claim 3, wherein the obtaining of the feature value of the original document data includes:
if the original file data comprises original video data, acquiring an image group corresponding to at least one video fragment in the original video data, and respectively calculating the hash value of each frame of original image in the image group by adopting a hash algorithm, wherein the characteristic value of the original video data comprises the hash value of each frame of original image;
if the original file data comprises the original image data, calculating a hash value of the original image data by adopting a hash algorithm, wherein the characteristic value of the original image data comprises the hash value of each original image data;
if the original file data comprises the original audio data, at least one audio fragment in the original audio data is obtained, a hash algorithm is adopted to calculate a hash value of the original audio fragment, and the characteristic value of the original audio data comprises the hash of each original audio fragment.
5. The infringement determination method according to claim 4, wherein the calculating, for each original image in the image group, a hash value of the original image by using a hash algorithm to obtain a feature value of the original video data includes:
aiming at each frame of original image in the image group, carrying out gray level conversion on the original image to generate a gray level image group;
and calculating the hash value of each gray image in the gray image group by adopting a hash algorithm to obtain the characteristic value of the original video data.
6. The infringement determination method according to claim 1, further comprising:
inputting the original file data into a preset multi-mode recognition model for calculation to generate first multi-mode information corresponding to the original file data, inputting the target file data to be judged into the preset multi-mode recognition model for calculation to generate second multi-mode information corresponding to the target file data; the preset multi-modal recognition model is obtained by training based on a multi-modal character data set of a character, wherein the multi-modal character data set of the character comprises at least one of face feature data, head feature data, body feature data and sound feature data;
calculating a similarity between the first multimodal information and the second multimodal information;
the obtaining of the feature value of the original file data includes:
and if the similarity is greater than a preset similarity threshold, acquiring a characteristic value of the original file data.
7. The infringement determination method according to claim 5, wherein the generating a grayscale image group by performing grayscale conversion on each frame of original images in the image group includes:
adjusting the image resolution of each original image in the image group to a preset resolution to generate an adjusted image group;
and carrying out gray level conversion on the adjusted image group to generate the gray level image group.
8. The infringement determination method according to claim 1, wherein the comparing the eigenvalue of the target file data to be determined with the eigenvalue of the uplink registration, and determining whether the target file data is infringement data according to the comparison result comprises:
sequentially calculating the distance value between the characteristic value of the target file data and each characteristic value in the characteristic values of the uplink registration;
determining whether the target file data is infringing data based on the distance value.
9. The infringement determination method according to claim 8, wherein the determining whether the target file data is infringement data based on the distance value includes:
and if the distance value is smaller than a preset distance threshold value, determining at least part of data in the target file data as infringing data.
10. The infringement determination method according to claim 9, wherein the determining whether the target file data is infringement data based on the distance value further includes:
acquiring the times that the distance value is smaller than the preset distance threshold value, and acquiring the number of characteristic values of the original file data;
and if the times that the distance value is smaller than the preset distance threshold value are equal to the number of the characteristic values of the original file data, determining all data of the target file data as infringement data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211341213.1A CN115391751A (en) | 2022-10-31 | 2022-10-31 | Infringement determination method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211341213.1A CN115391751A (en) | 2022-10-31 | 2022-10-31 | Infringement determination method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115391751A true CN115391751A (en) | 2022-11-25 |
Family
ID=84115149
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211341213.1A Pending CN115391751A (en) | 2022-10-31 | 2022-10-31 | Infringement determination method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115391751A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116542818A (en) * | 2023-07-06 | 2023-08-04 | 图林科技(深圳)有限公司 | Trademark monitoring and analyzing method based on big data technology |
| CN118051489A (en) * | 2024-04-15 | 2024-05-17 | 广东省电信规划设计院有限公司 | Knowledge sharing method and device based on blockchain intelligent contract and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109614775A (en) * | 2018-11-20 | 2019-04-12 | 安徽大学 | A kind of protect-ing frame structure and method that the copyright based on block chain is traced to the source |
| CN110929230A (en) * | 2019-12-04 | 2020-03-27 | 腾讯科技（深圳）有限公司 | Work management method, device, equipment and storage medium |
| CN111008366A (en) * | 2019-12-04 | 2020-04-14 | 腾讯科技（深圳）有限公司 | Copyright authorization method and device based on block chain |
| CN111507311A (en) * | 2020-05-22 | 2020-08-07 | 南京大学 | Video character recognition method based on multi-mode feature fusion depth network |
| CN111966968A (en) * | 2020-08-20 | 2020-11-20 | 广州原仓信息科技有限公司 | Copyright protection method and system based on block chain |
| CN112990273A (en) * | 2021-02-18 | 2021-06-18 | 中国科学院自动化研究所 | Compressed domain-oriented video sensitive character recognition method, system and equipment |
-
2022
- 2022-10-31 CN CN202211341213.1A patent/CN115391751A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109614775A (en) * | 2018-11-20 | 2019-04-12 | 安徽大学 | A kind of protect-ing frame structure and method that the copyright based on block chain is traced to the source |
| CN110929230A (en) * | 2019-12-04 | 2020-03-27 | 腾讯科技（深圳）有限公司 | Work management method, device, equipment and storage medium |
| CN111008366A (en) * | 2019-12-04 | 2020-04-14 | 腾讯科技（深圳）有限公司 | Copyright authorization method and device based on block chain |
| CN111507311A (en) * | 2020-05-22 | 2020-08-07 | 南京大学 | Video character recognition method based on multi-mode feature fusion depth network |
| CN111966968A (en) * | 2020-08-20 | 2020-11-20 | 广州原仓信息科技有限公司 | Copyright protection method and system based on block chain |
| CN112990273A (en) * | 2021-02-18 | 2021-06-18 | 中国科学院自动化研究所 | Compressed domain-oriented video sensitive character recognition method, system and equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116542818A (en) * | 2023-07-06 | 2023-08-04 | 图林科技(深圳)有限公司 | Trademark monitoring and analyzing method based on big data technology |
| CN118051489A (en) * | 2024-04-15 | 2024-05-17 | 广东省电信规划设计院有限公司 | Knowledge sharing method and device based on blockchain intelligent contract and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | Coverless image steganography using partial-duplicate image retrieval | |
| Zheng et al. | A survey on image tampering and its detection in real-world photos | |
| Walia et al. | Digital image forgery detection: a systematic scrutiny | |
| US20210117529A1 (en) | Authenticating an identity of a person | |
| Piva | An overview on image forensics | |
| CN115391751A (en) | Infringement determination method | |
| CN115997207B (en) | Detecting a sub-image region of interest in an image using a pilot signal | |
| CN112487365B (en) | Information steganography method and information detection method and device | |
| JP2005020742A (en) | Method and apparatus for video copy detection | |
| Dias et al. | Toward image phylogeny forests: Automatically recovering semantically similar image relationships | |
| US10769247B2 (en) | System and method for interacting with information posted in the media | |
| US11368289B1 (en) | Video registration and authentication using blockchain | |
| US20150186624A1 (en) | System and method for managing personal content copyright using context-based search engine | |
| Costa et al. | Image phylogeny forests reconstruction | |
| CN111966968A (en) | Copyright protection method and system based on block chain | |
| Ouyang et al. | A semi-fragile watermarking tamper localization method based on QDFT and multi-view fusion | |
| WO2019192375A1 (en) | Multimedia processing method and device thereof, storage medium, and electronic product | |
| Bozkurt et al. | Detection and localization of frame duplication using binary image template | |
| US11328095B2 (en) | Peceptual video fingerprinting | |
| Mehta et al. | Near-duplicate detection for LCD screen acquired images using edge histogram descriptor | |
| CN113011254A (en) | Video data processing method, computer equipment and readable storage medium | |
| Tang et al. | Border following–based reversible watermarking algorithm for images with resistance to histogram overflowing | |
| CN112559975A (en) | Block chain-based digital media copyright implementation method, equipment and medium | |
| Zeng et al. | Exposing image splicing with inconsistent sensor noise levels | |
| Karaküçük et al. | PRNU based source camera attribution for image sets anonymized with patch-match algorithm |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221125 |
|
| RJ01 | Rejection of invention patent application after publication |