CN107992527B - Data mark checking method, server and storage medium - Google Patents
Data mark checking method, server and storage medium Download PDFInfo
- Publication number
- CN107992527B CN107992527B CN201711113369.3A CN201711113369A CN107992527B CN 107992527 B CN107992527 B CN 107992527B CN 201711113369 A CN201711113369 A CN 201711113369A CN 107992527 B CN107992527 B CN 107992527B
- Authority
- CN
- China
- Prior art keywords
- data
- verified
- area
- preset
- verification
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/36—User authentication by graphic or iconic representation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/12—Applying verification of the received information
Abstract
The invention discloses a data mark checking method, a server and a storage medium, wherein the method comprises the following steps: the method comprises the steps that a server obtains data to be verified with a preset label, and a verification area in the data to be verified is extracted; performing feature marking on the data to be verified through a feature marking model to obtain a target area of the data to be verified, wherein the feature marking model is used for representing the corresponding relation between the data and the area; and comparing the pixel points in the target area with the pixel points in the verification area, and judging that the preset label of the data to be verified is unqualified when the number of the pixel points which are different between the target area and the verification area exceeds a preset number threshold. The invention marks the data through machine learning and can verify the data through the model, thereby saving a large amount of labor cost.
Description
Technical Field
The present invention relates to the field of data processing, and in particular, to a data tag verification method, a server, and a storage medium.
Background
With the development of times, network security becomes an indispensable part of people's lives, and more people spend a large amount of manpower and material resources to improve the protection work of network security. If the correctness is not checked manually, the method has great influence on the subsequent training.
Disclosure of Invention
The invention mainly aims to provide a data mark verification method, and aims to solve the technical problem that in the prior art, verification needs to be performed manually, so that a large amount of manpower is wasted.
In order to achieve the above object, the present invention provides a data mark verification method, including the steps of:
the method comprises the steps that a server obtains data to be verified with a preset label, and a verification area in the data to be verified is extracted;
performing feature marking on the data to be verified through a feature marking model to obtain a target area of the data to be verified, wherein the feature marking model is used for representing the corresponding relation between the data and the area;
and comparing the pixel points in the target area with the pixel points in the verification area, and judging that the preset label of the data to be verified is unqualified when the number of the pixel points which are different between the target area and the verification area exceeds a preset number threshold.
Preferably, before the data to be verified is subjected to feature labeling through a feature labeling model and a target area of the data to be verified is obtained, the method further includes:
and establishing a convolutional neural network model, acquiring a plurality of sample data with labels, training the convolutional neural network model, and taking the trained convolutional neural network model as the feature tag model.
Preferably, the performing feature marking on the data to be verified through a feature marking model to obtain a target area of the data to be verified specifically includes:
training the convolutional layer through the data to be verified, extracting features of the convolutional layer, adding a pooling layer at a preset position of the convolutional layer, performing pooling calculation on the extracted features through the pooling layer, taking the calculated data as a label of the data to be verified, and extracting a target area in the marked data.
Preferably, before the data to be verified with the preset tag is obtained, the method further includes:
receiving a marking request of a user, extracting a target data form in the marking request, and extracting a plurality of data materials corresponding to the target data form in a preset area according to the target data form;
receiving a marking quantity request of a user, and carrying out feature marking on the data materials according to the marking quantity request.
Preferably, the target data form is at least one of a character type, a slide type, and a click type.
Preferably, before the extracting, according to the target data form, a plurality of data materials corresponding to the target data form in a preset area, the method further includes:
and acquiring a user storage instruction, and storing the data materials in a preset area according to the storage instruction.
Preferably, the obtaining a user storage instruction and storing the data materials in a preset area according to the storage instruction specifically includes:
and acquiring a user storage instruction, putting the data materials into the preset convolutional neural network model for classification according to the storage instruction, and storing the classified materials in the preset area.
Preferably, the receiving a request for the number of marks from a user, and performing feature marking on the data materials according to the request for the number of marks specifically includes:
and extracting the code number in the mark number request, and carrying out price settlement according to the code number.
In addition, to achieve the above object, the present invention further provides a server, including: a memory, a processor and a data marker verification program stored on the memory and executable on the processor, the data marker verification program configured to implement the steps of the data marker verification method as described above.
In addition, to achieve the above object, the present invention further provides a storage medium, which stores a data tag verification program, and when the data tag verification program is executed by a processor, the storage medium implements the steps of the data tag verification method as described above.
According to the data mark checking method provided by the invention, the data is marked through machine learning, and the data can be checked through the model, so that a large amount of labor cost is saved.
Drawings
FIG. 1 is a schematic diagram of a server architecture of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a first embodiment of a data mark verification method according to the present invention;
FIG. 3 is a flowchart illustrating a second embodiment of a data mark verification method according to the present invention;
FIG. 4 is a flowchart illustrating a data mark verification method according to a third embodiment of the present invention;
FIG. 5 is a flowchart illustrating a fourth embodiment of a data mark verification method according to the present invention;
FIG. 6 is a flowchart illustrating a fifth embodiment of a data mark verification method according to the present invention;
fig. 7 is a flowchart illustrating a data mark verification method according to a sixth embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic diagram of a mark-up server structure of a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the marking server may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the markup server architecture shown in FIG. 1 does not constitute a limitation of markup servers, and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and a data tag checking program.
In the markup server shown in fig. 1, the network interface 1004 is mainly used for connecting a client and performing data communication with the client; the user interface 1003 is mainly used for connecting a user terminal and performing data communication with the terminal; the processor 1001 in the marking server of the present invention calls the data mark check program stored in the memory 1005, and performs the following operations:
the method comprises the steps that a server obtains data to be verified with a preset label, and a verification area in the data to be verified is extracted;
performing feature marking on the data to be verified through a feature marking model to obtain a target area of the data to be verified, wherein the feature marking model is used for representing the corresponding relation between the data and the area;
and comparing the pixel points in the target area with the pixel points in the verification area, and judging that the preset label of the data to be verified is unqualified when the number of the pixel points which are different between the target area and the verification area exceeds a preset number threshold.
Further, the processor 1001 may call the data mark check program stored in the memory 1005, and further perform the following operations:
and establishing a convolutional neural network model, acquiring a plurality of sample data with labels, training the convolutional neural network model, and taking the trained convolutional neural network model as the feature tag model.
Further, the processor 1001 may call the data mark check program stored in the memory 1005, and further perform the following operations:
training the convolutional layer through the data to be verified, extracting features of the convolutional layer, adding a pooling layer at a preset position of the convolutional layer, performing pooling calculation on the extracted features through the pooling layer, taking the calculated data as a label of the data to be verified, and extracting a target area in the marked data.
Further, the processor 1001 may call the data mark check program stored in the memory 1005, and further perform the following operations:
receiving a marking request of a user, extracting a target data form in the marking request, and extracting a plurality of data materials corresponding to the target data form in a preset area according to the target data form;
receiving a marking quantity request of a user, and carrying out feature marking on the data materials according to the marking quantity request.
Further, the processor 1001 may call the data mark check program stored in the memory 1005, and further perform the following operations:
and acquiring a user storage instruction, and storing the data materials in a preset area according to the storage instruction.
Further, the processor 1001 may call the data mark check program stored in the memory 1005, and further perform the following operations:
and acquiring a user storage instruction, putting the data materials into the preset convolutional neural network model for classification according to the storage instruction, and storing the classified materials in the preset area.
Further, the processor 1001 may call the data mark check program stored in the memory 1005, and further perform the following operations:
and extracting the code number in the mark number request, and carrying out price settlement according to the code number.
According to the embodiment, the data are marked through machine learning, and can be verified through the model, so that a large amount of labor cost is saved.
Based on the hardware structure, the embodiment of the data mark checking method is provided.
Referring to fig. 2, fig. 2 is a flowchart illustrating a data mark verification method according to a first embodiment of the present invention.
In a first embodiment, the data tag verification method includes the steps of:
step S10, the server acquires data to be verified with a preset label and extracts a verification area in the data to be verified;
it should be noted that, in this embodiment, data verification is performed through a data tagging platform, and the general data tagging platform may tag data as a character-type tag, a sliding-type tag, and a click-type tag, so that the three data formats may be tagged, and other formats may also be used, which is not limited in this embodiment.
In general, only character-type tags are available in the market, and there are no picture identifying code tags, sliding identifying code tags, and click identifying code tags, but the identifying codes can be marked by the universal data marking platform in this embodiment.
It is understood that the verification area is an area where the marked data is verified, for example, when a user verifies the missing block position through sliding verification, there is a mark range in the mark of the slider verification code, and the mark range can be used as an extracted verification area.
In order to receive data, the user logs in through a universal data tagging platform, and the user may log in through a network address, where the network address may be a Uniform Resource Locator (URL) address or an Internet Protocol (IP) address of an Internet, and a link in a website, and may also log in through other manners, which is not limited in this embodiment. The user can also scan the code through the WeChat interface to log in, conveniently provides a login entrance, and does not need to log in through complicated registration.
In a specific implementation, the data of the preset tag may be manually marked data, or may be data marked by the general data marking platform.
Step S20, performing feature labeling on the data to be verified through a feature labeling model to obtain a target area of the data to be verified, wherein the feature labeling model is used for representing the corresponding relation between the data and the area;
the feature labeling model is a trained model with a machine learning function, can carry out feature extraction on data through the preset convolutional neural network model, and carries out feature labeling according to the features of the data.
In order to improve the verification accuracy, the data is put into a feature marking model for feature extraction, the data is marked through the extracted features, and the marked area is used as a target area.
It should be noted that, when the data to be verified is artificially marked data, the artificially marked data is put into the feature marking model for feature marking, and the model marked by the feature marking model is verified against the artificially marked data, so that the verification of the artificially marked data is realized.
It can be understood that when the marking verification is carried out, after the data are marked manually, the marked data cannot be verified, the marked data can be verified through the universal data marking platform, so that the marked data can be verified, in addition, the universal data marking platform can be used for marking through machine learning, the universal marking of the data is realized, and the management and the improvement of the correctness of the data marking are facilitated.
Step S30, comparing the pixel points in the target area with the pixel points in the verification area, and judging that the preset label of the data to be verified is unqualified when the number of the pixel points which are different between the target area and the verification area exceeds a preset number threshold.
In this embodiment, the server may obtain pixel point information in a target region, where the pixel point information may represent matching information for performing data matching on the data to be verified, for example, a region for performing verification through sliding is marked on a sliding verification code, and the region is marked by a pixel point, so that position information for performing verification may be accurately indicated, the pixel point in the target region and the pixel point in the verification region are verified, a difference between the pixel points in the target region and the pixel point in the verification region is compared, and when data of the difference reaches a preset threshold value, it may be determined that a label of the data to be verified is an unqualified label.
It should be noted that, when the data is artificially marked data, the extracted first region and the target region are verified, and when the verified difference data reaches a preset threshold, it indicates that the difference between the artificially marked data and the data marked by using the preset convolutional neural network model is relatively large, so that it can be determined that the artificially marked data is unqualified.
In a specific implementation, the data may also be data that has been marked by the preset convolutional neural network model, and when the data reaches a preset number, the marked data may also be automatically verified, thereby omitting manual verification.
There will be a range of marks for the missing block position in the sliding verification. In the manual marking process, if the difference between the manual coding marking position and the position given by the preset convolutional neural network model is too large, the marking is judged to be unqualified, and thus the manual checking process is omitted. When the verification code is clicked, the position to be marked is preset, the convolutional neural network model gives some relative positions, if the difference between the position and the number of the artificial marks and the position number given by the preset convolutional neural network model is large, the judgment is unqualified, and if the difference between the position and the number of the artificial marks and the position number given by the preset convolutional neural network model is not large, the judgment is qualified. Thus ensuring the quality of the marking data, saving the time of manual inspection,
according to the embodiment, the data are marked through machine learning, and can be verified through the model, so that a large amount of labor cost is saved.
Further, as shown in fig. 3, a second embodiment of the data tag verification method according to the present invention is proposed based on the first embodiment, and in this embodiment, before the step S20, the method further includes the steps of:
step S201, a convolutional neural network model is established, a plurality of sample data with labels are obtained to train the convolutional neural network model, and the trained convolutional neural network model is used as the feature label model.
It should be noted that, in this embodiment, data is labeled through machine learning, and a trained model with a labeling function is required before the data is labeled, in this embodiment, a convolutional neural network model is established through a line, and is trained through the convolutional neural network model, so that the convolutional neural network model can have a function of a feature label, and the trained convolutional neural network model is used as a preset convolutional neural network model.
In a specific implementation, the model is trained by a large amount of training data, the training data are high-quality data, the generalization capability of the convolutional neural network model can be improved by the large amount of training data and the high-quality data, new data can be subjected to feature labeling by the generalization capability, and even if the new data are not in the previously trained data, the feature labeling of the new data can be realized, so that the capability of the convolutional neural network model is improved.
In this embodiment, the convolutional neural network model is trained by a large amount of data, so that data labeling of the preset convolutional neural network model can be realized, and the generalization capability of the preset convolutional neural network model is improved.
Further, as shown in fig. 4, a third embodiment of the data tag verification method according to the present invention is proposed based on the first embodiment, and in this embodiment, the step S20 specifically includes:
step S202, training a convolutional layer through the data to be verified, extracting features of the convolutional layer, adding a pooling layer at a preset position of the convolutional layer, performing pooling calculation on the extracted features by the pooling layer, taking the calculated data as a label of the data to be verified, and extracting a target area in the marked data.
In this embodiment, the convolutional neural network model can perform feature labeling on data, and can perform feature labeling on the data in the three forms, that is, character-type data, sliding-type data, and click-type data, so as to solve the problem that the feature labeling cannot be performed on the three forms at the same time.
In a specific implementation, a sparse self-encoder C1 is trained, C1 is used as a convolutional layer, convolutional feature extraction is performed from user data, finally, a pooling layer S1 is added at the downstream of C1, pooling calculation is performed on the features extracted by C1, if more abstract features need to be extracted, a convolutional layer C2 is added after S1, C2 is a self-encoder trained by data of S1, a pooling layer S2 is added at the downstream of C2, and the output of the last pooling can be used as a training classifier.
In this embodiment, feature extraction is performed on the data to be verified through the convolutional layer and the pooling layer, and other feature extraction can be performed on the basis, so that feature information in the data can be more accurately extracted, and the accuracy and the high yield of data marking are realized.
Further, as shown in fig. 5, a fourth embodiment of the data mark verification method according to the present invention is proposed based on any one of the first embodiment, the second embodiment and the third embodiment, in this embodiment, explained based on the first embodiment, before the step S10, the method further includes:
step S101, receiving a marking request of a user, extracting a target data form in the marking request, and extracting a plurality of data materials corresponding to the target data form in a preset area according to the target data form;
in this embodiment, a user may also mark data through the universal data marking platform, and when the user logs in through the universal data marking platform, the platform may push the type of the data to be marked, for example, whether the data belongs to slide type data or click type data, extract the data type selected by the user, and push the classified data from the background according to the data type, that is, according to the target data form selected by the user, the data material corresponding to the target data form may be extracted in a preset storage area.
It should be noted that the data materials are data pre-stored in the server, and when the data are received, the server may classify the data, and the data may be data without feature marks or data that has undergone feature marks, and the data are classified and stored in a preset area, thereby facilitating data management.
And step S102, receiving a marking quantity request of a user, and performing feature marking on the data materials according to the marking quantity request.
In a specific implementation, when the feature marking is performed according to a user request, the corresponding marking can be performed according to the number of the marks selected by the user.
In this embodiment, the server provides the user with a selection of a form of data marking, so that data marking in various forms can be realized, and in addition, the server can also provide the user with a selection of the number of marks, so that the user experience is improved, and the server can count the number of marks more favorably.
Further, as shown in fig. 6, a fifth embodiment of the data mark verification method of the present invention is proposed based on the fourth embodiment, and in this embodiment, before the step S101, the method further includes:
and acquiring a user storage instruction, and storing the data materials in a preset area according to the storage instruction.
The obtaining of the user storage instruction stores the data materials in a preset area according to the storage instruction, and specifically includes:
step S103, a user storage instruction is obtained, the data materials are placed into the preset convolutional neural network model for classification according to the storage instruction, and the classified materials are stored in the preset area.
It should be noted that, in this embodiment, the data is data pre-stored in the server, the server may receive a storage instruction of the user, pre-store the data that the user needs to label in the server according to the storage instruction, and the user may push the stored user data to the user through the user setup server by logging in the universal data labeling platform.
The server can also classify the received data materials through a preset convolutional neural network model, the preset convolutional neural network model is trained through a large amount of high-quality data, the model is trained through the data when the model is built, and therefore the model has the data labeling capacity and the classification capacity, and the model can classify the data through the type of the stored data.
In the specific implementation, the data can be divided into an image-text clicking type, a dragging slider type and a character type, and the data is distinguished and classified and managed according to the three classification forms, so that the actual requirements of users can be met, and the user experience is improved.
In this embodiment, the server may classify the data by presetting the convolutional neural network model, so that when a user has a data marking requirement, the user may perform corresponding data push according to the type of the data to be marked selected by the user, thereby improving user experience.
Further, as shown in fig. 7, a sixth embodiment of the data mark verification method according to the present invention is proposed based on the fourth embodiment, and in this embodiment, the step S102 specifically includes:
and step S104, extracting the code number in the mark number request, and carrying out price settlement according to the code number.
In this embodiment, when the user performs data processing through the universal data tagging platform, the user is paid instead of free, and when the user performs data tagging through the platform, the user charges a fee according to the number of tags selected by the user.
In order to realize reasonable statistics of charging, the server counts the characteristic mark data of the user, calculates the price according to the counted mark quantity and the corresponding charging standard, and pushes the calculated cost to the user.
In a particular implementation, as each type of captcha is added, a price is given to the indicia of the currently added captcha. The user can freely select which type of verification code is marked, and then the number of codes printed and the total price of each item are automatically counted in the account system.
In this embodiment, the server may extract the number of codes in the request for the number of tags, and perform price settlement according to the number of codes, thereby implementing intellectualization of the server.
In addition, an embodiment of the present invention further provides a storage medium, where a data tag verification program is stored on the storage medium, and when executed by a processor, the data tag verification program implements the following operations:
the method comprises the steps that a server obtains data to be verified with a preset label, and a verification area in the data to be verified is extracted;
performing feature marking on the data to be verified through a feature marking model to obtain a target area of the data to be verified, wherein the feature marking model is used for representing the corresponding relation between the data and the area;
and comparing the pixel points in the target area with the pixel points in the verification area, and judging that the preset label of the data to be verified is unqualified when the number of the pixel points which are different between the target area and the verification area exceeds a preset number threshold.
Further, the data tag checking program when executed by the processor further implements the following operations:
and establishing a convolutional neural network model, acquiring a plurality of sample data with labels, training the convolutional neural network model, and taking the trained convolutional neural network model as the feature tag model.
Further, the data tag checking program when executed by the processor further implements the following operations:
training the convolutional layer through the data to be verified, extracting features of the convolutional layer, adding a pooling layer at a preset position of the convolutional layer, performing pooling calculation on the extracted features through the pooling layer, taking the calculated data as a label of the data to be verified, and extracting a target area in the marked data.
Further, the data tag checking program when executed by the processor further implements the following operations:
receiving a marking request of a user, extracting a target data form in the marking request, and extracting a plurality of data materials corresponding to the target data form in a preset area according to the target data form;
receiving a marking quantity request of a user, and carrying out feature marking on the data materials according to the marking quantity request.
Further, the data tag checking program when executed by the processor further implements the following operations:
and acquiring a user storage instruction, and storing the data materials in a preset area according to the storage instruction.
Further, the data tag checking program when executed by the processor further implements the following operations:
and acquiring a user storage instruction, putting the data materials into the preset convolutional neural network model for classification according to the storage instruction, and storing the classified materials in the preset area.
Further, the data tag checking program when executed by the processor further implements the following operations:
and extracting the code number in the mark number request, and carrying out price settlement according to the code number.
According to the embodiment, the data are marked through machine learning, and can be verified through the model, so that a large amount of labor cost is saved.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system 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 system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A method for verifying a data marker, the method comprising the steps of:
the method comprises the steps that a server obtains data to be verified with a preset label, and extracts a verification area in the data to be verified, wherein the data to be verified with the preset label is artificially marked data, and the verification area is an area for verifying the marked data;
performing feature marking on the data to be verified through a feature marking model to obtain a target area of the data to be verified, wherein the feature marking model is used for representing the corresponding relation between the data and the area;
and comparing the pixel points in the target area with the pixel points in the verification area, and judging that the preset label of the data to be verified is unqualified when the number of the pixel points which are different between the target area and the verification area exceeds a preset number threshold.
2. The data mark verification method of claim 1, wherein before the data to be verified is subjected to feature marking through a feature mark model to obtain a target area of the data to be verified, the method further comprises:
and establishing a convolutional neural network model, acquiring a plurality of sample data with labels, training the convolutional neural network model, and taking the trained convolutional neural network model as the feature tag model.
3. The data mark verification method according to claim 1, wherein the obtaining of the target area of the data to be verified by performing the feature mark on the data to be verified through the feature mark model specifically includes:
training the convolutional layer through the data to be verified, extracting features of the convolutional layer, adding a pooling layer at a preset position of the convolutional layer, performing pooling calculation on the extracted features through the pooling layer, taking the calculated data as a label of the data to be verified, and extracting a target area in the marked data.
4. The data tag verification method of any one of claims 1 to 3, wherein before the obtaining of the data to be verified with the preset tag, the method further comprises:
receiving a marking request of a user, extracting a target data form in the marking request, and extracting a plurality of data materials corresponding to the target data form in a preset area according to the target data form;
receiving a marking quantity request of a user, and carrying out feature marking on the data materials according to the marking quantity request.
5. The data tag verification method of claim 4, wherein the target data form is at least one of a character type, a slide type, and a click type.
6. The data tag verification method of claim 4, wherein before extracting a number of data assets corresponding to the target dataform in a preset area according to the target dataform, the method further comprises:
and acquiring a user storage instruction, and storing the data materials in a preset area according to the storage instruction.
7. The data mark verification method according to claim 6, wherein the obtaining of the user storage instruction and the storing of the plurality of data materials in a preset area according to the storage instruction specifically include:
and acquiring a user storage instruction, putting the data materials into the preset convolutional neural network model for classification according to the storage instruction, and storing the classified materials in the preset area.
8. The data tag verification method of claim 4, wherein the receiving of the tag quantity request from the user and the feature tagging of the plurality of data materials according to the tag quantity request specifically comprises:
and extracting the code number in the mark number request, and carrying out price settlement according to the code number.
9. A server, characterized in that the server comprises: a memory, a processor and a data verification program stored on the memory and executable on the processor, the data marker verification method program being configured to implement the steps of the data marker verification method as claimed in any one of claims 1 to 8.
10. A storage medium having stored thereon a data verification program which, when executed by a processor, implements the steps of the data mark verification method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711113369.3A CN107992527B (en) | 2017-11-09 | 2017-11-09 | Data mark checking method, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711113369.3A CN107992527B (en) | 2017-11-09 | 2017-11-09 | Data mark checking method, server and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107992527A CN107992527A (en) | 2018-05-04 |
| CN107992527B true CN107992527B (en) | 2021-01-29 |
Family
ID=62030769
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711113369.3A Active CN107992527B (en) | 2017-11-09 | 2017-11-09 | Data mark checking method, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107992527B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109063456B (en) * | 2018-08-02 | 2021-10-08 | 浙江大学 | Security detection method and system for image type verification code |
| CN109325496B (en) * | 2018-09-30 | 2021-07-23 | 武汉斗鱼网络科技有限公司 | Bullet screen checking method and device based on character removal, terminal and storage medium |
| CN110674349B (en) * | 2019-09-27 | 2023-03-14 | 北京字节跳动网络技术有限公司 | Video POI (Point of interest) identification method and device and electronic equipment |
| CN111259980B (en) * | 2020-02-10 | 2023-10-03 | 北京小马慧行科技有限公司 | Method and device for processing annotation data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8483518B2 (en) * | 2010-02-19 | 2013-07-09 | Microsoft Corporation | Image-based CAPTCHA exploiting context in object recognition |
| CN107067006A (en) * | 2017-04-20 | 2017-08-18 | 金电联行（北京）信息技术有限公司 | A kind of method for recognizing verification code and system for serving data acquisition |
| CN107085730A (en) * | 2017-03-24 | 2017-08-22 | 深圳爱拼信息科技有限公司 | A kind of deep learning method and device of character identifying code identification |
| CN107292307A (en) * | 2017-07-21 | 2017-10-24 | 华中科技大学 | One kind is inverted Chinese character identifying code automatic identifying method and system |
-
2017
- 2017-11-09 CN CN201711113369.3A patent/CN107992527B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8483518B2 (en) * | 2010-02-19 | 2013-07-09 | Microsoft Corporation | Image-based CAPTCHA exploiting context in object recognition |
| CN107085730A (en) * | 2017-03-24 | 2017-08-22 | 深圳爱拼信息科技有限公司 | A kind of deep learning method and device of character identifying code identification |
| CN107067006A (en) * | 2017-04-20 | 2017-08-18 | 金电联行（北京）信息技术有限公司 | A kind of method for recognizing verification code and system for serving data acquisition |
| CN107292307A (en) * | 2017-07-21 | 2017-10-24 | 华中科技大学 | One kind is inverted Chinese character identifying code automatic identifying method and system |
Non-Patent Citations (3)
| Title |
|---|
| 如何正确使用验证码打码器;新十二六;《https://jingyan.baidu.com/article/c910274b8b924ecd361d2d89.html》;20161206;全文 * |
| 字符型图片验证码识别完整过程及Python实现;一点一滴的Beer;《https://www.cnblogs.com/beer/p/5672678.html》;20160718;全文 * |
| 扫描注册码图片对比相似度破解验证码;wiThouTTears;《http://blog.chinaunix.net/uid-8665522-id-2017884.html》;20140201;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107992527A (en) | 2018-05-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107992527B (en) | Data mark checking method, server and storage medium | |
| CN108027830B (en) | System and method for automatic content verification | |
| CN111079022A (en) | Personalized recommendation method, device, equipment and medium based on federal learning | |
| KR102002024B1 (en) | Method for processing labeling of object and object management server | |
| CN109948077B (en) | User behavior data acquisition method, device, equipment and computer storage medium | |
| CN112100431B (en) | Evaluation method, device and equipment of OCR system and readable storage medium | |
| CN110490651B (en) | Information pushing method, device, equipment and computer readable storage medium | |
| CN107733967A (en) | Processing method, device, computer equipment and the storage medium of pushed information | |
| CN108648019A (en) | Promote method, apparatus, electronic equipment and the storage medium of advertisement analysis efficiency | |
| CN111191201A (en) | User identification method, device and equipment based on data buried points and storage medium | |
| CN110363044A (en) | The input method and system of express delivery odd numbers | |
| CN110837653A (en) | Label prediction method, device and computer readable storage medium | |
| CN104850971A (en) | Correlation method between order information and logistics information, and device thereof | |
| CN112000884A (en) | User content recommendation method and device, server and storage medium | |
| CN115659226A (en) | Data processing system for acquiring APP label | |
| JP2014238815A (en) | Information processing system, information providing method, terminal device, and program | |
| CN113205130B (en) | Data auditing method and device, electronic equipment and storage medium | |
| CN105138875A (en) | Identification method and device for user information | |
| CN111782514A (en) | Test data comparison method and device | |
| KR20160131699A (en) | Advertising Method of Mobile Device, the Mobile Device and Program Distributing Server therefor | |
| US20220245536A1 (en) | Method and device for updating ai models, and storage medium | |
| CN114782955A (en) | Buried point processing method, electronic device, and storage medium | |
| CN112817816B (en) | Embedded point processing method and device, computer equipment and storage medium | |
| CN107330069A (en) | Multimedia data processing method and device, server and storage medium | |
| CN110929725B (en) | Certificate classification method, device and computer readable storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Data mark checking method, server and storage medium Effective date of registration: 20210622 Granted publication date: 20210129 Pledgee: Bank of China Limited Wuhan Donghu New Technology Development Zone Branch Pledgor: WUHAN JIYI NETWORK TECHNOLOGY Co.,Ltd. Registration number: Y2021420000041 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |