Identity authentication system and method based on natural language

Abstract

The invention provides an identity authentication system and method based on a natural language, and the system comprises a processor, a user login module, a text input module, a background collection module, a feature recognition module, a text completion module, a keyboard fingerprint generation module, and a language feature vector generation module. The user login module, the text input module, the background acquisition module, the feature recognition module, the text completion module, the keyboard fingerprint generation module and the language feature vector generation module are respectively connected with the processor. According to the method, input feature recognition, interest word selection, word association, sentiment analysis and other technologies are adopted to distinguish people and machines, the two functions of user login and man-machine verification are integrated, the method can be used for system login, website login, APP login and other aspects, a user does not need to memorize complex passwords or carry out complex picture and character recognition to log in an application system, and the user experience is improved. Identity verification and human-machine verification are unified into one process, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of identity authentication technology, and in particular to a natural language-based identity authentication system and method. Background Art

[0002] Identity authentication is the most basic function of system login, APP service, etc., which is used to identify user identity and prevent abnormal access such as crawlers and network attacks. It mainly adopts password authentication and SMS verification, which has the advantages of mature technology and easy implementation, but has the disadvantages of easy password theft and increased user memory burden. Currently, fingerprint, facial recognition and other biometric-based methods have begun to be used. This method requires the addition of specific hardware equipment, is incompatible with traditional information systems (such as character terminals), and cannot modify feature data after being stolen.

[0003] Human-machine verification that distinguishes whether the login is initiated by the user or accessed by crawler software or background programs is also an important security strategy for Internet applications. Currently, the problem of "I am a human" is solved by deforming pictures and text and selecting blurred pictures of objects. With the development of artificial intelligence, this technology is becoming easier to crack. In order to increase the accuracy of recognition, it is necessary to increase the difficulty of image recognition, but at the same time it also greatly increases the threshold for user login, blocking a large number of legitimate visits from human-machine verification. Therefore, it is necessary to design an identity authentication system based on natural language. Summary of the invention

[0004] The present application provides an identity authentication system and method based on natural language to solve the problems of low recognition efficiency and low recognition accuracy in the prior art, and realizes the purpose of distinguishing between people and machines by using standard input devices such as keyboard, mouse or touch screen, and adopting input feature recognition, interest word selection, word association, sentiment analysis and other technologies.

[0005] The present application provides an identity authentication system based on natural language, the identity authentication system includes a processor, a user login module, a text input module, a background acquisition module, a feature recognition module, a text completion module, a keyboard fingerprint generation module, and a language feature vector generation module, wherein the user login module, the text input module, the background acquisition module, the feature recognition module, the text completion module, the keyboard fingerprint generation module, and the language feature vector generation module are respectively connected to the processor;

[0006] Among them, the user login module is used for the user to input identity information during the first login; the text input module is used to input the carefully designed characters displayed by the system when logging in; the background collection module is used to collect the keystroke rate, error rate, correction rate of each input string, and the error input string modification information of special strings; the feature recognition module identifies the user's interests, career preferences, and emotional state characteristics; the text completion module is used for the user to complete the Internet hot words, industry terms, and emotional phrase fragments displayed by the system; the keyboard fingerprint generation module is used to generate a keyboard fingerprint based on the information collected in the background; the language feature vector generation module is used to generate the user's language feature vector as a supplement to the keyboard fingerprint for customer login credentials.

[0007] Preferably, the natural language-based identity authentication system provided by the present application further includes an adjustment module, wherein the adjustment module is connected to the processor, and the adjustment module is used to fine-tune the keyboard fingerprint and feature vector.

[0008] Preferably, the natural language-based identity authentication system provided by the present application further includes a storage module, which is connected to the processor and is used to store fine-tuned keyboard fingerprints and feature vectors as a basis for the next authentication.

[0009] Preferably, the natural language-based identity authentication system provided by the present application further includes a feature matching module, which is connected to the processor and is used to match the collected feature vectors with features reserved by the customer.

[0010] Preferably, the present application provides a natural language-based identity authentication system, which also includes a human-machine judgment module, which is connected to the processor and is used to further judge whether the features after feature matching are human operations or machine operations.

[0011] Preferably, a method for using a natural language-based identity authentication system comprises the following steps:

[0012] A. The user logs in initially. When logging in, the system displays a carefully designed string of text.

[0013] B. The user then inputs the character text;

[0014] C. At the same time, the background collects the keystroke rate, error rate, correction rate of each input string, and the modification of the wrong input string of special strings to form the user's "keyboard fingerprint";

[0015] D. At the same time, the user completes the network hot words, industry terms, and emotional phrases displayed by the system;

[0016] E. After natural language processing, the background calculates the user's interests, occupational preferences, and emotional state characteristics, and generates the user's language feature vector, which is used as a supplement to the keyboard fingerprint for customer login credentials;

[0017] F. The feature matching module is used to match the collected feature vectors with the features reserved by the customer;

[0018] G. The human-machine judgment module further judges and identifies the matched features;

[0019] H. If the verification is successful, it is determined to be a human login, and the original keyboard fingerprint and feature vector are fine-tuned and stored as the basis for the next authentication;

[0020] I. If the verification fails, it is judged as machine login.

[0021] Preferably, the feature matching module matching process is as follows:

[0022] a. Obtain multiple images after feature extraction;

[0023] b. Construct feature vectors. Use the BRIEF algorithm to randomly compare pixels in the feature point image block area. If the pixel value of the first pixel in a pair of pixels is greater than the pixel value of the second pixel, it is recorded as 1, otherwise it is recorded as 0. This process is repeated to obtain binary feature vectors of all feature point image block areas. The feature vectors contain information about the image block area around the feature point.

[0024] c. Use a multi-probe local sensitive hashing algorithm to map the binary feature vector of the target image and the binary feature vector of the comparison image to different hash buckets through multiple hash functions, and use the detection sequence of the multi-probe local sensitive hashing algorithm to compare the binary feature vectors in different hash buckets to obtain an initial matching pair of the target image and the comparison image;

[0025] d. Call the RANSAC algorithm function and use the homography matrix to eliminate mismatches in the initial matching pairs to obtain accurate image matching results.

[0026] Beneficial effects:

[0027] (1) The working principle of the present invention is simple. It uses standard input devices such as keyboards, mice or touch screens, and adopts input feature recognition, interest word selection, word association, sentiment analysis and other technologies to distinguish between people and machines, and combines the two functions of user login and human-machine verification into one. It can be used for system login, website login, APP login and other aspects. Users do not need to remember complex passwords or perform complex image and text recognition to log in to the application system. Identity authentication and human-machine verification are unified into one process, thereby improving user experience.

[0028] (2) The present invention adopts a pure software solution and does not require the addition of dedicated hardware devices such as fingerprint devices, face cameras, etc., and supports the transformation of traditional information systems. The process from input collection to feature acquisition is irreversible, and even if the feature data is obtained, the input behavior cannot be forged, which has high security.

[0029] The above description is only an overview of the technical solution of the embodiment of the present application. In order to more clearly understand the technical means of the embodiment of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present application, a brief introduction will be given below to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0031] Figure 1 It is the working principle diagram of the present invention;

[0032] Figure 2 It is the work flow chart of the present invention;

[0033] Figure 3 This is a flow chart of an embodiment of the present invention;

[0034] Explanation of the accompanying drawings: processor 1, user login module 2, text input module 3, background collection module 4, feature recognition module 5, text completion module 6, keyboard fingerprint generation module 7, language feature vector generation module 8, the user login module 2, text input module 3, background collection module 4, feature recognition module 5, text completion module 6, keyboard fingerprint generation module 7, language feature vector generation module 8, whole module 9, storage module 10, feature matching module 11, human-machine judgment module 12. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used in the specification of the application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification, claims and drawings of this application are intended to cover non-exclusive inclusions.

[0037] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase "embodiments" in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0038] The directional words appearing in the following description are all directions shown in the drawings, and do not limit the specific structure of the present application. For example, in the description of the present application, the directions or positional relationships indicated by the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present application.

[0039] In addition, the expressions of indicated directions such as the X direction, the Y direction, and the Z direction used to illustrate the operation and construction of the components of the present embodiment are not absolute but relative, and although these indications are appropriate when the components are in the positions shown in the figures, when these positions change, these directions should be interpreted differently to correspond to the changes.

[0040] In addition, the terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order, and may explicitly or implicitly include one or more of the features.

[0041] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, the "connection" or "connection" of a mechanical structure may refer to a physical connection. For example, the physical connection may be a fixed connection, such as a fixed connection through a fixing member, such as a fixed connection through a screw, bolt or other fixing member; the physical connection may also be a detachable connection, such as a mutual snap-on or snap-fit ​​connection; the physical connection may also be an integral connection, such as a connection formed by welding, bonding or integral molding. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0042] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0043] See also Figure 1-Figure 3 , the present application discloses an identity authentication system based on natural language, the identity authentication system comprises a processor 1, a user login module 2, a text input module 3, a background acquisition module 4, a feature recognition module 5, a text completion module 6, a keyboard fingerprint generation module 7, and a language feature vector generation module 8, wherein the user login module 2, the text input module 3, the background acquisition module 4, the feature recognition module 5, the text completion module 6, the keyboard fingerprint generation module 7, and the language feature vector generation module 8 are respectively connected to the processor 1;

[0044] Among them, the user login module is used for the user to input identity information during the first login; the text input module is used to input the carefully designed characters displayed by the system when logging in; the background collection module is used to collect the keystroke rate, error rate, correction rate of each input string, and the error input string modification information of special strings; the feature recognition module identifies the user's interests, career preferences, and emotional state characteristics; the text completion module is used for the user to complete the Internet hot words, industry terms, and emotional phrase fragments displayed by the system; the keyboard fingerprint generation module is used to generate a keyboard fingerprint based on the information collected in the background; the language feature vector generation module is used to generate the user's language feature vector as a supplement to the keyboard fingerprint for customer login credentials. When a user logs in for the first time, the system displays a carefully designed string of characters (such as characters used for input errors, repeated characters, etc.). The user enters the text, and the background collects the typing rate, error rate, correction rate of each input string, and the modification of the incorrect input string of special strings, and finally forms the user's "keyboard fingerprint"; the system displays fragments of Internet buzzwords, industry terms, emotional phrases, etc., allowing the user to complete the text. After natural language processing, the background calculates the user's interests, career preferences, emotional state and other features, generates the user's language feature vector, and uses it as a supplement to the keyboard fingerprint for customer login credentials. The above process can be repeated many times until the collected features are clear enough.

[0045] The present invention further comprises an adjustment module 9, which is connected to the processor 1 and is used for fine-tuning the keyboard fingerprint and the feature vector.

[0046] The present invention further comprises a storage module 10, which is connected to the processor 1 and is used to store the fine-tuned keyboard fingerprint and feature vector as a basis for the next authentication.

[0047] The present invention further comprises a feature matching module 11, which is connected to the processor 1 and is used for matching the collected feature vectors with the features reserved by the customer.

[0048] In addition, the present invention further comprises a human-machine judgment module 12, wherein the human-machine judgment module 12 is connected to the processor 1, and the human-machine judgment module is used to further judge whether the features after feature matching are human operation or machine operation.

[0049] Working principle: A method for using a natural language based identity authentication system, comprising the following steps:

[0050] A. The user logs in initially. When logging in, the system displays a carefully designed string of text.

[0051] B. The user then inputs the character text;

[0052] C. At the same time, the background collects the keystroke rate, error rate, correction rate of each input string, and the modification of the wrong input string of special strings to form the user's "keyboard fingerprint";

[0053] D. At the same time, the user completes the network hot words, industry terms, and emotional phrases displayed by the system;

[0054] E. After natural language processing, the background calculates the user's interests, occupational preferences, and emotional state characteristics, and generates the user's language feature vector, which is used as a supplement to the keyboard fingerprint for customer login credentials;

[0055] F. The feature matching module is used to match the collected feature vectors with the features reserved by the customer;

[0056] G. The human-machine judgment module further judges and identifies the matched features;

[0057] H. If the verification is successful, it is determined to be a human login, and the original keyboard fingerprint and feature vector are fine-tuned and stored as the basis for the next authentication;

[0058] I. If the verification fails, it is judged as machine login.

[0059] Among them, the matching process of the feature matching module is as follows:

[0060] a. Obtain multiple images after feature extraction;

[0061] b. Construct feature vectors. Use the BRIEF algorithm to randomly compare pixels in the feature point image block area. If the pixel value of the first pixel in a pair of pixels is greater than the pixel value of the second pixel, it is recorded as 1, otherwise it is recorded as 0. This process is repeated to obtain binary feature vectors of all feature point image block areas. The feature vectors contain information about the image block area around the feature point.

[0062] c. Use a multi-probe local sensitive hashing algorithm to map the binary feature vector of the target image and the binary feature vector of the comparison image to different hash buckets through multiple hash functions, and use the detection sequence of the multi-probe local sensitive hashing algorithm to compare the binary feature vectors in different hash buckets to obtain an initial matching pair of the target image and the comparison image;

[0063] d. Call the RANSAC algorithm function and use the homography matrix to eliminate mismatches in the initial matching pairs to obtain accurate image matching results.

[0064] The present invention adopts a pure software solution and does not require the addition of dedicated hardware equipment such as fingerprint devices, face cameras, etc., and supports the transformation of traditional information systems. It is irreversible from input collection to feature acquisition, and even if the feature data is obtained, the input behavior cannot be forged, and it has high security.

[0065] (2) In summary, the working principle of the present invention is simple. It uses standard input devices such as keyboards, mice or touch screens, and adopts input feature recognition, interest word selection, word association, sentiment analysis and other technologies to distinguish between people and machines, and combines the two functions of user login and human-machine verification into one. It can be used for system login, website login, APP login and other aspects. Users do not need to remember complex passwords or perform complex image and text recognition to log in to the application system. Identity authentication and human-machine verification are unified into one process, thereby improving user experience.

[0066] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A natural language based identity authentication system, characterized in that: The identity authentication system comprises a processor (1), a user login module (2), a text input module (3), a background acquisition module (4), a feature recognition module (5), a text completion module (6), a keyboard fingerprint generation module (7), and a language feature vector generation module (8); the user login module (2), the text input module (3), the background acquisition module (4), the feature recognition module (5), the text completion module (6), the keyboard fingerprint generation module (7), and the language feature vector generation module (8) are respectively connected to the processor (1); Among them, the user login module is used for the user to input identity information during the first login; the text input module is used to input the carefully designed characters displayed by the system when logging in; the background collection module is used to collect the keystroke rate, error rate, correction rate of each input string, and the error input string modification information of special strings; the feature recognition module identifies the user's interests, career preferences, and emotional state characteristics; the text completion module is used for the user to complete the Internet hot words, industry terms, and emotional phrase fragments displayed by the system; the keyboard fingerprint generation module is used to generate a keyboard fingerprint based on the information collected in the background; the language feature vector generation module is used to generate the user's language feature vector as a supplement to the keyboard fingerprint for customer login credentials.

2. According to claim 1, a natural language based identity authentication system is characterized in that: It also includes an adjustment module (9), which is connected to the processor (1) and is used to fine-tune the keyboard fingerprint and feature vector.

3. The natural language based identity authentication system according to claim 1, characterized in that: It also includes a storage module (10), which is connected to the processor (1) and is used to store the fine-tuned keyboard fingerprint and feature vector as a basis for the next authentication.

4. The natural language based identity authentication system according to claim 1, characterized in that: It also includes a feature matching module (11), which is connected to the processor (1) and is used to match the collected feature vector with the features reserved by the customer.

5. The natural language based identity authentication system according to claim 1, characterized in that: It also includes a human-machine judgment module (12), which is connected to the processor (1) and is used to further judge whether the features after feature matching are human operation or machine operation.

6. A method for using a natural language based identity authentication system as claimed in claim 1, characterized in that: The method of use includes the following steps: A. The user logs in initially. When logging in, the system displays a carefully designed string of text. B. The user then inputs the character text; C. At the same time, the background collects the keystroke rate, error rate, correction rate of each input string, and the modification of the wrong input string of special strings to form the user's "keyboard fingerprint"; D. At the same time, the user completes the network hot words, industry terms, and emotional phrases displayed by the system; E. After natural language processing, the background calculates the user's interests, occupational preferences, and emotional state characteristics, and generates the user's language feature vector, which is used as a supplement to the keyboard fingerprint for customer login credentials; F. The feature matching module is used to match the collected feature vectors with the features reserved by the customer; G. The human-machine judgment module further judges and identifies the matched features; H. If the verification is successful, it is determined to be a human login, and the original keyboard fingerprint and feature vector are fine-tuned and stored as the basis for the next authentication; I. If the verification fails, it is judged as machine login.

7. The method for using a natural language based identity authentication system according to claim 6, characterized in that: The matching process of the feature matching module is as follows: a. Obtain multiple images after feature extraction; b. Construct feature vectors. Use the BRIEF algorithm to randomly compare pixels in the feature point image block area. If the pixel value of the first pixel in a pair of pixels is greater than the pixel value of the second pixel, it is recorded as 1, otherwise it is recorded as 0. This process is repeated to obtain binary feature vectors of all feature point image block areas. The feature vectors contain information about the image block area around the feature point. c. Use a multi-probe local sensitive hashing algorithm to map the binary feature vector of the target image and the binary feature vector of the comparison image to different hash buckets through multiple hash functions, and use the detection sequence of the multi-probe local sensitive hashing algorithm to compare the binary feature vectors in different hash buckets to obtain an initial matching pair of the target image and the comparison image; d. Call the RANSAC algorithm function and use the homography matrix to eliminate mismatches in the initial matching pairs to obtain accurate image matching results.

Images