CN110351094B - Character verification method, device, computer equipment and storage medium - Google Patents
Character verification method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110351094B CN110351094B CN201910601303.1A CN201910601303A CN110351094B CN 110351094 B CN110351094 B CN 110351094B CN 201910601303 A CN201910601303 A CN 201910601303A CN 110351094 B CN110351094 B CN 110351094B
- Authority
- CN
- China
- Prior art keywords
- verification
- character
- semantic
- characters
- statement
- 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
- 238000012795 verification Methods 0.000 title claims abstract description 571
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012545 processing Methods 0.000 claims description 32
- 238000003062 neural network model Methods 0.000 claims description 29
- 238000013507 mapping Methods 0.000 claims description 18
- 238000012216 screening Methods 0.000 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000010200 validation analysis Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 abstract description 15
- 230000007547 defect Effects 0.000 abstract description 5
- 238000012549 training Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 9
- 238000012512 characterization method Methods 0.000 description 6
- 230000006854 communication Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000007175 bidirectional communication Effects 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 230000008719 thickening Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
- H04L9/3271—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using challenge-response
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computer Security & Cryptography (AREA)
- Biophysics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Signal Processing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Hardware Design (AREA)
- Character Discrimination (AREA)
- Document Processing Apparatus (AREA)
Abstract
The embodiment of the invention discloses a character verification method, a device, computer equipment and a storage medium, comprising the following steps: receiving a verification request sent by a target terminal; randomly extracting verification sentences in a preset sentence database according to the verification request; identifying the semantics of the verification statement and generating verification characters according to a verification mode characterized by the semantics of the verification statement; and sending the verification statement and the verification character to the target terminal. The server side simultaneously sends verification sentences and verification characters to the target terminal during verification, and a user can select correct characters from the verification characters to finish verification only after correctly understanding semantic prompts of the verification sentences. Therefore, the image recognition technology can select and verify in the verification character only after understanding the semantics of the verification statement, so that the defect that the direct input type verification mode is easily cracked by the image recognition technology is avoided, the verification safety is improved, and the network resource is protected to be safely used.
Description
Technical Field
The embodiment of the invention relates to the field of data security, in particular to a character verification method, a character verification device, computer equipment and a storage medium.
Background
Along with the development of scientific technology, the coming of the information age brings great convenience to us, and simultaneously brings great trouble to the life of people. For example, when buying a ticket on the internet, there are often illegal vendors who rapidly swipe the ticket by developing an application program and then resell at high price to obtain a fulminant, but users who really need to buy the ticket cannot buy the ticket through an internet interface, and in real life, similar internet resource robbery occurs in various fields, and the actions of rapidly swipe the ticket and get a commission through the application program are difficult to be stopped. To limit the occurrence of the above-described behavior, an information authentication application occurs.
In the prior art, verification is usually performed by using a verification code, when a server side performs verification operation, the server side firstly acquires the verification code from the server side, then receives verification information input by a user according to the verification code, finally, the server side sends the acquired user information to the server side, and the server side determines whether the verification is passed or not by comparing whether the verification code is consistent with characters in the verification information.
The inventor of the invention discovers in the research that in the prior art, the verification code technology is simple, the verification code is arranged on the background image for display, the verification code can be recognized without barriers through the image recognition technology, and then the recognized verification code is directly sent to the server for verification without manual input. Therefore, in the prior art, the verification code is easy to identify, the verification security level is low, and the network resource cannot be truly protected from being used safely.
Disclosure of Invention
The embodiment of the invention provides a verification method for prompting a verification result through a verification sentence during verification, wherein a user can select a character verification method, a device, computer equipment and a storage medium of a correct verification result only in the aspect of understanding the meaning of the verification sentence.
In order to solve the technical problems, the embodiment of the invention adopts the following technical scheme: provided is a character verification method including:
receiving a verification request sent by a target terminal;
randomly extracting verification sentences in a preset sentence database according to the verification request, wherein the verification sentences are used for verification prompts;
identifying the semantics of the verification statement and generating verification characters according to a verification mode characterized by the semantics of the verification statement, wherein at least one character in the verification characters has a mapping relation with the verification mode;
And sending the verification statement and the verification character to the target terminal.
Optionally, the identifying the semantics of the verification statement and generating the verification character according to the verification mode characterized by the semantics of the verification statement includes:
invoking the verification statement and reading a text field in the verification statement;
converting the text field into a plurality of matrixes according to a preset conversion mode;
inputting the data matrix into a preset semantic recognition model, wherein the semantic recognition model is a neural network model which is trained in advance to a convergence state and used for carrying out semantic recognition on characters;
and extracting the verification characters from a preset character database according to a verification mode of the semantic classification result representation output by the semantic recognition model.
Optionally, the verification mode is font verification, the verification mode characterized by the semantic classification result output according to the semantic recognition model extracts the verification characters from a preset character database, and the method further includes:
screening at least one deformation character from the verification characters;
performing deformation processing on the at least one deformation character according to the deformation type characterized by the verification mode to generate a semantic character, wherein the semantic character and the verification statement have a mapping relation;
And replacing the deformed character in the verification character with the semantic character.
Optionally, the sending the verification sentence and the verification character to the target terminal includes:
screening background images from a preset image database;
overlaying the verification sentence and the verification character on the background image to generate a verification image, wherein the verification character comprises the semantic character;
and sending the verification image to the target terminal.
Optionally, after the verification image is sent to the target terminal, the method further includes:
searching a verification record of the target terminal in a history verification list;
when the verification record of the target terminal accords with a preset first verification condition, invoking a screenshot picture of the verification image in a verification page to the target terminal;
inputting the screenshot picture and the verification image into a preset verification judgment model, wherein the verification judgment model is a neural network model which is trained in advance to a convergence state and is used for judging the similarity of the image;
and confirming whether the target terminal is virtual verification or not according to a judging result output by the verification judging model.
Optionally, after the verification sentence and the verification character are sent to the target terminal, the method further includes:
acquiring verification information uploaded by the target terminal, wherein the verification information comprises target characters which are screened by a user from the verification characters according to the verification statement and used for verification;
comparing the target character with the semantic character to judge whether the target character is consistent with the semantic character;
and when the target character is consistent with the semantic character, confirming that the target terminal passes verification.
Optionally, the comparing the target character with the semantic character to determine whether the target character is consistent with the semantic character includes:
calculating the hamming distance between the target character and the semantic character;
when the Hamming distance is zero, confirming that the target character is consistent with the semantic character; otherwise, confirming that the target character is inconsistent with the semantic character.
In order to solve the above technical problem, an embodiment of the present invention further provides a character verification device, including:
the acquisition module is used for receiving a verification request sent by the target terminal;
The processing module is used for randomly extracting verification sentences in a preset sentence database according to the verification request, wherein the verification sentences are used for verification prompts;
the recognition module is used for recognizing the semantics of the verification statement and generating verification characters according to a verification mode characterized by the semantics of the verification statement, wherein at least one character in the verification characters has a mapping relation with the verification mode;
and the execution module is used for sending the verification statement and the verification character to the target terminal.
Optionally, the character verification device further includes:
the first acquisition sub-module is used for calling the verification statement and reading a text field in the verification statement;
the first processing sub-module is used for converting the text field into a plurality of groups of matrixes according to a preset conversion mode;
the first recognition sub-module is used for inputting the data matrix into a preset semantic recognition model, wherein the semantic recognition model is a neural network model which is trained to a convergence state in advance and used for carrying out semantic recognition on characters;
and the first execution sub-module is used for extracting the verification characters from a preset character database according to the verification mode of the semantic classification result representation output by the semantic recognition model.
Optionally, the verification mode is font verification, and the character verification device further includes:
the first screening submodule is used for screening at least one deformation character from the verification characters;
the second processing sub-module is used for carrying out deformation processing on the at least one deformation character according to the deformation type characterized by the verification mode so as to generate a semantic character, wherein the semantic character and the verification statement have a mapping relation;
and the second execution sub-module is used for replacing the deformed character in the verification character with the semantic character.
Optionally, the character verification device further includes:
the second screening submodule is used for screening background images from a preset image database;
a third processing sub-module, configured to overlay the verification sentence and the verification character on the background image to generate a verification image, where the verification character includes the semantic character;
and the third execution sub-module is used for sending the verification image to the target terminal.
Optionally, the character verification device further includes:
the first searching sub-module is used for searching the verification record of the target terminal in the history verification list;
A fourth processing sub-module, configured to invoke, when the verification record of the target terminal meets a preset first verification condition, a screenshot picture of the verification image in a verification page to the target terminal;
the first input sub-module is used for inputting the screenshot picture and the verification image into a preset verification judgment model, wherein the verification judgment model is a neural network model which is trained in advance to be in a convergence state and is used for judging the similarity of the image;
and the fourth execution sub-module is used for confirming whether the target terminal is virtual verification according to the judging result output by the verification judging model.
Optionally, the character verification device further includes:
the second acquisition sub-module is used for acquiring verification information uploaded by the target terminal, wherein the verification information comprises target characters which are screened by a user from the verification characters according to the verification statement and used for verification;
a fifth processing sub-module, configured to compare a target character with the semantic character, so as to determine whether the target character is consistent with the semantic character;
and the fifth execution sub-module is used for confirming that the target terminal passes verification when the target character is consistent with the semantic character.
Optionally, the character verification device further includes:
a first computing sub-module for computing a hamming distance between the target character and the semantic character;
a sixth execution sub-module, configured to confirm that the target character is consistent with the semantic character when the hamming distance is zero; otherwise, confirming that the target character is inconsistent with the semantic character.
To solve the above technical problem, an embodiment of the present invention further provides a computer device, including a memory and a processor, where the memory stores computer readable instructions, and when the computer readable instructions are executed by the processor, the processor is caused to execute the steps of the character verification method.
To solve the above technical problem, the embodiments of the present invention further provide a storage medium storing computer readable instructions, where the computer readable instructions when executed by one or more processors cause the one or more processors to perform the steps of the character verification method described above.
The embodiment of the invention has the beneficial effects that: the server side simultaneously sends verification sentences and verification characters to the target terminal during verification, and a user can select correct characters from the verification characters to finish verification only after correctly understanding semantic prompts of the verification sentences. Therefore, the image recognition technology can select and verify in the verification character only after understanding the semantics of the verification statement, so that the defect that the direct input type verification mode is easily cracked by the image recognition technology is avoided, the verification safety is improved, and the network resource is protected from being safely used.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a basic flow diagram of a character verification method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of generating verification characters according to semantic recognition according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of transforming verification characters according to verification sentences according to an embodiment of the present invention;
FIG. 4 is a flow chart of generating a verification image by image conversion according to an embodiment of the present invention;
fig. 5 is a schematic flow chart of performing display verification on a target terminal repeatedly verified in an embodiment of the present invention;
FIG. 6 is a flow chart of a verification result judgment by a target character and a semantic character according to an embodiment of the present invention;
FIG. 7 is a flow chart of determining whether a target character is consistent with a semantic character according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of a basic structure of a character verification device according to an embodiment of the present invention;
Fig. 9 is a basic structural block diagram of a computer device according to an embodiment of the present invention.
Detailed Description
In order to enable those skilled in the art to better understand the present invention, the following description will make clear and complete descriptions of the technical solutions according to the embodiments of the present invention with reference to the accompanying drawings.
In some of the flows described in the specification and claims of the present invention and in the foregoing figures, a plurality of operations occurring in a particular order are included, but it should be understood that the operations may be performed out of order or performed in parallel, with the order of operations such as 101, 102, etc., being merely used to distinguish between the various operations, the order of the operations themselves not representing any order of execution. In addition, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first" and "second" herein are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, and are not limited to the "first" and the "second" being different types.
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
As used herein, a "terminal" includes both a device of a wireless signal receiver having no transmitting capability and a device of receiving and transmitting hardware having receiving and transmitting hardware capable of performing bi-directional communications over a bi-directional communication link, as will be appreciated by those skilled in the art. Such a device may include: a cellular or other communication device having a single-line display or a multi-line display or a cellular or other communication device without a multi-line display; a PCS (Personal Communications Service, personal communication system) that may combine voice, data processing, facsimile and/or data communication capabilities; a PDA (Personal Digital Assistant ) that can include a radio frequency receiver, pager, internet/intranet access, web browser, notepad, calendar and/or GPS (Global Positioning System ) receiver; a conventional laptop and/or palmtop computer or other appliance that has and/or includes a radio frequency receiver. As used herein, "terminal," "terminal device" may be portable, transportable, installed in a vehicle (aeronautical, maritime, and/or land-based), or adapted and/or configured to operate locally and/or in a distributed fashion, to operate at any other location(s) on earth and/or in space. The "terminal" and "terminal device" used herein may also be a communication terminal, a network access terminal, and a music/video playing terminal, for example, may be a PDA, a MID (Mobile Internet Device ), and/or a mobile phone with a music/video playing function, and may also be a smart tv, a set top box, and other devices.
Referring to fig. 1 specifically, fig. 1 is a basic flow chart of the character verification method according to the present embodiment.
As shown in fig. 1, a character verification method includes:
s1100, receiving a verification request sent by a target terminal;
when a user operates the target terminal to enter the application program or starts a certain functional module of the application program, the user instruction triggers a corresponding verification function. For example, user actions such as application login, online purchase of various tickets, or submitting an order by an e-commerce platform trigger a user verification function.
After the verification function is triggered, the target terminal sends a verification request to the corresponding server side, and the verification request is used for acquiring verification data for verification.
S1200, randomly extracting verification sentences in a preset sentence database according to the verification request, wherein the verification sentences are used for verification prompt;
in this embodiment, the information for verification sent by the server side to the target terminal includes a background image, a verification sentence, and a verification character, where the verification sentence and the verification character are set on the background image.
The server side is provided with a statement database, and a plurality of verification statements are preset in the statement database. The verification statement is extracted from the statement database by means of random extraction or sequence extraction.
The validation statement is a literal field that prompts the user to select the correct character for validation, e.g., validation statement is (but not limited to): the prompt sentence is selected by selecting the characters beside the 'female' character in the following characters, selecting the characters with the character sizes larger than the conventional character sizes in the following characters, selecting the characters with distorted characters in the following characters or selecting the words expressing the 'happy emotion' in the following characters. The verification sentence has the function of prompting the user to select the correct character for verification, and the user can select the correct character from verification characters for verification only after understanding the verification sentence, so that the text field can be used as the verification sentence as long as the verification character has a prompting meaning expression and has a character with a mapping relation with the prompting meaning expression.
S1300, recognizing the semantics of the verification statement and generating verification characters according to a verification mode characterized by the semantics of the verification statement, wherein at least one character in the verification characters has a mapping relation with the verification mode;
after the verification statement is obtained through random extraction, the verification mode characterized by the text field recorded by the verification statement is identified. The recognition mode is that a neural network model capable of recognizing the semantics is trained according to deep learning, and then the neural network model is adopted to recognize the semantics of the verification statement.
In this embodiment, the verification method of the verification statement characterization can be divided into: the selection of characters is based on pronunciation, on structure, on font style, or on word sense. For example, the verification style of the verification statement token of "select a character whose initial consonant is y among the following characters" is to select a character according to pronunciation; the verification mode of the verification statement characterization of the character beside the female character in the following characters is to select the characters according to the structure; the verification mode of the verification statement characterization of "please select the font distortion in the following characters" is to select the characters according to the font form; the verification method of the verification statement token of "please select the word expressing happiness in the following words" selects the word according to the word sense.
And extracting corresponding verification characters from a preset character database according to the verification mode of the verification statement characterization, wherein at least one character in the extracted verification characters is mapped with the verification statement. For example, the validation statement is: "select the following characters with" female "next to the characters", verify the characters as: "Fu", "high", "rate", "Zhen".
The verification character is a text field which is formed by a plurality of text characters and carries correct characters, the text characters can be mutually independent without forming specific words, but the forming mode of the verification character is not limited to the specific word, and according to different specific application scenes, in some embodiments, the verification character is formed by a plurality of words. The verification characters comprise regular characters and characters with mapping relation with verification sentences. The user selects the characters with the mapping relation with the verification statement and the correct characters, so that character verification can be completed, otherwise, character verification cannot be completed.
S1400, the verification statement and the verification character are sent to the target terminal.
And sending the generated verification statement and verification characters to the target terminal so as to enable the target terminal to perform character verification.
In some embodiments, the verification data sent by the server to the target terminal further includes: and setting the verification characters and the verification sentences on the background image, synthesizing a verification picture, and then sending the verification picture to the target terminal for verification.
In the above embodiment, the server side simultaneously transmits the verification sentence and the verification character to the target terminal during verification, and the user can select the correct character from the verification characters to complete verification only after correctly understanding the semantic prompt of the verification sentence. Therefore, the image recognition technology can select and verify in the verification character only after understanding the semantics of the verification statement, so that the defect that the direct input type verification mode is easily cracked by the image recognition technology is avoided, the verification safety is improved, and the network resource is protected from being safely used.
Further, referring to fig. 2, in an alternative embodiment, step S1300 shown in fig. 1 includes:
S1311, calling the verification statement and reading a text field in the verification statement;
the verification statement is a text field with specific semantics composed of characters, and the text field of the verification statement is read first when the verification statement is subjected to character verification.
S1312, converting the text field into a plurality of matrixes according to a preset conversion mode;
after the literal field is read, the literal field is converted to a array matrix by the matlab software application. Wherein each word or word constituting the text field is mapped to be replaced with one element of the array matrix, and the arrangement order of the elements is identical to the arrangement order of the text fields.
S1313, inputting the data matrix into a preset semantic recognition model, wherein the semantic recognition model is a neural network model which is trained to a convergence state in advance and used for carrying out semantic recognition on characters;
detecting the semantics of the verification statement is performed through a semantic recognition model. The semantic recognition model is a neural network model trained to a convergence state for classifying semantics expressed by the verification statement. Specifically, the verification statement to be detected is converted into an array matrix which can be identified by the neural network model through matlab software, and then the array matrix is input into the semantic identification model to obtain a classification result which is output by the model and expresses the semantics of the verification statement.
In the present embodiment, the semantic recognition model may be a convolutional neural network model (CNN) that has been trained to a converged state, but the semantic recognition model is not limited thereto and may be: a deep neural network model (DNN), a recurrent neural network model (RNN), or a variant of the three network models.
When the initial neural network model serving as the semantic recognition model is trained, a large number of array matrixes converted by the verification sentences are collected to serve as training samples, and each training sample is calibrated after the original verification sentences of the training sample are read manually (calibration refers to the real expressed semantics of the training sample). And inputting a training sample into an initial neural network model, acquiring a classification result (the classification result is the semantic classification of the training sample obtained by the model), calculating the distance between the classification result and a calibration result (such as Euclidean distance, mahalanobis distance or cosine distance) through a loss function of the neural network model, comparing the calculation result with a set distance threshold, if the calculation result is smaller than or equal to the distance threshold (such as 0.05), continuing to train the next training sample, if the calculation result is larger than the distance threshold, calculating the difference between the calculation result and the training result through the loss function, and correcting the weight in the neural network model through back propagation, so that the neural network model can improve the weight of the element corresponding to the word capable of accurately expressing text semantics in the training sample, and the judgment accuracy is increased. After the above scheme and a large number of training samples are circularly executed for training, the semantic judgment accuracy of the neural network model obtained by training on the array matrix characterization is greater than a certain value, for example, 97%, the neural network model is trained to a convergence state, and the neural network trained to convergence is the semantic recognition model.
The semantic recognition model trained to the convergence state can accurately extract the semantic represented by the array matrix.
S1314, extracting the verification characters from a preset character database according to a verification mode of semantic classification result representation output by the semantic recognition model.
And extracting verification characters with the first character length from the character database according to the semantic classification result output by the semantic recognition model.
For example, when the validation statement is: please select the characters with the sequence numbers of the fourth bit and the sixth bit in the following text. At this time, the semantic classification result output by the semantic recognition model is: "verify based on character number, the largest character needs to be the sixth bit". Then the verification characters of six characters or more are extracted from the verification word stock.
When the verification statement is: when the character beside the female character is selected from the following characters, the semantic classification result output by the semantic recognition model is: "verify based on radicals, verify that radicals are female". At least one character is extracted from the character database as a verification character next to the female character.
When the verification statement is: when selecting sentences such as characters subjected to font thickening processing in the following characters, the semantic classification result output by the semantic recognition model is: "verify according to the font, verify the font as thickening".
The verification sentence is subjected to semantic recognition through the neural network model, so that the terminal can correspondingly generate verification characters according to the semantic recognition result, the efficiency and accuracy of verification character generation are improved, and the verification efficiency is further improved.
In some embodiments, the verification of the verification statement characterization is performed in the following manner: since verification is performed according to the font style, when generating verification characters, it is necessary to deform part of the characters with respect to the semantics of the verification sentence.
Further, referring to fig. 3, in an alternative embodiment, after step S1314 shown in fig. 2, the method further includes:
s1321, at least one deformation character is selected from the verification characters;
when the verification mode represented by the verification statement is that characters are selected through the fonts for verification, at least one deformation character is selected from the verification characters after the characters forming the verification characters are obtained. In this embodiment, the number of characters selected as the deformed characters in the verification characters is not limited to 1, and according to different specific application scenarios, in some embodiments, the number of deformed characters can be more until all characters in the verification characters are deformed characters.
S1322, performing deformation processing on the at least one deformation character according to the deformation type characterized by the verification mode to generate a semantic character, wherein the semantic character and the verification statement have a mapping relation;
And according to the semantic classification result obtained by judging the semantic recognition model, the characterized deformation type carries out deformation processing on at least one deformation character to generate semantic characters.
The deformation types in this embodiment include (but are not limited to): the character is enlarged, reduced, thickened, tilted, rotated, distorted or discolored.
The character generated after the deformation processing is defined as a semantic character, and a mapping relation exists between the semantic character and the verification statement, namely, the phonetic character is a standard answer of character verification.
S1323, replacing the deformed character in the verification character with the semantic character.
And replacing the deformed character in the verification character with the generated semantic character, namely writing the correct answer to be verified into the verification character, and finishing the deformation processing of the verification character. And simultaneously, storing the semantic characters, wherein the semantic characters are used as correct answers of verification sentences for verification comparison.
Through the character deformation processing, the character verification result is more outstanding, the selection of a user is facilitated, and meanwhile, the character shape change is not easy to identify by an image recognition technology, so that the character verification safety is improved.
In some embodiments, the validation characters and validation statements need to be displayed in a picture format. Therefore, it is necessary to perform imaging processing on the verification character and the verification sentence.
Further, referring to fig. 4, in an alternative embodiment, step S1400 shown in fig. 1 includes:
s1411, screening background images from a preset image database;
in this embodiment, the server side is provided with an image database, in which various kinds of pictures are prestored, and the pictures stored in the image database can be used for character verification.
After the semantic characters replace the deformed characters, a picture is extracted in an image database in a random screening mode to serve as a background image. However, the screening method is not limited to this, and in some embodiments, when the background image is screened, the background image with the color difference value between the font color of the verification character equal to 2 or 3 needs to be screened, so as to increase the fusion degree between the verification character and the background image, make the image recognition technology difficult to recognize the verification character, and improve the difficulty of machine recognition.
S1412, overlaying the verification statement and the verification character on the background image to generate a verification image, wherein the verification character comprises the semantic character;
and setting the verification statement and the verification character on the background image, wherein the verification statement and the verification character are set on top when the image level is set, so that the verification statement and the verification character are covered on the background image. And generating a verification image carrying the verification sentence and the verification character after the setting is completed.
S1413, the verification image is sent to the target terminal.
The verification image is transmitted to the target terminal after being generated so that the target terminal can use the verification image for character verification.
The verification characters and the verification sentences are arranged in the background image, so that the confusion degree between the verification sentences and the verification characters and the background can be increased, and the recognition difficulty is increased.
In some embodiments, in order to prevent the same terminal from passing through the virtual verification, the verification system is quickly swiped, the server records the verification records of each target terminal, and checks the behavior of the virtual swipe according to the verification records. Referring to fig. 5, fig. 5 is a schematic flow chart of performing display verification on a target terminal repeatedly verified in this embodiment.
Further, referring to fig. 5, in an alternative embodiment, after step S1413 shown in fig. 4, the method further includes:
s1421, searching a verification record of the target terminal in a history verification list;
in this embodiment, each record of verification performed by the target terminal at the server side is recorded in the history verification list, and the recording manner is as follows: the identity information of the target terminal, for example, the IP address or Mac address of the target terminal is recorded. And then recording each verification request of the target terminal below the identity information of the corresponding target terminal in the history verification list. Therefore, as long as the identity information of the target terminal in the verification request is obtained, the corresponding verification record can be found in the history verification list.
S1422, when the verification record of the target terminal accords with a preset first verification condition, calling a screenshot picture of the verification image in a verification page to the target terminal;
the verification record records the verification frequency of the target terminal in a set time period, for example, the target terminal is verified 100 times in one hour. The length of the time period for counting the verification frequency in the verification record can be adjusted according to different specific application scenes.
When detecting whether the frequency of the target terminal in the set time period accords with the set first verification condition, wherein the first verification condition refers to the value of the verification frequency in the set time period. For example, the number of times the target terminal performs authentication must not exceed 10 times within 1 hour of the setting, but the frequency value of the setting of the first authentication condition is not limited thereto, and can be increased or decreased adaptively according to the scene needs depending on the specific application scene.
When the verification frequency of the target terminal in the set time period is greater than or equal to the verification frequency set by the first verification condition, the server side sends a call request to the target terminal, and the target terminal is called to display a screenshot picture of a verification image in a verification page so as to identify whether a user uses a virtual verification mode to verify.
When the target terminal displays the verification image, the verification page including the verification image needs to be stored in the frame buffer memory, that is, the frame buffer memory is a direct image of the picture displayed by the screen, which is also called a Bit Map (Bit Map), that is, display data.
Because the verification image has the set area in the bitmap, the data area representing the content of the verification area is extracted from the bitmap according to the information of the set area to generate a local bitmap, namely the target data representing the display content of the verification image.
Finally, the target data is converted into a conventional picture format, such as (but not limited to) JPG, PNG or TIF, and the like, so as to generate a verification image.
In some embodiments, when the verification image is not available in the frame buffer memory, the verification mode is indicated as virtual verification.
When the verification frequency of the target terminal in the set time period is smaller than the verification frequency set by the first verification condition, a screenshot picture is not required to be called to the target terminal.
S1423, inputting the screenshot picture and the verification image into a preset verification judgment model, wherein the verification judgment model is a neural network model which is trained in advance to be in a convergence state and is used for judging the similarity of the images;
And inputting the screenshot picture and the verification image into a preset verification judgment model, wherein the verification judgment model is a neural network model which is trained in advance to a convergence state and is used for judging the similarity of the image.
In the present embodiment, the verification judgment model may be a convolutional neural network model (CNN) that has been trained to a converged state, but the verification judgment model is not limited thereto and may be: a deep neural network model (DNN), a recurrent neural network model (RNN), or a variant of the three network models.
The verification judgment model is a neural network model in a convergent form, so that whether the verification images are identical or not can be accurately and rapidly judged.
S1424, confirming whether the target terminal is virtual verification according to the judgment result output by the verification judgment model.
And in the judging result output by the verification judging model, a judging conclusion that whether the screenshot picture and the verification image are the same or not is recorded in the verification judging model. When the screenshot picture is the same as the verification image, confirming that the verification of the target terminal is non-virtual verification; otherwise, judging that the target terminal performs virtual verification, and prohibiting responding to the request of the target terminal for accessing the server side.
The server side judges whether the verification image and the screenshot picture are the same or not, so that a virtual verifier can be prevented from randomly writing image data into the frame buffer memory by means of fraud to avoid detection, the verification accuracy is improved, and the safety of network data is further ensured.
In some embodiments, the server side obtains the target character for verification selected by the user and uploaded by the target terminal, and judges the verification result according to whether the target character is consistent with the semantic character.
Further, referring to fig. 6, in an alternative embodiment, after step S1400 shown in fig. 1, the method further includes:
s1431, acquiring verification information uploaded by the target terminal, wherein the verification information comprises target characters which are screened by a user from the verification characters according to the verification statement and used for verification;
after sending the verification statement and the verification character to the target terminal, the server waits for receiving verification information uploaded by the target terminal, wherein the verification information comprises the target character.
The target characters are selected from verification characters according to a click instruction of a user, wherein the characters in the target characters possibly have mapping relations with verification sentences; it is possible that only individual characters or no characters have a mapping relation with the verification statement. When the characters in the target characters have mapping relations with the verification sentences, the verification passes; otherwise, the verification fails.
S1432, comparing the target character with the semantic character to judge whether the target character is consistent with the semantic character;
the server compares the target character with the semantic character in a way of calculating the hamming distance or the hamming distance between the target character and the semantic character. When the Hamming distance or the Hamming distance between the target character and the semantic character is zero, the target character is consistent with the semantic character; otherwise, the target character is inconsistent with the semantic character.
S1433, when the target character is consistent with the semantic character, confirming that the target terminal passes verification.
When the target character is consistent with the semantic character, the server confirms that the target terminal character passes verification; otherwise, confirming that the verification of the target terminal fails.
In some implementations, whether the target character is consistent with the phonetic character is determined by calculating a hamming distance or a hamming distance between the target character and the semantic character.
Further, referring to fig. 7, in an alternative embodiment, step S1432 shown in fig. 6 includes:
s1441, calculating a hamming distance between the target character and the semantic character;
the hamming distance between the target character and the semantic character is calculated as the number of different bits corresponding to the two fields (same length), for example, the hamming distance between "connected" and "references" is 3.
S1442, when the Hamming distance is zero, confirming that the target character is consistent with the semantic character; otherwise, confirming that the target character is inconsistent with the semantic character.
When the hamming distance between the target character and the semantic character is zero, the target character is consistent with the semantic character; otherwise, the target character is inconsistent with the semantic character.
The target character and the semantic character can be rapidly compared through the Hamming distance, so that the comparison efficiency is improved, and the verification efficiency of the server side is further improved.
In order to solve the technical problems, the embodiment of the invention also provides a character verification device.
Referring to fig. 8, fig. 8 is a schematic diagram illustrating a basic structure of a character verification apparatus according to the present embodiment.
As shown in fig. 8, a character verification apparatus includes: the device comprises an acquisition module 2100, a processing module 2200, an identification module 2300 and an execution module 2400. The acquiring module 2100 is configured to receive a verification request sent by a target terminal; the processing module 2200 is configured to extract a verification sentence from a preset sentence database according to a verification request, where the verification sentence is used for verifying a prompt; the identification module 2300 is used for identifying the verification statement and generating verification characters according to a verification mode characterized by the semantics of the verification statement, wherein at least one character in the verification characters has a mapping relation with the verification mode; the execution module 2400 is configured to send the verification sentence and the verification character to the target terminal.
The character verification device simultaneously sends verification sentences and verification characters to the target terminal during verification, and a user can select correct characters from the verification characters to finish verification only after correctly understanding semantic prompts of the verification sentences. Therefore, the image recognition technology can select and verify in the verification character only after understanding the semantics of the verification statement, so that the defect that the direct input type verification mode is easily cracked by the image recognition technology is avoided, the verification safety is improved, and the network resource is protected from being safely used.
In some embodiments, the character verification apparatus further comprises: the device comprises a first acquisition sub-module, a first processing sub-module, a first identification sub-module and a first execution sub-module. The first acquisition sub-module is used for acquiring a text field of the verification statement; the first processing sub-module is used for converting the text field into an array matrix according to a preset conversion mode; the first recognition submodule is used for inputting the data matrix into a preset semantic recognition model, wherein the semantic recognition model is a neural network model which is trained to a convergence state in advance and used for carrying out semantic recognition on characters; the first execution submodule is used for extracting verification characters from a preset character database according to a verification mode of semantic classification result representation output by the semantic recognition model.
In some embodiments, the verification mode is font verification, and the character verification device further includes: the system comprises a first screening sub-module, a second processing sub-module and a second executing sub-module. The first screening submodule is used for screening at least one deformation character from the verification characters; the second processing sub-module is used for carrying out deformation processing on at least one deformation character according to the deformation type represented by the verification mode to generate a semantic character, wherein the semantic character has a mapping relation with the verification statement; the second execution submodule is used for replacing deformed characters in the verification characters with semantic characters.
In some embodiments, the character verification apparatus further comprises: the system comprises a second screening sub-module, a third processing sub-module and a third executing sub-module. The second screening sub-module is used for screening background images from a preset image database; the third processing sub-module is used for overlaying the verification statement and the verification character on the background image to generate a verification image, wherein the verification character comprises a semantic character; the third execution submodule is used for sending the verification image to the target terminal.
In some embodiments, the character verification apparatus further comprises: the system comprises a first searching sub-module, a fourth processing sub-module, a first input sub-module and a fourth executing sub-module. The first searching sub-module is used for searching the verification record of the target terminal in the history verification list; the fourth processing sub-module is used for calling a screenshot picture of the verification image in the verification page to the target terminal when the verification record of the target terminal accords with a preset first verification condition; the first input submodule is used for inputting the screenshot picture and the verification image into a preset verification judgment model, wherein the verification judgment model is a neural network model which is trained in advance to be in a convergence state and is used for judging the similarity of the image; and the fourth execution submodule is used for confirming whether the target terminal is virtual verification according to the judging result output by the verification judging model.
In some embodiments, the character verification apparatus further comprises: the system comprises a second acquisition sub-module, a fifth processing sub-module and a fifth execution sub-module. The second acquisition sub-module is used for acquiring verification information uploaded by the target terminal, wherein the verification information comprises target characters which are screened from verification characters by a user according to verification sentences and used for verification; the fifth processing submodule is used for comparing the target character with the semantic character to judge whether the target character is consistent with the semantic character or not; and the fifth execution submodule is used for confirming that the target terminal passes the verification when the target character is consistent with the semantic character.
In some embodiments, the character verification apparatus further comprises: a first computing sub-module and a sixth execution sub-module. The first calculation submodule is used for calculating the hamming distance between the target character and the semantic character; the sixth execution submodule is used for confirming that the target character is consistent with the semantic character when the Hamming distance is zero; otherwise, confirming that the target character is inconsistent with the semantic character.
In order to solve the technical problems, the embodiment of the invention also provides computer equipment. Referring specifically to fig. 9, fig. 9 is a basic structural block diagram of a computer device according to the present embodiment.
As shown in fig. 9, the internal structure of the computer device is schematically shown. The computer device includes a processor, a non-volatile storage medium, a memory, and a network interface connected by a system bus. The nonvolatile storage medium of the computer device stores an operating system, a database and computer readable instructions, the database can store a control information sequence, and the computer readable instructions can enable the processor to realize a character verification method when the computer readable instructions are executed by the processor. The processor of the computer device is used to provide computing and control capabilities, supporting the operation of the entire computer device. The memory of the computer device may have stored therein computer readable instructions that, when executed by the processor, cause the processor to perform a character verification method. The network interface of the computer device is for communicating with a terminal connection. It will be appreciated by those skilled in the art that the structure shown in fig. 9 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application applies, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
The processor in this embodiment is configured to perform specific functions of the acquisition module 2100, the processing module 2200, the identification module 2300, and the execution module 2400 in fig. 8, and the memory stores program codes and various types of data required for executing the above modules. The network interface is used for data transmission between the user terminal or the server. The memory in this embodiment stores program codes and data required for executing all the sub-modules in the face image key point detection device, and the server can call the program codes and data of the server to execute the functions of all the sub-modules.
The computer equipment simultaneously sends the verification statement and the verification character to the target terminal during verification, and a user can select the correct character from the verification characters to finish verification only after correctly understanding the semantic prompt of the verification statement. Therefore, the image recognition technology can select and verify in the verification character only after understanding the semantics of the verification statement, so that the defect that the direct input type verification mode is easily cracked by the image recognition technology is avoided, the verification safety is improved, and the network resource is protected from being safely used.
The invention also provides a storage medium storing computer readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of any of the character verification methods of the embodiments described above.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored in a computer-readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
Claims (9)
1. A character verification method, comprising:
receiving a verification request sent by a target terminal;
randomly extracting verification sentences in a preset sentence database according to the verification request, wherein the verification sentences are used for verification prompts;
identifying the semantics of the verification statement, and extracting verification characters from a preset character database according to a verification mode characterized by the semantics of the verification statement, wherein at least one character in the verification characters has a mapping relation with the verification mode;
transmitting the verification statement and the verification character to the target terminal;
the step of identifying the semantics of the verification statement and extracting verification characters from a preset character database according to the verification mode characterized by the semantics of the verification statement comprises the following steps:
invoking the verification statement and reading a text field in the verification statement;
converting the text field into a plurality of matrixes according to a preset conversion mode;
inputting the data matrix into a preset semantic recognition model, wherein the semantic recognition model is a neural network model which is trained in advance to a convergence state and used for carrying out semantic recognition on characters;
And extracting the verification characters from a preset character database according to a verification mode of the semantic classification result representation output by the semantic recognition model.
2. The character verification method according to claim 1, wherein the verification mode is a font verification mode, and the verification mode represented by the semantic classification result output according to the semantic recognition model is after extracting the verification character from a preset character database, the method further comprises:
screening at least one deformation character from the verification characters;
performing deformation processing on the at least one deformation character according to the deformation type characterized by the verification mode to generate a semantic character, wherein the semantic character and the verification statement have a mapping relation;
and replacing the deformed character in the verification character with the semantic character.
3. The character verification method according to claim 2, wherein the transmitting the verification sentence and the verification character to the target terminal includes:
screening background images from a preset image database;
overlaying the verification sentence and the verification character on the background image to generate a verification image, wherein the verification character comprises the semantic character;
And sending the verification image to the target terminal.
4. A character verification method according to claim 3, wherein after said transmitting the verification image to the target terminal, the method further comprises:
searching a verification record of the target terminal in a history verification list;
when the verification record of the target terminal accords with a preset first verification condition, invoking a screenshot picture of the verification image in a verification page to the target terminal;
inputting the screenshot picture and the verification image into a preset verification judgment model, wherein the verification judgment model is a neural network model which is trained in advance to a convergence state and is used for judging the similarity of the image;
and confirming whether the target terminal is virtual verification or not according to a judging result output by the verification judging model.
5. The character verification method according to claim 2, wherein after the verification sentence and the verification character are transmitted to the target terminal, the method further comprises:
acquiring verification information uploaded by the target terminal, wherein the verification information comprises target characters which are screened by a user from the verification characters according to the verification statement and used for verification;
Comparing the target character with the semantic character to judge whether the target character is consistent with the semantic character;
and when the target character is consistent with the semantic character, confirming that the target terminal passes verification.
6. The character verification method according to claim 5, wherein the comparing the target character with the semantic character to determine whether the target character is consistent with the semantic character comprises:
calculating the hamming distance between the target character and the semantic character;
when the Hamming distance is zero, confirming that the target character is consistent with the semantic character; otherwise, confirming that the target character is inconsistent with the semantic character.
7. A character verification apparatus, comprising:
the acquisition module is used for receiving a verification request sent by the target terminal;
the processing module is used for randomly extracting verification sentences in a preset sentence database according to the verification request, wherein the verification sentences are used for verification prompts;
the recognition module is used for recognizing the semantics of the verification statement and extracting verification characters from a preset character database according to a verification mode characterized by the semantics of the verification statement, wherein at least one character in the verification characters has a mapping relation with the verification mode;
The execution module is used for sending the verification statement and the verification character to the target terminal;
the step of identifying the semantics of the verification statement and extracting verification characters from a preset character database according to the verification mode characterized by the semantics of the verification statement comprises the following steps:
invoking the verification statement and reading a text field in the verification statement;
converting the text field into a plurality of matrixes according to a preset conversion mode;
inputting the data matrix into a preset semantic recognition model, wherein the semantic recognition model is a neural network model which is trained in advance to a convergence state and used for carrying out semantic recognition on characters;
and extracting the verification characters from a preset character database according to a verification mode of the semantic classification result representation output by the semantic recognition model.
8. A computer device comprising a memory and a processor, the memory having stored therein computer readable instructions that, when executed by the processor, cause the processor to perform the steps of the character verification method of any one of claims 1 to 6.
9. A storage medium storing computer readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of the character validation method of any one of claims 1 to 6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910601303.1A CN110351094B (en) | 2019-07-03 | 2019-07-03 | Character verification method, device, computer equipment and storage medium |
| PCT/CN2019/103061 WO2021000407A1 (en) | 2019-07-03 | 2019-08-28 | Character verification method and apparatus, and computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910601303.1A CN110351094B (en) | 2019-07-03 | 2019-07-03 | Character verification method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110351094A CN110351094A (en) | 2019-10-18 |
| CN110351094B true CN110351094B (en) | 2024-03-15 |
Family
ID=68177523
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910601303.1A Active CN110351094B (en) | 2019-07-03 | 2019-07-03 | Character verification method, device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110351094B (en) |
| WO (1) | WO2021000407A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112699348A (en) * | 2020-12-25 | 2021-04-23 | 中国平安人寿保险股份有限公司 | Method and device for verifying nuclear body information, computer equipment and storage medium |
| CN114726595B (en) * | 2022-03-24 | 2023-09-29 | 中科吉芯(昆山)信息科技有限公司 | Method for authenticating identity of man-machine by using space-time information |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101923702A (en) * | 2010-08-25 | 2010-12-22 | 郝红卫 | Image valid code generating method |
| CN102006163A (en) * | 2009-09-01 | 2011-04-06 | 阿里巴巴集团控股有限公司 | User authentication method, device and server |
| CN102710607A (en) * | 2012-05-10 | 2012-10-03 | 北京像素软件科技股份有限公司 | Security verification method based on graphic marker |
| CN104852885A (en) * | 2014-02-14 | 2015-08-19 | 腾讯科技（深圳）有限公司 | Method, device and system for verifying verification code |
| CN104915664A (en) * | 2015-05-22 | 2015-09-16 | 腾讯科技（深圳）有限公司 | Contact object identification acquisition method and device |
| CN106330439A (en) * | 2016-10-25 | 2017-01-11 | 先锋智道（北京）科技有限公司 | Verification code generating method, generating device and generating system |
| CN106572049A (en) * | 2015-10-09 | 2017-04-19 | 腾讯科技（深圳）有限公司 | Identity verifying apparatus and method |
| CN107360137A (en) * | 2017-06-15 | 2017-11-17 | 深圳市牛鼎丰科技有限公司 | Construction method and device for the neural network model of identifying code identification |
| CN109033798A (en) * | 2018-09-14 | 2018-12-18 | 北京金堤科技有限公司 | One kind is semantic-based to click method for recognizing verification code and its device |
| CN109272043A (en) * | 2018-09-21 | 2019-01-25 | 北京京东金融科技控股有限公司 | Training data generation method, system and electronic equipment for optical character identification |
| CN109284584A (en) * | 2017-07-21 | 2019-01-29 | 北京京东尚科信息技术有限公司 | Verification method and device |
| CN109858542A (en) * | 2019-01-25 | 2019-06-07 | 广州云测信息技术有限公司 | A kind of character identifying method and device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101197678B (en) * | 2007-12-27 | 2011-04-06 | 腾讯科技（深圳）有限公司 | Picture identifying code generation method and generation device |
| CN103701600A (en) * | 2013-12-13 | 2014-04-02 | 百度在线网络技术（北京）有限公司 | Input validation method and device |
| CN108154148A (en) * | 2018-01-22 | 2018-06-12 | 厦门美亚商鼎信息科技有限公司 | The artificial synthesis of training sample and the method for recognizing verification code based on the sample |
-
2019
- 2019-07-03 CN CN201910601303.1A patent/CN110351094B/en active Active
- 2019-08-28 WO PCT/CN2019/103061 patent/WO2021000407A1/en active Application Filing
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102006163A (en) * | 2009-09-01 | 2011-04-06 | 阿里巴巴集团控股有限公司 | User authentication method, device and server |
| CN101923702A (en) * | 2010-08-25 | 2010-12-22 | 郝红卫 | Image valid code generating method |
| CN102710607A (en) * | 2012-05-10 | 2012-10-03 | 北京像素软件科技股份有限公司 | Security verification method based on graphic marker |
| CN104852885A (en) * | 2014-02-14 | 2015-08-19 | 腾讯科技（深圳）有限公司 | Method, device and system for verifying verification code |
| CN104915664A (en) * | 2015-05-22 | 2015-09-16 | 腾讯科技（深圳）有限公司 | Contact object identification acquisition method and device |
| CN106572049A (en) * | 2015-10-09 | 2017-04-19 | 腾讯科技（深圳）有限公司 | Identity verifying apparatus and method |
| CN106330439A (en) * | 2016-10-25 | 2017-01-11 | 先锋智道（北京）科技有限公司 | Verification code generating method, generating device and generating system |
| CN107360137A (en) * | 2017-06-15 | 2017-11-17 | 深圳市牛鼎丰科技有限公司 | Construction method and device for the neural network model of identifying code identification |
| CN109284584A (en) * | 2017-07-21 | 2019-01-29 | 北京京东尚科信息技术有限公司 | Verification method and device |
| CN109033798A (en) * | 2018-09-14 | 2018-12-18 | 北京金堤科技有限公司 | One kind is semantic-based to click method for recognizing verification code and its device |
| CN109272043A (en) * | 2018-09-21 | 2019-01-25 | 北京京东金融科技控股有限公司 | Training data generation method, system and electronic equipment for optical character identification |
| CN109858542A (en) * | 2019-01-25 | 2019-06-07 | 广州云测信息技术有限公司 | A kind of character identifying method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021000407A1 (en) | 2021-01-07 |
| CN110351094A (en) | 2019-10-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP4195102A1 (en) | Image recognition method and apparatus, computing device and computer-readable storage medium | |
| EP3961441B1 (en) | Identity verification method and apparatus, computer device and storage medium | |
| RU2661750C1 (en) | Symbols recognition with the use of artificial intelligence | |
| CN109902285B (en) | Corpus classification method, corpus classification device, computer equipment and storage medium | |
| CN111667066A (en) | Network model training and character recognition method and device and electronic equipment | |
| CN109389098B (en) | Verification method and system based on lip language identification | |
| CN111612081B (en) | Training method, device, equipment and storage medium for recognition model | |
| CN109462603A (en) | Voiceprint authentication method, equipment, storage medium and device based on blind Detecting | |
| CN110351094B (en) | Character verification method, device, computer equipment and storage medium | |
| CN111684459A (en) | Identity authentication method, terminal equipment and storage medium | |
| CN114616565A (en) | Living body detection using audio-visual disparity | |
| CN113177435A (en) | Test paper analysis method and device, storage medium and electronic equipment | |
| CN114758327A (en) | Method, device and equipment for identifying risks in code image | |
| CN111241873A (en) | Image reproduction detection method, training method of model thereof, payment method and payment device | |
| CN116311214A (en) | License plate recognition method and device | |
| KR102351578B1 (en) | Apparatus and method for recognizing character | |
| CN111008624A (en) | Optical character recognition method and method for generating training sample for optical character recognition | |
| CN111507467A (en) | Neural network model training method and device, computer equipment and storage medium | |
| CN113850109A (en) | Video image alarm method based on attention mechanism and natural language processing | |
| EP4064095A1 (en) | Encoding, decoding and integrity validation systems for a security document with a steganography-encoded image and methods, security document, computing devices, computer programs and associated computer-readable data carrier | |
| CN114625872A (en) | Risk auditing method, system and equipment based on global pointer and storage medium | |
| CN113221718B (en) | Formula identification method, device, storage medium and electronic equipment | |
| CN111860212B (en) | Super-division method, device, equipment and storage medium for face image | |
| CN112990147A (en) | Method and device for identifying administrative-related images, electronic equipment and storage medium | |
| CN111738248A (en) | Character recognition method, training method of character decoding model and electronic equipment |
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 |