CN106599671B - Method and device for identifying picture based on user filling verification code - Google Patents
Method and device for identifying picture based on user filling verification code Download PDFInfo
- Publication number
- CN106599671B CN106599671B CN201510683529.2A CN201510683529A CN106599671B CN 106599671 B CN106599671 B CN 106599671B CN 201510683529 A CN201510683529 A CN 201510683529A CN 106599671 B CN106599671 B CN 106599671B
- Authority
- CN
- China
- Prior art keywords
- picture
- identification
- user
- nouns
- identified
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/36—User authentication by graphic or iconic representation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a method and a device for identifying pictures based on a verification code filled by a user, wherein the method comprises the steps of sending at least one picture to be identified and a plurality of known pictures to the user as the verification code picture, receiving a user identification noun input by the user after identifying the verification code picture, recording an identification record corresponding to the picture to be identified, judging whether the user identification noun input by the user is matched with the known picture according to the known picture and the picture noun thereof, setting a weighting score for the identification record according to the matching times with the known picture, and finally identifying the picture noun of the picture to be identified according to all recorded identification records corresponding to the picture to be identified and the weighting scores thereof. The device comprises a verification code picture sending module, a receiving module, a weighting module and an identification module. The method and the device of the invention accelerate the picture identification processing speed, increase the machine learning experience and effectively improve the identification processing capability of a large number of pictures.
Description
Technical Field
The invention belongs to the technical field of computers, and particularly relates to a method and a device for identifying pictures based on a verification code filled in by a user.
Background
The development of the internet is always going forward in innovation and change, from a contact platform to a browsing platform, to an interaction platform to a working platform, and the internet is gradually going deep into the lives of people. With the continuous development of the internet, the data gradually enters a big data era, and urban data, enterprise data, medical data and website data become important components of virtual and real life.
In the process of machine learning of big data, a background server applied to the internet often encounters the situation that a machine cannot accurately identify pictures, and needs a large amount of manpower for marking and correcting. For massive internet data, manual processing of pictures which cannot be learned by a machine is extremely heavy and tedious work.
Disclosure of Invention
The invention aims to provide a method for identifying pictures based on a verification code filled in by a user, which takes a picture to be identified as a verification code picture, determines a picture noun of the picture to be identified by identifying the verification code picture in the process of user identity verification, skillfully identifies a large number of pictures to be identified by means of the identification of the user, and saves manpower and material resources.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a method for picture recognition based on a user filling in a passcode, the method comprising:
sending at least one picture to be identified and a plurality of known pictures as verification code pictures to a user;
receiving a user identification noun input by a user after identifying the verification code picture, and recording an identification record corresponding to the picture to be identified, wherein the identification record comprises a picture ID of the picture to be identified and the user identification noun input by the user;
judging whether a user identification noun input by a user is matched with a known picture according to the known picture and a picture noun thereof, and setting a weighting score for an identification record according to the matching times with the known picture;
and identifying the picture nouns of the picture to be identified according to all recorded identification records corresponding to the picture to be identified and the weighted scores of the identification records.
Further, after receiving the user identification noun input by the user after identifying the verification code picture, the method further includes:
recording the result of whether the user successfully logs in or not;
the method further comprises the steps of:
setting an additional weighted score for the identification record according to the number of times of successful continuous login of the user;
the weighted score of the identified record further includes the additional weighted score.
Further, before recognizing the picture nouns of the picture to be recognized according to all recorded recognition records and the weighting scores thereof corresponding to the picture to be recognized, the method further includes:
and deleting the identification records with the weight scores less than or equal to the set threshold.
Further, the method comprises the steps of:
and correcting the weighted score according to the historical credit score of the user, wherein the correction formula is as follows:
F＝round((F0+Y+Z)/3，2)
wherein F is the modified weighted score, F0For the weighted score before correction, Y is the user's historical credit scoreAnd Z is a base score.
The method for identifying the picture nouns of the picture to be identified according to all recorded identification records and the weighted scores thereof corresponding to the picture to be identified comprises the following steps:
acquiring M identification records with weighting scores ranked at the top in all identification records corresponding to the picture to be identified, and merging the identification records of the same user identification nouns to obtain merged identification records, wherein the merged identification records comprise the picture ID of the picture to be identified, the corresponding user identification nouns, the times of the same user identification nouns and the weighted average score;
and screening out the combined user identification nouns with the maximum times of the same user identification nouns as the picture nouns of the picture to be identified according to the combined identification records, taking the combined user identification nouns with the large weighted average score as the picture nouns of the picture to be identified when more than two combined identification records with the maximum times of the same user identification nouns exist, and submitting the picture nouns to manual identification when the combined weighted average scores of the two combined identification records with the maximum times of the same user identification nouns are the same.
Further, the picture to be recognized corresponds to the display times set for the picture to be recognized, and the picture to be recognized and the known pictures are sent to the user to serve as verification code pictures, and the method further comprises the following steps:
and verifying whether the number of times that the picture to be identified is submitted as the verification code picture reaches the display number, and when the display number is reached, not submitting the picture as the verification code picture.
The invention also provides a device for identifying the picture based on the verification code filled in by the user, which comprises:
the verification code picture sending module is used for sending at least one picture to be identified and a plurality of known pictures as verification code pictures to a user;
the receiving module is used for receiving a user identification noun input by a user after identifying the verification code picture and recording an identification record corresponding to the picture to be identified, wherein the identification record comprises the picture ID of the picture to be identified and the user identification noun input by the user;
the weighting module is used for judging whether a user identification noun input by a user is matched with the known picture or not according to the known picture and the picture noun thereof and setting a weighting score for the identification record according to the matching times with the known picture;
and the identification module is used for identifying the picture nouns of the picture to be identified according to all recorded identification records corresponding to the picture to be identified and the weighted scores of the identification records.
Further, the receiving module is also used for recording the result of whether the user successfully logs in this time;
then, the weighting module also sets an additional weighting score for the identification record according to the number of times of successful continuous login of the user; the weighted score of the identified record further includes the additional weighted score.
Further, the weighting module is also used for deleting the identification records with the weighting scores smaller than or equal to the set threshold value.
Further, the weighting module is further configured to modify the weighting score according to the user historical credit score, where the modification formula is as follows:
F＝round((F0+Y+Z)/3，2)
wherein F is the modified weighted score, F0For the weighted score before correction, Y is the user's historical credit score and Z is the base score.
Further, the recognition module recognizes the picture nouns of the picture to be recognized according to all recorded recognition records and the weighted scores thereof corresponding to the picture to be recognized, and executes the following operations:
acquiring M identification records with weighting scores ranked at the top in all identification records corresponding to the picture to be identified, and merging the identification records of the same user identification nouns to obtain merged identification records, wherein the merged identification records comprise the picture ID of the picture to be identified, the corresponding user identification nouns, the times of the same user identification nouns and the weighted average score;
and screening out the combined user identification nouns with the maximum times of the same user identification nouns as the picture nouns of the picture to be identified according to the combined identification records, taking the combined user identification nouns with the large weighted average score as the picture nouns of the picture to be identified when more than two combined identification records with the maximum times of the same user identification nouns exist, and submitting the picture nouns to manual identification when the combined weighted average scores of the two combined identification records with the maximum times of the same user identification nouns are the same.
Furthermore, the picture to be identified corresponds to the display times set for the picture to be identified, the identifying code picture sending module is further configured to verify whether the number of times that the picture to be identified is submitted as the identifying code picture reaches the display times, and when the number of times that the picture is submitted as the identifying code picture reaches the display times, the picture is not submitted as the identifying code picture.
According to the method and the device for identifying the picture based on the verification code filled in by the user, the picture to be identified is used as the verification code picture, the picture noun of the picture to be identified is determined by identifying the verification code picture in the user identity verification process, a large number of pictures to be identified are identified skillfully by means of the identification of the user, and manpower and material resources are saved. By the method and the device, the picture identification processing speed is increased, the machine learning experience is increased, and the identification processing capacity of a large number of pictures is effectively improved.
Drawings
FIG. 1 is a flowchart of a method for identifying a picture based on a user filling in a verification code according to the present invention;
fig. 2 is a schematic structural diagram of an apparatus for performing picture recognition based on a user filling in a verification code according to the present invention.
Detailed Description
The technical solutions of the present invention are further described in detail below with reference to the drawings and examples, which should not be construed as limiting the present invention.
The general idea of the invention is to utilize the link that the verification code needs to be input in the verification process when the user logs in, the picture to be recognized is mixed in the verification picture and is sent to the user, and the user needs to select the picture for verification, and then the picture to be recognized can be analyzed according to the selection of the user to the picture to be recognized, so as to recognize the picture to be recognized.
This embodiment provides four data tables for this purpose: data table a, data table B, data table C, and data table D, wherein:
the data table A is used for storing pictures which cannot be identified by a machine and also pictures to be identified which need to be identified by the method;
the data table B is used for storing known pictures and corresponding names;
the data table C is used for storing identification records;
the data table D is used for storing the final recognition result of the picture to be recognized.
In the embodiment, when the user logs in, 4 pictures are sent to the user as the verification codes, wherein 3 pictures are from the data table B, and 1 picture is from the data table A. It should be noted that the specific number of pictures used as the verification code is not limited, but only includes one picture to be recognized, and 4 pictures are taken as an example in the present embodiment for explanation.
And (5) requiring the user to identify the pictures and returning the user identification nouns of the 4 pictures. And after receiving the user identification nouns returned by the user, verifying the answer of the user, and if the user fills three picture nouns from the data table B, determining that the user can pass the verification.
Based on the verification process, the method for identifying the picture based on the verification code filled in by the user in this embodiment as shown in fig. 1 includes:
and step S1, sending the picture to be identified and a plurality of known pictures as verification code pictures to the user.
When a user logs in, the user needs to be authenticated, and if the authentication passes the form of a picture authentication code, a picture serving as the authentication code needs to be sent to the user. For example, assuming that the total number of the verification code pictures is 4, three known pictures are taken from the data table B, and one picture to be identified is taken from the data table a and sent to the user as the verification code picture.
The matter to be done by the invention is to identify the picture nouns corresponding to the picture to be identified, and the picture nouns can be the names of objects contained in the picture. In this embodiment, 4 pictures are taken as an example of the verification code picture, and in actual use, more verification code pictures can be provided, including at least one picture to be recognized and a plurality of known pictures, and the identity verification is performed according to the recognition result of the known pictures, and the number of the included pictures to be recognized does not affect the identity verification.
Step S2, receiving a user identification noun input by the user after identifying the verification code picture, and recording an identification record corresponding to the picture to be identified, where the identification record includes the picture ID of the picture to be identified and the user identification noun input by the user.
In this embodiment, the user is required to identify the verification code picture and return the user identification noun of 4 pictures. After receiving the verification code picture, the user inputs the user identification nouns of the pictures one by one, and the picture nouns input by the user are called user identification nouns in the embodiment.
After receiving the user identification nouns of the returned 4 pictures, comparing the user identification nouns with the known picture nouns, and if the user fills in three picture nouns of the known pictures from the data table B, the user is considered to be verified.
For example, three known pictures selected from the data table B are an electric fan, a television and a washing machine, respectively, while one picture selected from the data table a is a picture to be identified, and four pictures are sent to the user as verification code pictures in a disordered order. Suppose the electric fan is arranged at the first position, the picture to be recognized is arranged at the second position, the television is arranged at the third position, and the washing machine is arranged at the fourth position.
And judging that the verification is passed according to the user identification nouns returned by the user, wherein the user identification nouns returned by the user correspond to the picture nouns of the three known pictures, and the user identification nouns returned by the user are all consistent with the known picture nouns, namely the first picture returns an electric fan, the third picture returns a television, and the fourth picture returns a washing machine. Obviously, the picture to be recognized does not affect the judgment result, but the user still returns the corresponding user recognition noun, so that the picture to be recognized can be recognized by analyzing the user recognition noun returned by the user, and the recognized picture noun is given.
However, although the user gives the user identification noun for the picture to be identified, it cannot be determined that the user identification noun given by the user is the real picture noun of the picture to be identified, and further analysis is required for this purpose.
In order to facilitate the analysis of the user identification nouns corresponding to the to-be-identified pictures returned by the user, in this embodiment, an identification record is recorded in the data table C, where the identification record includes the picture ID of the to-be-identified picture and the user identification noun input by the user.
In this embodiment, the result of whether the user successfully logs in this time is also recorded, so as to facilitate the weighting calculation in the subsequent steps.
And step S3, judging whether the user identification noun input by the user is matched with the known picture according to the known picture and the picture noun thereof, and setting a weighting score for the identification record according to the matching times with the known picture.
In order to analyze the user identification nouns corresponding to the to-be-identified pictures returned by the user, the embodiment determines the correct number of user identification nouns input by the user according to the known pictures, and sets a weighted score for the identification record, wherein the weighted score is related to the user identification nouns correctly returned by the user to the known pictures.
For example: this example has three known pictures, and the following table sets the weight f for the identification record1：
| The correct amount | Weighted score |
| 0 | -1 |
| 1 | 1 |
| 2 | 2 |
| 3 | 5 |
TABLE 1
Namely, the three pieces of the Chinese characters are identified with errors, and the weighting score is-1; one is correctly identified, and the weighting score is 1; the two pieces are correctly identified, and the weighting score is 2; all three were identified correctly with a weight score of 5. It can be seen that if the user passes the verification, the weighting score of the identification record corresponding to the verification is 5. At each verification, an identification record is recorded to the data table C, whether the verification is passed or not.
It is easy to understand that, the weighted score corresponding to each identification record may be the weighted score obtained in table 1, and other factors, such as the user history credit, the number of successful times of continuous login of the user, etc., may be further added to further improve the reliability of the weighted score of the identification record.
For example, according to the recorded result of whether the user successfully logs in this time, the number of times that the user successfully logs in continuously can be known, and then an additional weighting score can be set for the identification record according to the number of times that the user successfully logs in continuously. Specific additional weighting score f2Can be calculated according to the following table:
| number of consecutive logins | Additional weighted scores |
| 5 consecutive failures | -1 |
| Have not been successively successful | 2 |
| Ten times in succession | 5 |
TABLE 2
To this end, when considering the number of consecutive logins of the user, the weighted score of the identification record further includes the additional weighted score, and the calculation formula is as follows:
F＝f1+f2
it should be noted that, when the weighted score F of the identification record is less than or equal to the set threshold (for example, -1), the identification record is not trusted and does not need to participate in subsequent calculations, so the method of this embodiment further includes:
and screening out the identification records with the weight scores F less than or equal to the set threshold.
Further, the present embodiment also introduces a user history credit score to correct the weighting score F, and the calculation formula is as follows:
F＝round((F0+Y+Z)/3，2)
wherein Y is the user historical credit score, Z is the base score, F is the modified weighted score, F0Is a weighted score before correction. Can see through the pair F0Y, Z, after averaging, the weighted fraction F after correction can be obtained by rounding up two digits after taking the decimal point. And the corrected weighting fraction F is adopted to carry out calculation in the subsequent steps, so that the obtained result is more credible.
And step S4, recognizing the picture nouns of the picture to be recognized according to all the recorded recognition records corresponding to the picture to be recognized and the weighted scores of the recognition records.
With the recognition of the picture to be recognized by a plurality of users, more and more recognition records corresponding to the picture to be recognized are obtained in the data table C, and all recorded recognition records and weighted scores thereof corresponding to the picture to be recognized can be analyzed to find out an accurate picture noun of the picture to be recognized.
Simply, the user identification nouns in the identification records with the largest weighting score in the recorded identification records can be directly selected as the picture nouns of the picture to be identified.
Preferably, the scheme adopted by the embodiment is as follows:
acquiring M identification records with weighting scores ranked at the top in all identification records corresponding to the picture to be identified, and merging the identification records of the same user identification nouns to obtain merged identification records, wherein the merged identification records comprise the picture ID of the picture to be identified, the corresponding user identification nouns, the times of the same user identification nouns and the weighted average score;
and screening out the combined user identification nouns with the maximum times of the same user identification nouns as the picture nouns of the picture to be identified according to the combined identification records, taking the combined user identification nouns with the large weighted average score as the picture nouns of the picture to be identified when more than two combined identification records with the maximum times of the same user identification nouns exist, and submitting the picture nouns to manual identification when the combined weighted average scores of the two combined identification records with the maximum times of the same user identification nouns are the same.
The following is a detailed description:
according to the calculation of the steps S1-S3, the identification records of the picture to be identified and the corresponding weighted scores are not difficult to obtain, and the following table is assumed for a plurality of identification records of the picture to be identified, wherein F is arranged in the order of magnitude:
| picture ID | User recognition noun | F0 | Y | F |
| 111 | Refrigerator with a door | F0-1 | Y1 | F1 |
| 111 | Microwave oven with a heat exchanger | F0-2 | Y2 | F2 |
| 111 | Safe deposit box | F0-3 | Y3 | F3 |
| 111 | Refrigerator with a door | F0-4 | Y4 | F4 |
| 111 | Microwave oven with a heat exchanger | F0-5 | Y5 | F5 |
| 111 | Baking oven | F0-6 | Y6 | F6 |
| 111 | Air conditioner | F0-7 | Y7 | F7 |
| 111 | Wood cabinet | F0-8 | Y8 | F8 |
| 111 | Washing machine | F0-9 | Y9 | F9 |
| 111 | Haier | F0-10 | Y10 | F10 |
| … | … | … | … | … |
TABLE 3
Wherein F0The weighted score before correction is F, the weighted score after correction is F, and the user history score is Y.
Taking the first M (M ═ 10) identification records of the picture to be identified 111, merging the identification records corresponding to the same user identification nouns to obtain the following merged identification records:
TABLE 4
Wherein the weighted score P is averaged1＝round((F1+F3)/2，2)，P2＝round((F2+F5) 2, 2), i.e. the weighted average score is the average of the weighted scores of the identification records corresponding to the same user identification noun.
Sequencing the merged identification records according to the times of the same user identification nouns corresponding to each merged identification record, and acquiring the user identification nouns corresponding to the merged identification records with the first ranking as picture nouns of the picture to be identified; when the times of the same user identification nouns of more than two combined identification records are the same, taking the combined user identification nouns of the identification records with large weighted average scores as the picture nouns of the picture to be identified; and when the times of the same user identification nouns of more than two combined identification records are the same and the weighted average scores are still the same, pushing the same to operation and maintenance personnel for manual identification.
And finally, writing the identification result into a data table D for subsequent machine learning or other services.
It should be noted that, after a picture to be recognized is subjected to user recognition for many times, the picture to be recognized can be recognized certainly according to the method of the present invention, and then the picture does not need to be submitted to the user again for recognition, so that the present invention sets the display times for each picture to be recognized, and when the number of times that a picture to be recognized is submitted and displayed as an authentication code picture reaches the display times, the picture to be recognized is not submitted any more, and is deleted from the data table a.
Corresponding to the above method, an apparatus for performing picture recognition based on a user filling in a verification code according to this embodiment is shown in fig. 2, and includes:
the verification code picture sending module is used for sending at least one picture to be identified and a plurality of known pictures as verification code pictures to a user;
the receiving module is used for receiving a user identification noun input by a user after identifying the verification code picture and recording an identification record corresponding to the picture to be identified, wherein the identification record comprises the picture ID of the picture to be identified and the user identification noun input by the user;
the weighting module is used for judging whether a user identification noun input by a user is matched with the known picture or not according to the known picture and the picture noun thereof and setting a weighting score for the identification record according to the matching times with the known picture;
and the identification module is used for identifying the picture nouns of the picture to be identified according to all recorded identification records corresponding to the picture to be identified and the weighted scores of the identification records.
Corresponding to the method, the receiving module is also used for recording the result of whether the user successfully logs in this time;
then, the weighting module also sets an additional weighting score for the identification record according to the number of times of successful continuous login of the user; the weighted score of the identified record further includes the additional weighted score.
Corresponding to the method, the weighting module is also used for deleting the identification records with the weighting scores smaller than or equal to the set threshold value.
Correspondingly to the method, the weighting module is further configured to modify the weighting score according to the user historical credit score, where the modification formula is as follows:
F＝round((F0+Y+Z)/3，2)
wherein F is the modified weighted score, F0For the weighted score before correction, Y is the user's historical credit score and Z is the base score.
Correspondingly to the method, the recognition module recognizes the picture nouns of the picture to be recognized according to all recorded recognition records and the weighted scores thereof corresponding to the picture to be recognized, and executes the following operations:
acquiring M identification records with weighting scores ranked at the top in all identification records corresponding to the picture to be identified, and merging the identification records of the same user identification nouns to obtain merged identification records, wherein the merged identification records comprise the picture ID of the picture to be identified, the corresponding user identification nouns, the times of the same user identification nouns and the weighted average score;
and screening out the combined user identification nouns with the maximum times of the same user identification nouns as the picture nouns of the picture to be identified according to the combined identification records, taking the combined user identification nouns with the large weighted average score as the picture nouns of the picture to be identified when more than two combined identification records with the maximum times of the same user identification nouns exist, and submitting the picture nouns to manual identification when the combined weighted average scores of the two combined identification records with the maximum times of the same user identification nouns are the same.
Similarly, the picture to be identified corresponds to the display times set for the picture to be identified, the identifying code picture sending module is also used for verifying whether the times of submitting the picture to be identified as the identifying code picture reaches the display times, and when the display times are reached, the picture is not submitted as the identifying code picture.
The above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and those skilled in the art can make various corresponding changes and modifications according to the present invention without departing from the spirit and the essence of the present invention, but these corresponding changes and modifications should fall within the protection scope of the appended claims.
Claims (10)
1. A method for picture recognition based on a user filling in a verification code, the method comprising:
sending at least one picture to be identified and a plurality of known pictures as verification code pictures to a user;
receiving a user identification noun input by a user after identifying the verification code picture, and recording an identification record corresponding to the picture to be identified, wherein the identification record comprises a picture ID of the picture to be identified and the user identification noun input by the user;
judging whether a user identification noun input by a user is matched with a known picture according to the known picture and a picture noun thereof, and setting a weighting score for an identification record according to the matching times with the known picture;
identifying the picture nouns of the picture to be identified according to all recorded identification records corresponding to the picture to be identified and the weighted scores of the identification records;
wherein the setting of the weighted score for the recognition record further comprises:
correcting the weighted score according to the number of successful continuous login of the user and the historical credit score of the user;
the identifying the picture nouns of the picture to be identified according to all recorded identification records and the weighted scores thereof corresponding to the picture to be identified comprises the following steps:
acquiring M identification records with weighting scores ranked at the top in all identification records corresponding to the picture to be identified, and merging the identification records of the same user identification nouns to obtain merged identification records, wherein the merged identification records comprise the picture ID of the picture to be identified, the corresponding user identification nouns, the times of the same user identification nouns and the weighted average score;
and screening out the combined user identification nouns with the maximum times of the same user identification nouns as the picture nouns of the picture to be identified according to the combined identification records, taking the combined user identification nouns with the large weighted average score as the picture nouns of the picture to be identified when more than two combined identification records with the maximum times of the same user identification nouns exist, and submitting the picture nouns to manual identification when the combined weighted average scores of the two combined identification records with the maximum times of the same user identification nouns are the same.
2. The method for picture recognition based on user filling out verification code according to claim 1, wherein the modifying the weighted score according to the number of successful logins of the user comprises:
recording the result of whether the user successfully logs in or not;
setting an additional weighted score for the identification record according to the number of times of successful continuous login of the user;
the weighted score of the identified record further includes the additional weighted score.
3. The method as claimed in claim 1 or 2, wherein before identifying the picture nouns of the picture to be identified according to all recorded identification records and their weighted scores corresponding to the picture to be identified, the method further comprises:
and deleting the identification records with the weight scores less than or equal to the set threshold.
4. The method for picture recognition based on user filling out verification code according to claim 1, wherein the weighted score is modified according to user historical credit score, and the modification formula is as follows:
F＝round((F0+Y+Z)/3，2)
wherein F is the modified weighted score, F0For the weighted score before correction, Y is the user's historical credit score and Z is the base score.
5. The method for picture recognition based on user filling in verification code according to claim 1, wherein the picture to be recognized corresponds to the number of display times set for the picture to be recognized, and the sending of the picture to the user includes at least one picture to be recognized and a plurality of known pictures as verification code pictures, and further includes the steps of:
and verifying whether the number of times that the picture to be identified is submitted as the verification code picture reaches the display number, and when the display number is reached, not submitting the picture as the verification code picture.
6. An apparatus for picture recognition based on a user filling in a verification code, the apparatus comprising:
the verification code picture sending module is used for sending at least one picture to be identified and a plurality of known pictures as verification code pictures to a user;
the receiving module is used for receiving a user identification noun input by a user after identifying the verification code picture and recording an identification record corresponding to the picture to be identified, wherein the identification record comprises the picture ID of the picture to be identified and the user identification noun input by the user;
the weighting module is used for judging whether a user identification noun input by a user is matched with the known picture or not according to the known picture and the picture noun thereof and setting a weighting score for the identification record according to the matching times with the known picture;
the recognition module is used for recognizing the picture nouns of the picture to be recognized according to all recorded recognition records corresponding to the picture to be recognized and the weighted scores of the recognition records;
the weighting module is used for correcting the weighting score according to the number of times of successful continuous login of the user and the historical credit score of the user;
the identification module identifies the picture nouns of the picture to be identified according to all recorded identification records and the weighted scores thereof corresponding to the picture to be identified, and executes the following operations:
acquiring M identification records with weighting scores ranked at the top in all identification records corresponding to the picture to be identified, and merging the identification records of the same user identification nouns to obtain merged identification records, wherein the merged identification records comprise the picture ID of the picture to be identified, the corresponding user identification nouns, the times of the same user identification nouns and the weighted average score;
and screening out the combined user identification nouns with the maximum times of the same user identification nouns as the picture nouns of the picture to be identified according to the combined identification records, taking the combined user identification nouns with the large weighted average score as the picture nouns of the picture to be identified when more than two combined identification records with the maximum times of the same user identification nouns exist, and submitting the picture nouns to manual identification when the combined weighted average scores of the two combined identification records with the maximum times of the same user identification nouns are the same.
7. The apparatus for picture recognition based on user filling out authentication code according to claim 6,
the weighting module also sets an additional weighting score for the identification record according to the number of times of successful continuous login of the user; the weighted score of the identified record further includes the additional weighted score.
8. The apparatus for picture recognition based on user filling out verification code according to claim 6 or 7, wherein the weighting module is further configured to delete recognition records with weighting scores less than or equal to a set threshold.
9. The apparatus for picture recognition based on user filling out verification code according to claim 6, wherein the weighting module is further configured to modify the weighting score according to the user's historical credit score, the modification formula is as follows:
F＝round((F0+Y+Z)/3，2)
wherein F is the modified weighted score, F0For the weighted score before correction, Y is the user's historical credit score and Z is the base score.
10. The apparatus as claimed in claim 6, wherein the picture to be recognized corresponds to a number of display times set for the picture to be recognized, and the verification code picture sending module is further configured to verify whether the number of times that the picture to be recognized is submitted as the verification code picture reaches the number of display times, and when the number of display times is reached, the picture is not submitted as the verification code picture.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510683529.2A CN106599671B (en) | 2015-10-20 | 2015-10-20 | Method and device for identifying picture based on user filling verification code |
| PCT/CN2016/101731 WO2017067398A1 (en) | 2015-10-20 | 2016-10-11 | Method and device for identifying pictures based on filling in verification codes by user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510683529.2A CN106599671B (en) | 2015-10-20 | 2015-10-20 | Method and device for identifying picture based on user filling verification code |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106599671A CN106599671A (en) | 2017-04-26 |
| CN106599671B true CN106599671B (en) | 2020-02-07 |
Family
ID=58554792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510683529.2A Active CN106599671B (en) | 2015-10-20 | 2015-10-20 | Method and device for identifying picture based on user filling verification code |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106599671B (en) |
| WO (1) | WO2017067398A1 (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107301342A (en) * | 2017-08-10 | 2017-10-27 | 佛山市三水区彦海通信工程有限公司 | A kind of touch screen unlocking method |
| CN108461129B (en) * | 2018-03-05 | 2022-05-20 | 余夏夏 | Medical image labeling method and device based on image authentication and user terminal |
| CN110808961B (en) * | 2019-10-16 | 2022-02-01 | 上海易点时空网络有限公司 | Data processing method and device for security verification |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101388078A (en) * | 2008-09-27 | 2009-03-18 | 腾讯科技（深圳）有限公司 | Text identification method and device based on verification |
| CN102467653A (en) * | 2010-10-29 | 2012-05-23 | 方正国际软件(北京)有限公司 | Image-text identification method and system |
| CN103186781A (en) * | 2011-12-31 | 2013-07-03 | 北京新媒传信科技有限公司 | Text recognition method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4848206B2 (en) * | 2005-06-03 | 2011-12-28 | 株式会社リコー | Document management system and document management method |
-
2015
- 2015-10-20 CN CN201510683529.2A patent/CN106599671B/en active Active
-
2016
- 2016-10-11 WO PCT/CN2016/101731 patent/WO2017067398A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101388078A (en) * | 2008-09-27 | 2009-03-18 | 腾讯科技（深圳）有限公司 | Text identification method and device based on verification |
| CN102467653A (en) * | 2010-10-29 | 2012-05-23 | 方正国际软件(北京)有限公司 | Image-text identification method and system |
| CN103186781A (en) * | 2011-12-31 | 2013-07-03 | 北京新媒传信科技有限公司 | Text recognition method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106599671A (en) | 2017-04-26 |
| WO2017067398A1 (en) | 2017-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8914862B2 (en) | Cloud identification processing and verification | |
| CN105989268A (en) | Safety access method and system for human-computer identification | |
| CN107682368B (en) | Verification method, client, server and system based on interactive operation | |
| CN107347052B (en) | Method and device for detecting database collision attack | |
| CN108881126B (en) | Method, device and system for verifying verification code, storage medium and computer terminal | |
| CN106599671B (en) | Method and device for identifying picture based on user filling verification code | |
| US9032491B2 (en) | Multi-factor authentication enrollment optimization method and apparatus | |
| CN113127633B (en) | Intelligent conference management method and device, computer equipment and storage medium | |
| CN112686301A (en) | Data annotation method based on cross validation and related equipment | |
| CN105653833A (en) | Method and device for recommending game community | |
| CN110782996A (en) | Construction method and device of medical database, computer equipment and storage medium | |
| CN109194689A (en) | Abnormal behaviour recognition methods, device, server and storage medium | |
| WO2017101703A1 (en) | Method and apparatus for recognizing service request to change mobile phone number | |
| WO2019056501A1 (en) | Personalized wifi hotspot pushing method, device, and storage medium | |
| CN114386013A (en) | Automatic student status authentication method and device, computer equipment and storage medium | |
| WO2020181800A1 (en) | Apparatus and method for predicting score for question and answer content, and storage medium | |
| CN108460049A (en) | A kind of method and system of determining information category | |
| CN110837562A (en) | Case processing method, device and system | |
| CN111078990A (en) | System and method for arranging and recommending resource links | |
| CN114741014A (en) | Webpage form filling method and device | |
| US11020657B1 (en) | Systems and methods for identification and automation of gaming competition reporting and integrity | |
| CN106301880B (en) | Method and equipment for determining network relationship stability and recommending internet service | |
| CN117312683B (en) | Method, system and medium for rapidly adding friends through multiple channels | |
| CN113326368B (en) | Answering data processing method, device, equipment and storage medium | |
| CN107577827B (en) | A kind of method and device of internet information grading |
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 |