CN110858244B - Verification method, data processing method, computer equipment and storage medium - Google Patents
Verification method, data processing method, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110858244B CN110858244B CN201810887424.2A CN201810887424A CN110858244B CN 110858244 B CN110858244 B CN 110858244B CN 201810887424 A CN201810887424 A CN 201810887424A CN 110858244 B CN110858244 B CN 110858244B
- Authority
- CN
- China
- Prior art keywords
- verification
- answer
- reference image
- description information
- question
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/45—Structures or tools for the administration of authentication
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The embodiment of the application discloses a verification method and a verification device. The method comprises the following steps: the method comprises the steps of obtaining a reference image, generating description information of image content according to the reference image, determining verification questions and verification answers aiming at the reference image according to a grammar structure of the description information, verifying submitted answers aiming at the reference image and the verification questions based on the verification answers, automatically generating the verification questions and the verification answers aiming at the image through understanding and text analysis of the image content, analyzing correct verification answers according to the reference image and the verification questions without complex thinking of human beings, wherein for a machine, logic relations among the reference image, the verification questions and the verification answers are difficult to understand, so that the answers cannot be selected correctly, and the problem that human-computer verification is broken by the machine is avoided.
Description
Technical Field
The present application relates to the field of verification technologies, and in particular, to a verification method, a data processing method, a computer device, and a computer readable storage medium.
Background
Man-machine verification is a test method for automatically distinguishing computers from human beings. To prevent the occurrence of malicious operations such as automatically performed brute force password cracking, ticket swiping, etc., the current user may be authenticated to determine whether the current user is a computer or a human. In some man-machine verification technologies commonly seen at present, a terminal can stretch out a picture containing characters, a current user is required to input the characters in the picture in a designated input field, when the characters input by the current user are matched with the characters in the picture, the current user can be considered to be human, and verification is passed; alternatively, requiring the user to select a picture containing the object described in the question, i.e., deeming the current user to be a human, the verification is passed.
The applicant finds that the computer has the capability of picture recognition, can automatically recognize characters or objects in pictures, and further breaks the normal system safety through verification, so that the security risks of normal users and application operators are caused.
Disclosure of Invention
The present application has been made in view of the above problems, and has as its object to provide an authentication method, a data processing method, and a computer device, a computer-readable storage medium, which overcome or at least partially solve the above problems.
According to one aspect of the present application, there is provided a verification method comprising:
acquiring a reference image;
generating description information describing the reference image;
determining a verification question and a verification answer for the reference image according to the grammar structure of the description information;
and verifying the submitted answer aiming at the reference image and the verification question based on the verification answer.
Optionally, the determining the verification question and the verification answer for the reference image according to the syntax structure of the description information includes:
selecting a verification answer from the description information;
determining that a preset grammar structure containing the verification answer exists in the description information;
and removing part of the verification answer from the description information as a verification question.
Optionally, before removing the part of the verification answer from the description information as a verification question, the method further includes:
determining that a preset grammar structure containing the verification answer does not exist in the description information;
and re-selecting a verification answer from the description information, or re-acquiring a reference image.
Optionally, before removing the part of the verification answer from the description information as a verification question, the method further includes:
Verifying that a verification answer exists in the reference image;
and if the verification does not exist, the reference image is acquired again.
Optionally, the selecting a verification answer from the description information includes:
analyzing the description information to obtain a plurality of words;
and selecting at least one word as a verification answer according to the parts of speech of the plurality of words.
Optionally, before the verifying the submitted answer for the reference image and the verification question based on the verification answer, the method further comprises:
at least one candidate answer is generated for provision with the verification answer.
Optionally, the generating at least one candidate answer provided with the verification answer includes:
and selecting at least one candidate answer within a preset similarity range with the verification answer.
Optionally, the generating the description information describing the reference image includes:
a data set is generated based on the image description, and description information for the reference image is generated.
Optionally, the verifying that the reference image has a verification answer includes:
and identifying the reference image based on the image identification data set, and determining whether a verification answer exists in the identification result.
Optionally, the acquiring the reference image includes:
Selecting a reference image according to a man-machine verification request of a client;
the verifying the submitted answer for the reference image and the verification question based on the verification answer comprises:
and providing the reference image, the verification question, the verification answer and the candidate answer to the client for human-computer verification by the client.
Correspondingly, according to another aspect of the present application, there is also provided a data processing method, including:
acquiring a reference image and a grammar structure of the reference image;
determining a verification question and a verification answer for the reference image based on the grammar structure;
acquiring an answer to be processed;
and generating a verification result based on the verification answer and the answer to be processed.
Optionally, the grammar structure includes a grammar structure including a verification answer in description information describing the reference image.
Accordingly, according to another aspect of the present application, there is also provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a method as one or more of the above when executing the computer program.
Accordingly, in accordance with another aspect of the present application, there is also provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs a method as described above for one or more of the above.
According to the embodiment of the application, the reference image is acquired, the description information of the image content is generated according to the reference image, then the verification question and the verification answer for the reference image are determined according to the grammar structure of the description information, the submitted answer for the reference image and the verification question is verified based on the verification answer, so that the verification question and the verification answer for the image are automatically generated through understanding and text analysis of the image content, and the correct verification answer is analyzed according to the reference image and the verification question without complex thinking of human being, but for a machine, the logic relation among the reference image, the verification question and the verification answer is difficult to understand, so that the answer cannot be correctly selected, and the problem that the human-computer verification is cracked by the machine is avoided.
Further, when determining the verification question and the verification answer for the reference image according to the grammar structure of the description information, firstly selecting the verification answer from the description information, determining that the description information has a preset grammar structure containing the verification answer, and removing part of the verification answer from the description information as the verification question to determine that the verification answer semantically accords with human understanding, thereby obtaining the human-machine verification question for identifying human response.
Further, by identifying the reference image based on the image identification data set, whether a verification answer exists in the identification result is determined, and objects included in the reference image can be identified more accurately than the image description generation data set, so that the situation that the verification answer in the generated description information does not exist in the reference image due to misidentification of the image description generation data set is avoided.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 shows a picture for reference in a gallery;
FIG. 2 shows a schematic diagram of a verification process;
FIG. 3 shows a flow chart of an embodiment of a verification method according to a first embodiment of the application;
FIG. 4 is a flow chart of an embodiment of a verification method according to a second embodiment of the application;
FIG. 5 is a flow chart of an embodiment of a data processing method according to a third embodiment of the present application;
FIG. 6 shows a schematic diagram of a human-machine verification process;
fig. 7 is a block diagram showing an embodiment of a verification apparatus according to a fourth embodiment of the present application;
FIG. 8 is a block diagram showing an embodiment of a data processing apparatus according to a fifth embodiment of the present application;
FIG. 9 illustrates an exemplary system that may be used to implement various embodiments described in this disclosure.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
For a better understanding of the present application, the following description is given to illustrate the concepts related to the present application to those skilled in the art:
the reference image includes images in various forms such as pictures, moving pictures, videos, animations and the like, is used for providing the current user with observations to answer the human-machine verification questions related to the images during human-machine verification, and can specifically include any applicable form of image, and the embodiment of the application is not limited thereto.
The description information is used to describe the content of the reference image, and may specifically include text, audio, etc., for example, a picture for reference in the gallery shown in fig. 1 may be generated: a person sitting beside a table may play a guitar, or any other suitable form, as embodiments of the application are not limited in this regard. With the development of artificial intelligence, with the progress of deep neural network training and the availability of large classification data sets, the use of convolutional neural networks can learn to represent the content in an image as natural language sentences, or natural language audio. Unlike simply identifying individual objects in a picture, the identified descriptive information may describe the content of the entire reference image. The description information may be specifically generated in any applicable manner, which is not limited by the embodiment of the present application.
The whole or part of the description information has a grammar structure, which includes a dynamic guest structure, a centering structure, a main-called structure, a state middle structure, a dynamic complement structure, a meta guest structure, etc., or any other suitable grammar structure, which is not limited in the embodiment of the present application. For example, from the description information "one sits at a table and plays guitar", the verification answer selected is "guitar", and then the description information detects that "playing guitar" including "guitar" is a moving object structure, belonging to the preset grammar structure. Because the generated description information may not be smooth, or the verification answer is randomly selected, the situation that the preset grammar structure containing the verification answer cannot be detected in the description information may occur, so that the human is difficult to understand the logic relationship between the verification question and the verification answer, and the human-computer verification with the verification question and the verification answer is not suitable.
In man-machine authentication, in addition to providing a reference image to a user, an authentication question is provided to the user, and only when the user answers an authentication answer, the user can be considered to be human, and authentication is passed. Verification questions include the form of selection questions, filling questions, etc., or any other suitable form, to which embodiments of the application are not limited. For example, from the description information "one person sits at a desk and plays a guitar", a word "guitar" is randomly selected as a verification answer, the word "guitar" is removed from the description information, the remaining part "one person plays ____ at a desk" as a verification question, the user is required to observe a reference image, answer the verification question, and among several answer options, a verification answer is selected, that is, verification passes.
In an alternative embodiment of the present application, other interference terms need to be generated to identify human-machine behavior during verification, at least one candidate answer is also needed to be provided with the verification answer, and the verification answer and the candidate answer are taken together as options of a selection question for a user to select.
In an alternative embodiment of the application, the image description generating data set is used for generating description information for the reference image, and the description information comprises one or more models, and the model capable of generating the description information can be obtained according to the description information marked for a plurality of image samples in a supervised learning mode.
In an alternative embodiment of the present application, the image recognition data set is used to recognize an object or any other suitable object in the reference image, including one or more models, and a supervised learning mode may be adopted to obtain a model capable of generating target information according to target information marked for a plurality of image samples. The image recognition data set is only used for recognizing objects or other targets in the reference image, and compared with the image description generation data set, the object included in the reference image can be recognized more accurately, and the situation that verification answers in generated description information are not in the reference image due to misrecognition of the image description generation data set is avoided.
According to one embodiment of the application, after the client sends a request for man-machine verification to the server, the server needs to provide pictures and problems for man-machine recognition for the client, but because the computer has the picture recognition capability, characters or objects in the pictures can be automatically recognized, and further, the normal user and an application operator are greatly negatively influenced by verification, and the network order is disturbed. As shown in the schematic diagram of the verification process in fig. 2, the present application provides a verification mechanism, by acquiring a reference image, generating description information describing the content of the image according to the reference image, then determining verification questions and verification answers for the reference image according to the grammar structure of the description information, verifying the submitted answers for the reference image and the verification questions based on the verification answers, so that the verification questions and the verification answers for the image are automatically generated through understanding and text analysis of the content of the image, and analyzing correct verification answers according to the reference image and the verification questions without complex thinking of human being, but for a machine, it is difficult to understand the logic relationship among the reference image, the verification questions and the verification answers, so that the answers cannot be correctly selected, and the problem that human-computer verification is broken by the machine is avoided. The application is applicable but not limited to the above application scenario.
Referring to fig. 3, a flowchart of an embodiment of a verification method according to a first embodiment of the application is shown, which may specifically include the steps of:
step 101, a reference image is acquired.
In the embodiment of the application, in order to meet a large number of man-machine verification requirements, a plurality of reference images can be prepared in advance, and when a request of man-machine verification exists, one reference image is selected from a gallery storing the plurality of reference images to be watched by a user, and man-machine verification is performed accordingly.
And 102, generating description information describing the reference image.
In the embodiment of the present application, the reference image is input into the image description generation data set to generate the description information for the content of the reference image, which may specifically include any applicable generation manner, and the embodiment of the present application is not limited thereto.
And step 103, determining a verification question and a verification answer for the reference image according to the grammar structure of the description information.
In the embodiment of the present application, the implementation manner of determining the verification question and the verification answer for the reference image may include various ways according to the grammar structure of the description information, for example, selecting the verification answer from the description information, determining that the description information has a preset grammar structure containing the verification answer, taking the part of the description information from which the verification answer is removed as the verification question, or dividing the description information into two parts according to the grammar structure of the description information, wherein one part is taken as the verification answer and the other part is taken as the verification question, and specifically may include any applicable way of determining the verification question and the verification answer.
For example, from the description "one person sits at a table and plays a guitar", the "bullet" is selected as the verification answer, and the verification question may be "one person sits at a table and ___ guitar", or "sits at a table and ___ guitar", or any other applicable verification question and verification answer.
Step 104, verifying the submitted answer aiming at the reference image and the verification question based on the verification answer.
In the embodiment of the application, a user submits an answer considered by the user aiming at a reference image and a verification question, then the submitted answer is verified based on the verification answer, and if the submitted answer is consistent with the verification answer, the verification is passed. The verification method may include multiple ways, for example, if the form of the selected question is the form of the submitted answer is completely consistent with the verification answer, if the form of the filled question is the form of the filled question, the similarity comparison may be performed between the submitted answer and the verification answer, if the similarity is higher than a preset threshold, the verification may be performed, or any other suitable verification method may be used, which is not limited in this embodiment of the present application.
According to the embodiment of the application, the reference image is acquired, the description information of the image content is generated according to the reference image, then the verification question and the verification answer for the reference image are determined according to the grammar structure of the description information, the submitted answer for the reference image and the verification question is verified based on the verification answer, so that the verification question and the verification answer for the image are automatically generated through understanding and text analysis of the image content, and the correct verification answer is analyzed according to the reference image and the verification question without complex thinking of human being, but for a machine, the logic relation among the reference image, the verification question and the verification answer is difficult to understand, so that the answer cannot be correctly selected, and the problem that the human-computer verification is cracked by the machine is avoided.
Referring to fig. 4, a flowchart of an embodiment of a verification method according to a second embodiment of the present application is shown, and the method may specifically include the following steps:
step 201, selecting a reference image according to a man-machine verification request of a client.
In the embodiment of the application, a client sends a man-machine verification request to a server, and the server selects a reference image from a reference image library after receiving the request.
Step 202, generating a data set based on the image description, and generating description information for the reference image.
In the embodiment of the application, a reference image is input into an image description generation data set, and description information for the content of the reference image is generated.
And 203, selecting a verification answer from the description information.
In the embodiment of the application, the verification answer is selected from the description information, that is, the verification answer is a part of the description information, for example, the verification answer is a word, a phrase, and the like in the description information. The method of selecting the verification answer may include a plurality of ways, for example, selecting randomly in the description information, selecting according to the parts of speech of a plurality of words in the description information, or any other suitable selecting way, which is not limited by the embodiment of the present application.
In one embodiment of the present application, optionally, a specific implementation manner of selecting the verification answer from the description information may include: and analyzing the description information to obtain a plurality of words, and selecting at least one word as a verification answer according to the parts of speech of the plurality of words.
Analyzing the description information, dividing the description information into a plurality of words in a language, and selecting at least one word as a verification answer according to the parts of speech of the plurality of words, for example, randomly selecting a noun as the verification answer or selecting a first verb as the verification answer, wherein the method can specifically comprise any applicable selection mode, and the embodiment of the application is not limited to the method.
For example, a word segmentation tool is used for word segmentation to obtain a word list, a part-of-speech tagging tool is used for tagging the part of speech of the segmented result, and a word marked as a noun part-of-speech is randomly selected to obtain a verification answer, such as a guitar.
Step 204, determining that a preset grammar structure containing the verification answer exists in the description information.
In the embodiment of the application, after the verification answer is selected from the description information, the existence of the preset grammar structure containing the verification answer in the description information is determined first so as to determine that the verification answer semantically accords with human understanding. The preset guest-moving structure can be set according to actual needs, and the embodiment of the application is not limited to the above. If there is a preset grammar structure containing the verification answer in the description information, step 207 is performed.
For example, suppose that from the description information "a person sits beside a table plays a guitar", a "guitar" is selected as a verification answer, and then, by detection, the phrase "playing a guitar" is a moving guest structure, and belongs to one of preset grammar structures, then, the verification answer passes semantic detection, and the verification answer semantically accords with human understanding, and is suitable as an answer for man-machine verification.
Step 205, determining that there is no preset grammar structure containing the verification answer in the description information.
In the embodiment of the present application, if the description information does not have the preset grammar structure including the verification answer, step 206 is performed until the description information includes the preset grammar structure including the verification answer, step 207 may be performed.
And step 206, re-selecting a verification answer from the description information, or re-acquiring a reference image.
In the embodiment of the present application, if the detected result indicates that the preset grammar structure containing the verification answer does not exist, the verification answer is re-selected from the description information, or the reference image is directly re-acquired, returning to step 201. In practical application, the verification answers can be selected again from the description information, and if other verification answers cannot be selected or the selected other verification answers do not have the preset grammar structure, the reference image is selected again.
Step 207, verifying that a verification answer exists in the reference image.
In the embodiment of the application, in order to ensure that the image content consistent with the verification answer exists in the reference image, before the verification question is generated according to the description information and the selected verification answer, the verification answer exists in the reference image.
In one embodiment of the present application, optionally, an implementation of verifying that a verification answer exists in the reference image may include: and identifying a reference image based on the image identification data set, and determining whether a verification answer exists in the identification result.
The reference image is input into an image recognition data set (also called a target detection model), the reference image is recognized, an object or various other targets contained in the reference image are determined, and a verification answer is determined to exist in a recognition result, so that man-machine verification can be performed on the selected verification answer, the object contained in the reference image can be more accurately recognized compared with the image description generation data set, and the situation that the verification answer in the generated description information does not exist in the reference image due to misrecognition of the image description generation data set is avoided.
If the verification does not exist, the reference image is reacquired, step 208.
In the embodiment of the application, if the verification result shows that the verification answer does not exist in the reference image, the generated description information is wrong, misleading can be generated for the user, and the user can not correctly answer, so that even a normal user can not normally pass the man-machine verification. In such a case, it is necessary to return to step 201, re-acquire the reference image, and generate description information based on the re-acquired reference image, and then re-select the verification answer.
And step 209, removing part of the verification answer from the description information as a verification question.
In the embodiment of the present application, after selecting the verification answer, the verification answer in the description information is removed to obtain a verification question, or "what" or "? "etc. means that the words or symbols of the question replace the verification answers in the descriptive information, get the verification questions, or generate the verification questions in any other suitable manner, and the embodiments of the present application are not limited in this respect.
At step 210, at least one candidate answer is generated for provision with the verification answer.
In the embodiment of the application, before verifying the submitted answer for the reference image and the verification question based on the verification answer, if the selected question is adopted, at least one candidate answer provided together with the verification answer is also required to be generated as an interference item to distinguish the human-computer behavior. The candidate answer may be generated according to the verification answer, for example, searching for a paraphrase with the verification answer as the candidate answer, or randomly generating at least one candidate answer, which may specifically include any applicable manner, and embodiments of the present application are not limited thereto.
In one embodiment of the present application, optionally, one implementation of generating at least one candidate answer provided with the verification answer may include: and selecting at least one candidate answer within a preset similarity range with the verification answer.
Selecting at least one word with similarity to the verification answer within a preset similarity range from a dictionary as a candidate answer, for example, determining the similarity between words by means of a trained word2vec model (word vector model), and providing the verification answer and the candidate answer together as an answer set to a client for human-computer verification.
Step 211, providing the reference image, the verification question, the verification answer and the candidate answer to the client for the client to perform man-machine verification.
In the embodiment of the application, the reference image, the verification question, the verification answer and the candidate answer are returned to the client side for the user, and for the real user, the verification answer is not difficult to select according to the reference image and the verification question, but for the computer, the logical relationship among the reference image, the verification question and the verification answer cannot be known, so that correct answer cannot be achieved, and man-machine verification is difficult to pass.
According to the embodiment of the application, a reference image is selected according to a man-machine verification request of a client, a data set is generated based on image description, description information for the reference image is generated, a verification answer is selected from the description information, a preset grammar structure containing the verification answer is determined to exist in the description information, the preset grammar structure containing the verification answer is determined to not exist in the description information, the verification answer is selected again from the description information, or the reference image is acquired again, the verification answer exists in the reference image, if the verification does not exist, the reference image is acquired again, a part of the verification answer is removed from the description information and is used as a verification question, at least one candidate answer provided together with the verification answer is generated, the reference image, the verification question, the verification answer and the candidate answer are provided for the client for man-machine verification, so that the verification of the client is performed through understanding and text analysis of image content, the verification question and the verification answer for the image are automatically generated, the correct verification answer does not need to be considered by a human being in a complex way, if the machine is difficult to understand the machine, and the correct answer is difficult to be understood by a machine, and the machine is difficult to be prevented from being a correct.
Referring to fig. 5, a flowchart of an embodiment of a data processing method according to a third embodiment of the present application is shown, and the method may specifically include the following steps:
step 301, obtaining a reference image and a syntax structure of the reference image.
In the embodiment of the application, a plurality of reference pictures are prepared in advance, and the syntax structures set for the reference pictures are acquired when the reference pictures are acquired corresponding to the plurality of syntax structures set in advance.
In an alternative embodiment of the present application, the syntax structure includes a syntax structure including a verification answer in description information describing the reference picture. Any suitable syntax structure is provided according to the actual needs, and the embodiment of the present application is not limited thereto.
Step 302, determining a verification question and a verification answer for the reference image based on the grammar structure.
In the embodiment of the present application, the description information describing the reference image is generated, the verification question and the verification answer of the reference image are determined based on the preset grammar structure, for example, the verification answer is selected from the description information, the preset grammar structure containing the verification answer is determined to exist in the description information, the part of the description information from which the verification answer is removed is used as the verification question, or any other applicable manner is used to determine the verification question and the verification answer.
Step 303, obtaining the answer to be processed.
In the embodiment of the application, after the reference image and the verification question are provided for the user, the user submits the answer considered by the user, namely the answer to be processed, aiming at the reference image and the verification question.
And step 304, generating a verification result based on the verification answer and the answer to be processed.
In the embodiment of the application, the verification result is generated according to the verification answer and the answer to be processed, if the verification answer is consistent with the answer to be processed, the verification result is passed, otherwise, the verification result is not passed.
According to the embodiment of the application, the reference image and the grammar structure of the reference image are obtained, the verification question and the verification answer for the reference image are determined based on the grammar structure, the answer to be processed is obtained, and the verification result is generated based on the verification answer and the answer to be processed. Through understanding the image content and text analysis, verification questions and verification answers for the image are automatically generated, and correct verification answers are analyzed according to the reference image and the verification questions without complex thinking of human beings, but for a machine, the logic relationship among the reference image, the verification questions and the verification answers is difficult to understand, so that the answers cannot be correctly selected, and the problem that human-computer verification is broken by the machine is avoided.
In order that those skilled in the art will better understand the present application, one implementation of the present application will be described below by way of specific examples.
A schematic diagram of a man-machine verification process is shown in fig. 6.
Step 1, a user requests that when the user accesses a page requiring man-machine identification (verification), the client side sends a request to the server.
And 2, selecting a candidate image (namely a reference image), and selecting a picture from a gallery by the server.
And 3, generating image description, inputting the image description into an image description generation model (namely an image description generation data set) for the candidate graph, and generating description information for the candidate graph.
And 4, extracting nouns.
Step 5, detecting whether a dependency relationship exists (i.e. a preset grammar structure).
And 6, if a pre-stored relation exists, the extracted noun can be used as a verification answer.
And 7, the user answers according to the candidate graph and the verification question, and verifies based on the verification answer.
Referring to fig. 7, a block diagram of an embodiment of a verification apparatus according to a fourth embodiment of the present application may specifically include:
an image acquisition module 401 for acquiring a reference image;
an information generating module 402, configured to generate description information describing the reference image;
A question answer determining module 403, configured to determine a verification question and a verification answer for the reference image according to the syntax structure of the description information;
and the verification module 404 is used for verifying the submitted answer aiming at the reference image and the verification question based on the verification answer.
In one embodiment of the present application, optionally, the answer to question determination module includes:
the answer selecting sub-module is used for selecting a verification answer from the description information;
a presence determination submodule, configured to determine that a preset grammar structure including the verification answer exists in the description information;
and the question generation sub-module is used for taking the part of the description information, from which the verification answer is removed, as a verification question.
In one embodiment of the present application, optionally, the apparatus further comprises:
the absence determining module is used for determining that a preset grammar structure containing the verification answer does not exist in the description information before the part of the description information, from which the verification answer is removed, is taken as a verification question;
and the first re-selection module is used for re-selecting the verification answer from the description information or re-acquiring the reference image.
In one embodiment of the present application, optionally, the apparatus further comprises:
the answer verification module is used for verifying that the verification answer exists in the reference image before the part of the description information, from which the verification answer is removed, is used as a verification question;
and the second re-selection module is used for re-acquiring the reference image if the verification does not exist.
In one embodiment of the present application, optionally, the answer selecting submodule includes:
a word parsing unit for parsing the description information to obtain a plurality of words;
and the answer selecting unit is used for selecting at least one word as a verification answer according to the parts of speech of the words.
In one embodiment of the present application, optionally, the apparatus further comprises:
and the candidate answer generation module is used for generating at least one candidate answer provided together with the verification answer before verifying the submitted answer aiming at the reference image and the verification question based on the verification answer.
In one embodiment of the present application, optionally, the candidate answer generation module includes:
and the candidate answer selecting sub-module is used for selecting at least one candidate answer which is within a preset similarity range with the verification answer.
In one embodiment of the present application, optionally, the information generating module includes:
and the information generation sub-module is used for generating a data set based on the image description and generating description information aiming at the reference image.
In one embodiment of the present application, optionally, the answer verification module includes:
and the answer determination submodule is used for identifying the reference image based on the image identification data set and determining whether a verification answer exists in the identification result.
In one embodiment of the present application, optionally, the image acquisition module includes:
the image selecting sub-module is used for selecting a reference image according to the man-machine verification request of the client;
the verification module comprises:
and the verification sub-module is used for providing the reference image, the verification question, the verification answer and the candidate answer to the client for the man-machine verification of the client.
According to the embodiment of the application, the reference image is acquired, the description information of the image content is generated according to the reference image, then the verification question and the verification answer for the reference image are determined according to the grammar structure of the description information, the submitted answer for the reference image and the verification question is verified based on the verification answer, so that the verification question and the verification answer for the image are automatically generated through understanding and text analysis of the image content, and the correct verification answer is analyzed according to the reference image and the verification question without complex thinking of human being, but for a machine, the logic relation among the reference image, the verification question and the verification answer is difficult to understand, so that the answer cannot be correctly selected, and the problem that the human-computer verification is cracked by the machine is avoided.
Referring to fig. 8, there is shown a block diagram of an embodiment of a data processing apparatus according to a fifth embodiment of the present application, which may specifically include:
a structure obtaining module 501, configured to obtain a reference image and a syntax structure of the reference image;
a question answer determining module 502, configured to determine a verification question and a verification answer for the reference image based on the syntax structure;
an answer obtaining module 503, configured to obtain an answer to be processed;
and a result generating module 504, configured to generate a verification result based on the verification answer and the answer to be processed.
In one embodiment of the present application, optionally, the syntax structure includes a syntax structure including a verification answer in description information describing the reference image.
According to the embodiment of the application, the reference image and the grammar structure of the reference image are obtained, the verification question and the verification answer for the reference image are determined based on the grammar structure, the answer to be processed is obtained, and the verification result is generated based on the verification answer and the answer to be processed. Through understanding the image content and text analysis, verification questions and verification answers for the image are automatically generated, and correct verification answers are analyzed according to the reference image and the verification questions without complex thinking of human beings, but for a machine, the logic relationship among the reference image, the verification questions and the verification answers is difficult to understand, so that the answers cannot be correctly selected, and the problem that human-computer verification is broken by the machine is avoided.
For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
Embodiments of the present disclosure may be implemented as a system configured as desired using any suitable hardware, firmware, software, or any combination thereof. Fig. 9 schematically illustrates an example system (or apparatus) 600 that can be used to implement various embodiments described in this disclosure.
For one embodiment, FIG. 9 illustrates an exemplary system 600 having one or more processors 602, a system control module (chipset) 604 coupled to at least one of the processor(s) 602, a system memory 606 coupled to the system control module 604, a non-volatile memory (NVM)/storage device 608 coupled to the system control module 604, one or more input/output devices 610 coupled to the system control module 604, and a network interface 612 coupled to the system control module 606.
The processor 602 may include one or more single-core or multi-core processors, and the processor 602 may include any combination of general-purpose or special-purpose processors (e.g., graphics processors, application processors, baseband processors, etc.). In some embodiments, system 600 can function as a browser as described in embodiments of the present application.
In some embodiments, the system 600 can include one or more computer-readable media (e.g., system memory 606 or NVM/storage 608) having instructions and one or more processors 602 combined with the one or more computer-readable media configured to execute the instructions to implement the modules to perform the actions described in this disclosure.
For one embodiment, the system control module 604 may include any suitable interface controller to provide any suitable interface to at least one of the processor(s) 602 and/or any suitable device or component in communication with the system control module 604.
The system control module 604 may include a memory controller module to provide an interface to the system memory 606. The memory controller modules may be hardware modules, software modules, and/or firmware modules.
The system memory 606 may be used to load and store data and/or instructions for the system 600, for example. For one embodiment, system memory 606 may comprise any suitable volatile memory, such as, for example, a suitable DRAM. In some embodiments, the system memory 606 may comprise double data rate type four synchronous dynamic random access memory (DDR 4 SDRAM).
For one embodiment, the system control module 604 may include one or more input/output controllers to provide an interface to the NVM/storage 608 and the input/output device(s) 610.
For example, NVM/storage 608 may be used to store data and/or instructions. NVM/storage 608 may include any suitable non-volatile memory (e.g., flash memory) and/or may include any suitable non-volatile storage device(s) (e.g., one or more Hard Disk Drives (HDDs), one or more Compact Disc (CD) drives, and/or one or more Digital Versatile Disc (DVD) drives).
NVM/storage 608 may include storage resources physically part of the device on which system 600 is installed or it may be accessed by the device without being part of the device. For example, NVM/storage 608 may be accessed over a network via input/output device(s) 610.
Input/output device(s) 610 can provide an interface for system 600 to communicate with any other suitable devices, input/output device 610 can include communication components, audio components, sensor components, and the like. Network interface 612 may provide an interface for system 600 to communicate over one or more networks, and system 600 may communicate wirelessly with one or more components of a wireless network according to any of one or more wireless network standards and/or protocols, such as accessing a wireless network based on a communication standard, such as WiFi,2G, or 3G, or a combination thereof.
For one embodiment, at least one of the processor(s) 602 may be packaged together with logic of one or more controllers (e.g., memory controller modules) of the system control module 604. For one embodiment, at least one of the processor(s) 602 may be packaged together with logic of one or more controllers of the system control module 604 to form a System In Package (SiP). For one embodiment, at least one of the processor(s) 602 may be integrated on the same die with logic of one or more controllers of the system control module 604. For one embodiment, at least one of the processor(s) 602 may be integrated on the same die with logic of one or more controllers of the system control module 604 to form a system on chip (SoC).
In various embodiments, system 600 may be, but is not limited to being: a browser, workstation, desktop computing device, or mobile computing device (e.g., a laptop computing device, handheld computing device, tablet, netbook, etc.). In various embodiments, system 600 may have more or fewer components and/or different architectures. For example, in some embodiments, system 600 includes one or more cameras, keyboards, liquid Crystal Display (LCD) screens (including touch screen displays), non-volatile memory ports, multiple antennas, graphics chips, application Specific Integrated Circuits (ASICs), and speakers.
Wherein if the display comprises a touch panel, the display screen may be implemented as a touch screen display to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation.
The embodiment of the application also provides a non-volatile readable storage medium, wherein one or more modules (programs) are stored in the storage medium, and when the one or more modules are applied to terminal equipment, the terminal equipment can execute instructions (instructions) of each method step in the embodiment of the application.
In one example, a computer device is provided comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements a method according to an embodiment of the application when executing the computer program.
There is also provided in one example a computer readable storage medium having stored thereon a computer program, characterized in that the program when executed by a processor implements a method as in one or more of the embodiments of the application.
The embodiment of the application discloses a verification method and a verification device, and example 1 comprises the verification method comprising the following steps:
acquiring a reference image;
generating description information describing the reference image;
determining a verification question and a verification answer for the reference image according to the grammar structure of the description information;
and verifying the submitted answer aiming at the reference image and the verification question based on the verification answer.
Example 2 may include the method of example 1, wherein the determining a verification question and a verification answer for the reference image according to a syntax structure of the description information includes:
selecting a verification answer from the description information;
determining that a preset grammar structure containing the verification answer exists in the description information;
and removing part of the verification answer from the description information as a verification question.
Example 3 may include the method of example 1 and/or example 2, wherein, prior to said removing the portion of the verification answer from the description information as a verification question, the method further comprises:
determining that a preset grammar structure containing the verification answer does not exist in the description information;
and re-selecting a verification answer from the description information, or re-acquiring a reference image.
Example 4 may include the method of one or more of examples 1-3, wherein, prior to removing the portion of the verification answer from the description information as a verification question, the method further comprises:
verifying that a verification answer exists in the reference image;
and if the verification does not exist, the reference image is acquired again.
Example 5 may include the method of one or more of examples 1-4, wherein the selecting a verification answer from the descriptive information comprises:
analyzing the description information to obtain a plurality of words;
and selecting at least one word as a verification answer according to the parts of speech of the plurality of words.
Example 6 may include the method of one or more of examples 1-5, wherein, prior to the verifying the submitted answer to the reference image and the verification question based on the verification answer, the method further comprises:
at least one candidate answer is generated for provision with the verification answer.
Example 7 may include the method of one or more of examples 1-6, wherein the generating at least one candidate answer provided with the verification answer comprises:
and selecting at least one candidate answer within a preset similarity range with the verification answer.
Example 8 may include the method of one or more of examples 1-7, wherein the generating description information describing the reference image comprises:
a data set is generated based on the image description, and description information for the reference image is generated.
Example 9 may include the method of one or more of examples 1-8, wherein the verifying that a verification answer is present in the reference image comprises:
and identifying the reference image based on the image identification data set, and determining whether a verification answer exists in the identification result.
Example 10 may include the method of one or more of examples 1-9, wherein the acquiring a reference image comprises:
selecting a reference image according to a man-machine verification request of a client;
the verifying the submitted answer for the reference image and the verification question based on the verification answer comprises:
and providing the reference image, the verification question, the verification answer and the candidate answer to the client for human-computer verification by the client.
Example 11 includes a data processing method, comprising:
acquiring a reference image and a grammar structure of the reference image;
determining a verification question and a verification answer for the reference image based on the grammar structure;
Acquiring an answer to be processed;
and generating a verification result based on the verification answer and the answer to be processed.
Example 12 includes the method of example 11, wherein the syntax structure includes a syntax structure including a verification answer in description information describing the reference image.
Example 13 includes an authentication apparatus, comprising:
the image acquisition module is used for acquiring a reference image;
the information generation module is used for generating description information describing the reference image;
the question answer determining module is used for determining a verification question and a verification answer aiming at the reference image according to the grammar structure of the description information;
and the verification module is used for verifying the submitted answer aiming at the reference image and the verification question based on the verification answer.
Example 14 may include the apparatus of example 13, wherein the answer to question determination module comprises:
the answer selecting sub-module is used for selecting a verification answer from the description information;
a presence determination submodule, configured to determine that a preset grammar structure including the verification answer exists in the description information;
and the question generation sub-module is used for taking the part of the description information, from which the verification answer is removed, as a verification question.
Example 15 may include the apparatus of example 13 and/or example 14, wherein the apparatus further comprises:
the absence determining module is used for determining that a preset grammar structure containing the verification answer does not exist in the description information before the part of the description information, from which the verification answer is removed, is taken as a verification question;
and the first re-selection module is used for re-selecting the verification answer from the description information or re-acquiring the reference image.
Example 16 may include the apparatus of one or more of examples 13-15, wherein the apparatus further comprises:
the answer verification module is used for verifying that the verification answer exists in the reference image before the part of the description information, from which the verification answer is removed, is used as a verification question;
and the second re-selection module is used for re-acquiring the reference image if the verification does not exist.
Example 17 may include the apparatus of one or more of examples 13-16, wherein the answer selection submodule includes:
a word parsing unit for parsing the description information to obtain a plurality of words;
and the answer selecting unit is used for selecting at least one word as a verification answer according to the parts of speech of the words.
Example 18 may include the apparatus of one or more of examples 13-17, wherein the apparatus further comprises:
and the candidate answer generation module is used for generating at least one candidate answer provided together with the verification answer before verifying the submitted answer aiming at the reference image and the verification question based on the verification answer.
Example 19 may include the apparatus of one or more of examples 13-18, wherein the candidate answer generation module comprises:
and the candidate answer selecting sub-module is used for selecting at least one candidate answer which is within a preset similarity range with the verification answer.
Example 20 may include the apparatus of example 13-example 19 or more, wherein the information generation module comprises:
and the information generation sub-module is used for generating a data set based on the image description and generating description information aiming at the reference image.
Example 21 may include the apparatus of one or more of examples 13-20, wherein the answer verification module comprises:
and the answer determination submodule is used for identifying the reference image based on the image identification data set and determining whether a verification answer exists in the identification result.
Example 22 may include the apparatus of one or more of examples 13-21, wherein the image acquisition module comprises:
The image selecting sub-module is used for selecting a reference image according to the man-machine verification request of the client;
the verification module comprises:
and the verification sub-module is used for providing the reference image, the verification question, the verification answer and the candidate answer to the client for the man-machine verification of the client.
Example 23 includes a data processing apparatus, comprising:
the structure acquisition module is used for acquiring a reference image and a grammar structure of the reference image;
a question answer determining module for determining a verification question and a verification answer for the reference image based on the grammar structure;
the answer acquisition module is used for acquiring an answer to be processed;
and the result generation module is used for generating a verification result based on the verification answer and the answer to be processed.
Example 24 includes the apparatus of example 23, wherein the syntax structure includes a syntax structure including a verification answer in description information describing the reference image.
Example 25 includes a computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the method as in one or more of examples 1-12 when the computer program is executed.
Example 26 includes a computer-readable storage medium having stored thereon a computer program that when executed by a processor performs a method as in examples 1-12 or more.
While certain embodiments have been illustrated and described for purposes of description, various alternative, and/or equivalent embodiments, or implementations calculated to achieve the same purposes are shown and described without departing from the scope of the embodiments of the present application. This disclosure is intended to cover any adaptations or variations of the embodiments discussed herein. It is manifestly, therefore, that the embodiments described herein are limited only by the claims and the equivalents thereof.
Claims (12)
1. A method of authentication, comprising:
acquiring a reference image;
generating description information describing the reference image;
determining a verification question and a verification answer for the reference image according to the grammar structure of the description information;
verifying the submitted answer aiming at the reference image and the verification question based on the verification answer;
wherein, according to the grammar structure of the description information, determining the verification question and the verification answer for the reference image includes:
selecting a verification answer from the description information;
Determining that a preset grammar structure containing the verification answer exists in the description information;
removing part of the verification answers from the description information as verification questions;
wherein verifying the submitted answer for the reference image and the verification question based on the verification answer comprises: and if the verification question is in the form of a filling question, comparing the similarity between the submitted answer and the verification answer, and if the similarity is higher than a preset threshold, passing the verification.
2. The method of claim 1, wherein prior to said removing the portion of the verification answer from the descriptive information as a verification question, the method further comprises:
determining that a preset grammar structure containing the verification answer does not exist in the description information;
and re-selecting a verification answer from the description information, or re-acquiring a reference image.
3. The method of claim 1, wherein prior to removing the portion of the verification answer from the descriptive information as a verification question, the method further comprises:
verifying that a verification answer exists in the reference image;
and if the verification does not exist, the reference image is acquired again.
4. The method of claim 1, wherein selecting a verification answer from the descriptive information comprises:
analyzing the description information to obtain a plurality of words;
and selecting at least one word as a verification answer according to the parts of speech of the plurality of words.
5. The method of claim 1, wherein prior to said validating the submitted answer for the reference image and the validation question based on the validation answer, the method further comprises:
at least one candidate answer is generated for provision with the verification answer.
6. The method of claim 5, wherein the generating at least one candidate answer provided with the verification answer comprises:
and selecting at least one candidate answer within a preset similarity range with the verification answer.
7. The method of claim 1, wherein the generating description information describing the reference image comprises:
a data set is generated based on the image description, and description information for the reference image is generated.
8. A method according to claim 3, wherein said verifying that a verification answer is present in the reference image comprises:
And identifying the reference image based on the image identification data set, and determining whether a verification answer exists in the identification result.
9. The method of claim 1, wherein the acquiring a reference image comprises:
selecting a reference image according to a man-machine verification request of a client;
the verifying the submitted answer for the reference image and the verification question based on the verification answer comprises:
and providing the reference image, the verification question, the verification answer and the candidate answer to the client for human-computer verification by the client.
10. A method of data processing, comprising:
acquiring a reference image and a grammar structure of the reference image, wherein the grammar structure comprises a grammar structure containing verification answers in description information describing the reference image;
determining a verification question and a verification answer for the reference image based on the grammar structure, wherein the verification question is a part of the description information except for the verification answer;
acquiring an answer to be processed;
generating a verification result based on the verification answer and the answer to be processed;
wherein, based on the verification answer and the answer to be processed, generating the verification result includes: and if the verification question is in the form of a filling question, comparing the similarity between the submitted answer and the verification answer, and if the similarity is higher than a preset threshold, passing the verification.
11. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to one or more of claims 1-10 when executing the computer program.
12. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to one or more of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810887424.2A CN110858244B (en) | 2018-08-06 | 2018-08-06 | Verification method, data processing method, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810887424.2A CN110858244B (en) | 2018-08-06 | 2018-08-06 | Verification method, data processing method, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110858244A CN110858244A (en) | 2020-03-03 |
| CN110858244B true CN110858244B (en) | 2023-08-25 |
Family
ID=69634727
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810887424.2A Active CN110858244B (en) | 2018-08-06 | 2018-08-06 | Verification method, data processing method, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110858244B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111966990B (en) * | 2020-08-21 | 2024-06-04 | 网易（杭州）网络有限公司 | Verification code processing method and device, electronic equipment and storage medium |
| CN116561733B (en) * | 2023-05-29 | 2024-10-18 | 北京百度网讯科技有限公司 | Verification method and device based on picture verification code |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103428163A (en) * | 2012-05-15 | 2013-12-04 | 上海博路信息技术有限公司 | Verification code based on image content |
| CN103942486A (en) * | 2013-01-17 | 2014-07-23 | 上海博路信息技术有限公司 | Verification code of image array |
| CN106340049A (en) * | 2015-07-15 | 2017-01-18 | 中国传媒大学 | Verification code generating method based on animation semantics |
| CN107995170A (en) * | 2017-11-21 | 2018-05-04 | 重庆金融资产交易所有限责任公司 | Auth method, device, computer equipment and computer-readable recording medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150199400A1 (en) * | 2014-01-15 | 2015-07-16 | Konica Minolta Laboratory U.S.A., Inc. | Automatic generation of verification questions to verify whether a user has read a document |
| US20160364374A1 (en) * | 2015-06-09 | 2016-12-15 | International Business Machines Corporation | Visual indication for images in a question-answering system |
-
2018
- 2018-08-06 CN CN201810887424.2A patent/CN110858244B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103428163A (en) * | 2012-05-15 | 2013-12-04 | 上海博路信息技术有限公司 | Verification code based on image content |
| CN103942486A (en) * | 2013-01-17 | 2014-07-23 | 上海博路信息技术有限公司 | Verification code of image array |
| CN106340049A (en) * | 2015-07-15 | 2017-01-18 | 中国传媒大学 | Verification code generating method based on animation semantics |
| CN107995170A (en) * | 2017-11-21 | 2018-05-04 | 重庆金融资产交易所有限责任公司 | Auth method, device, computer equipment and computer-readable recording medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110858244A (en) | 2020-03-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11817013B2 (en) | Display apparatus and method for question and answer | |
| CN107995536B (en) | Method, device and equipment for extracting video preview and computer storage medium | |
| WO2021203863A1 (en) | Artificial intelligence-based object detection method and apparatus, device, and storage medium | |
| KR102347398B1 (en) | Actionable content displayed on a touch screen | |
| CN106210836B (en) | Interactive learning method and device in video playing process and terminal equipment | |
| US10114809B2 (en) | Method and apparatus for phonetically annotating text | |
| CN110225387A (en) | A kind of information search method, device and electronic equipment | |
| US20140316764A1 (en) | Clarifying natural language input using targeted questions | |
| US20100228804A1 (en) | Constructing image captchas utilizing private information of the images | |
| CN109800386A (en) | Highlight the key component of text in document | |
| CN109558513B (en) | Content recommendation method, device, terminal and storage medium | |
| US10885286B2 (en) | Simultaneous and real time translation and language switching across a set of features | |
| CN109492085B (en) | Answer determination method, device, terminal and storage medium based on data processing | |
| CN110858244B (en) | Verification method, data processing method, computer equipment and storage medium | |
| CN109600681B (en) | Subtitle display method, device, terminal and storage medium | |
| CN113849623A (en) | Text visual question answering method and device | |
| WO2017211202A1 (en) | Method, device, and terminal device for extracting data | |
| KR101694290B1 (en) | Apparatus and method for detecting game bot | |
| CN109325135B (en) | Text-based video generation method, device, computer equipment and storage medium | |
| KR20230062251A (en) | Apparatus and method for document classification based on texts of the document | |
| US20140181672A1 (en) | Information processing method and electronic apparatus | |
| US20140212039A1 (en) | Efficient Verification or Disambiguation of Character Recognition Results | |
| CN112231655B (en) | Data processing method, computer equipment and storage medium | |
| CN112836523A (en) | Word translation method, device and equipment and readable storage medium | |
| US20160253992A1 (en) | Ocr through voice recognition |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40024918 Country of ref document: HK |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |