WO2018166291A1 - 一种基于多因素交叉验证的用户签到身份识别方法 - Google Patents

一种基于多因素交叉验证的用户签到身份识别方法 Download PDF

Info

Publication number
WO2018166291A1
WO2018166291A1 PCT/CN2018/072532 CN2018072532W WO2018166291A1 WO 2018166291 A1 WO2018166291 A1 WO 2018166291A1 CN 2018072532 W CN2018072532 W CN 2018072532W WO 2018166291 A1 WO2018166291 A1 WO 2018166291A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
information
sign
module
verification
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2018/072532
Other languages
English (en)
French (fr)
Inventor
李超
戴明弟
曾庆田
赵中英
岳广飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong University of Science and Technology
Original Assignee
Shandong University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shandong University of Science and Technology filed Critical Shandong University of Science and Technology
Publication of WO2018166291A1 publication Critical patent/WO2018166291A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
    • G07C1/10—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people together with the recording, indicating or registering of other data, e.g. of signs of identity
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation

Definitions

  • the invention belongs to the field of information technology, and particularly relates to a user sign-in identification method based on multi-factor cross-validation.
  • the traditional manual sign-in program can't solve the behavior of others signing up. As the number of activities increases, it is impossible for the manager to fully count the attendance of each activity, and the behavior of others signing can't be prevented.
  • Fingerprint identification and sign-in technology collects fingerprints to collect attendance.
  • the cost of fingerprint identification equipment is high and cannot cover all courses.
  • the pressure on the server for statistical work is extremely high.
  • the efficiency of fingerprint admission technology is extremely low, which seriously affects users. Activity time.
  • the current face recognition technology includes two types of schemes: one is to extract facial key points according to the processing result of the face image, and then to compare and analyze; the other is to call the face comparison interface based on the open platform API interface and obtain the analysis result. .
  • the first method uses the image as a starting point to extract the facial image features.
  • the features that can be used by the face recognition system are generally classified into visual features, pixel statistical features, face image transform coefficient features, face image algebra features, and the like. Face feature extraction is performed on certain features of the face and is the process of modeling the face.
  • the methods of face feature extraction are summarized into two categories: one is based on knowledge representation methods; the other is based on algebraic features or statistical learning.
  • the feature data of the extracted face image is searched and matched with the feature template stored in the database.
  • a threshold when the similarity exceeds the threshold, the result of the matching is output.
  • Face recognition is to compare the face features to be recognized with the obtained face feature templates, and judge the identity information of the faces according to the degree of similarity. This process is divided into two categories: one is confirmation, one-to-one image comparison process; the other is recognition, which is a one-to-many image matching process.
  • the second type of method calls the interface of the face verification function through the open platform API, and judges whether it is the same person according to the returned result.
  • the advantages of this method are low development cost, simple and fast operation, and high efficiency.
  • the face recognition rate of the open platform is not stable, and the system overhead of calling the interface is large. There is no remedial action when the result of the acquisition fails.
  • Single-factor sign-in technology is a simple check-in verification based on the time of sign-in or check-in. However, it is prone to cheating and there are more vulnerabilities.
  • the present invention proposes a user sign-in identification method based on multi-factor cross-validation, which is reasonable in design, overcomes the deficiencies of the prior art, and has good effects.
  • a multi-factor cross-validation user sign-in identification method adopts a user basic information management module, a user activity management module, a user sign-in information sensing module, a user sign-in decision module, an intelligent verification module and a statistical analysis module;
  • the user sign-in identification method based on multi-factor cross-validation includes the following steps:
  • Step 1 The user basic information management module completes the management of the user's personal information, and the user activity management module realizes the entry and management of the activity information, and realizes the information perception through the user's sign-in information sensing module;
  • Step 2 Perform a check-in decision by the user signing in the decision module, and calculate the probability of successful sign-in of the user under multiple factors;
  • Step 3 Perform smart verification through the intelligent verification module, and intelligently extract the check-in information of some users for secondary verification;
  • Step 4 Perform statistical analysis on the user's check-in information through the statistical analysis module, and feed back the analysis result to the intelligent verification module to implement management of the user attendance information.
  • the user basic information management module is configured to acquire various identity information of the user, and obtain the face image of the user as the verification credential;
  • a user activity management module configured to complete entry, editing, deletion, and update of user activity information
  • the user sign-in information sensing module is configured to complete the perception of the user's check-in information, including the perception of location information, the perception of the activity scene or image information, the perception of the fingerprint information, and the perception of the activity information;
  • the user sign-in decision module is configured to make a decision on the overall check-in
  • the intelligent verification module is configured to perform secondary extraction verification of the user after performing weighted sorting on a user who has successfully checked in but has a relatively low accuracy rate, and a user who has not signed in successfully but has a relatively high accuracy rate;
  • the statistical analysis module is configured to implement statistics and analysis of the user's check-in information, and to keep track of the attendance of the activity and the participation status of the user.
  • the information perception includes location information perception, image information perception, fingerprint information perception, and activity information perception.
  • step 2 the method specifically includes the following steps:
  • Step 2.1 Build a check-in factor decision tree
  • Step 2.2 Using the perceptual information, under the rules of the decision tree, obtain the decision tree leaf node, that is, the decision result;
  • Step 2.3 Output the decision result.
  • step 3 the method specifically includes the following steps:
  • Step 3.1 Select a verification rule
  • Step 3.2 Perform multi-factor cross-validation
  • Step 3.3 Perform secondary verification based on the check-in accuracy and feedback results.
  • step 4 the method specifically includes the following steps:
  • Step 4.1 Store statistical results
  • Step 4.2 Feed the statistical results back to the decision mechanism of the intelligent verification module and the decision tree.
  • the invention realizes low-cost and high-efficiency application on the basis of ensuring the reliability and accuracy of the user's sign-in information through multi-source related information sensing, multi-factor cross-validation technology and intelligent verification technology; the specifics are as follows:
  • the invention utilizes multiple sensing technologies of the intelligent terminal to realize the perception of multi-dimensional sign-in information such as location, scene, fingerprint and course information, thereby effectively improving the accuracy of the sign-in, and also Avoid the appearance of cheating.
  • Intelligent verification function The invention not only provides a solution for sign-in, but also provides an intelligent verification function, which is based on the output of the decision-making mechanism, realizes random selection of the sign-in user, and performs actual verification, and the function intelligently lines The combination of upper and lower lines ensures the authenticity and reliability of the check-in data.
  • FIG. 1 is a flow chart of a method for user sign-in identification based on multi-factor cross-validation according to the present invention.
  • FIG. 2 is a structural diagram of a check-in factor decision tree in the present invention.
  • Figure 3 is a schematic block diagram of the present invention.
  • FIG. 4 is a functional block diagram of the present invention.
  • Solving these three problems can avoid and filter out many users' cheating and signing behaviors (for example, users can check in at other nearby locations; users can also let other users replace authentication through network file transfer, etc.).
  • the positioning function can be realized by technologies such as IP positioning, GPS positioning, and wireless network positioning. Since the IP positioning technology is simple to implement, it requires an independent fixed IP address. For the data connection of the mobile device and the dynamic IP allocated by the wireless network function, the IP positioning technology cannot obtain an accurate location.
  • the GPS positioning technology is the main acquisition and positioning method for smart mobile devices. However, the disadvantage of GPS positioning technology is that the positioning is offset when the device is located indoors. Therefore, how to make GPS positioning more accurate is a key problem to be solved. Positioning through the wireless network is the best positioning technology for mobile devices that need to obtain location in the classroom, but the wireless network positioning workload is huge and the cost is high. Therefore, solving the problem of accurate and reliable GPS positioning is particularly critical.
  • Identification technology for sign-in subject images Since each picture contains many interference factors, such as background, brightness, and changes in face, it is not possible to use simple image comparison techniques. Through the image key point extraction technology, the contour of the face, the relative position and shape of the facial features are extracted as key information, and the accuracy of the face verification is greatly improved. Therefore, how to solve the key point extraction and comparison of face is also a key issue to complete the sign-in function.
  • Fingerprint identification technology of sign-in subject With the rapid development of intelligent mobile terminal equipment, fingerprint recognition technology is gradually popularized. At present, fingerprint recognition technology is mainly used for unlocking and payment of mobile terminals. Fingerprints can be applied to sign-in areas with their unique characteristics. Therefore, how to apply fingerprint recognition technology to the sign-in field becomes an important part of individual information perception during the sign-in process.
  • Multi-factor verification includes location, image, content and other factors.
  • the location factor needs to be based on IP positioning, base station positioning, GPS positioning, wireless network positioning and other positioning methods.
  • the image factors include the perception of the sign-in user and the perception of the surrounding environment, and comprehensively judge the authenticity of the sign-in user and the sign-in environment based on the data obtained from the image perception. A variety of factors are crossed and comprehensively judged, and the check-in accuracy after verification is obtained, thereby determining the sign-in result.
  • the traditional method is to perform secondary verification by manual.
  • the method is based on random extraction by the user, but there is a certain error and the validity is poor.
  • How to verify the probability based on multi-factor decision-making and intelligently extract the user based on the information such as the sign-in failure of the accumulated data, and improve the validity of the verification user by the analysis of the comprehensive factors becomes the key technical problem of the present invention.
  • the invention adopts "sensing-decision-verification-statistical analysis" as the main line of technology, and realizes the function of signing in the user activity.
  • the invention firstly utilizes the sensing technology of the mobile terminal to realize the positioning of the user's location, the acquisition of the activity information (time, location, content), the acquisition of the user's avatar information, the acquisition of the user's fingerprint information, and the like; secondly, using the acquired multi-dimensional sign-in Information, construct multi-factor sign-in judgment mechanism, realize user verification of sign-in information, this mechanism can effectively avoid various cheating methods; again, use intelligent verification algorithm to realize intelligent extraction of verification users; finally, the present invention also provides administrators with An effective statistical analysis function to monitor and count the user's active attendance.
  • the flow chart of the present invention is shown in FIG. 1
  • the detailed overall technical solution is shown in FIG. 3 .
  • the invention obtains all the information of the sign-in from the perception; then the decision-making, calculates the probability of the user's sign-in success under multiple factors; then verifies, intelligently extracts some users' sign-in information for secondary determination; finally analyzes and analyzes the user's sign-in information. . Therefore, the present invention is based on the basic content of the scheme, and gives detailed functional modules from a functional point of view, and gives detailed implementation technical solutions for each functional module.
  • the main functional modules of the present invention (shown in FIG. 4) include: a user information management module, a user course information management module, a user check-in information sensing module, a user check-in decision module, a smart verification module, and a statistical analysis module.
  • the module mainly accomplishes the goal of acquiring the identity information of the user and acquiring the face image of the user as the verification credential technology.
  • the main problem to be solved is to quickly obtain information identifying the identity as a basis for future sign-in.
  • the invention adopts the database storage technology and the file storage technology to complete together.
  • the user information registration technology uses database connection technology to store all basic information in a database, such as name, gender, age, interest and other basic information
  • the user face image collection technology uses file stream technology to store the picture during the service period.
  • the file storage path is stored in the corresponding user basic information tuple in the database.
  • the face registration information will be easily obtained.
  • the module mainly completes the functions of inputting, editing, deleting and updating user activity information, and is also a key module for sign-in verification. It also includes the activity setting module of the administrator terminal.
  • the module mainly completes the sensing technology of the user's sign-in information, including the perception of the location information, the perception of the active scene (image) information, the perception of the fingerprint information, and the perception of the activity information.
  • the specific implementation method is as follows.
  • IP location information The basic principle of IP location is to estimate the geographic location by using the IP device's name, registration information, or delay information. Since the IP positioning technology is not very accurate, it can be used as one of the conditions for fuzzy judgment or probability judgment.
  • the GPS global satellite positioning and navigation system was initially used only for military purposes, and later converted to civilian use is widely used in business and scientific research. Traditional GPS positioning technology works well outdoors, but it is less effective indoors or where satellite signals cannot be covered. More and more WiFi hotspots (also known as APs, or wireless routers) are more likely to receive at least one AP signal at any point in the city. As long as the hotspot is powered on, no matter how it is encrypted, it will definitely send a signal to the surroundings.
  • WiFi hotspots also known as APs, or wireless routers
  • the signal contains the unique global ID of this hotspot. Even if it is far from this hotspot, the connection cannot be established, but it can still be heard. Hotspots are generally rarely changed and are relatively fixed. In this way, the positioning terminal only needs to listen to the hot spots in the vicinity, detect the signal strength of each hot spot, and then send the information to the Skyhook server. Based on this information, the server queries the coordinates recorded by each hotspot in the database, and performs operations to know the specific location of the client, and then tells the client the coordinates. As long as the number of AP signals received is more, the positioning will be more accurate.
  • Perception of active scene (image) information In scene information perception, image recognition and processing techniques are mainly used. Image recognition technology may be based on the main features of the image. Each image has its characteristics, such as the letter A has a sharp point, P has a circle, and the center of Y has an acute angle. Studies of eye movements during image recognition have shown that the line of sight is always concentrated on the main features of the image, that is, where the contour of the image is most curved or the direction of the outline changes abruptly, where the amount of information is greatest. Moreover, the scanning route of the eye is always transferred from one feature to another in turn. It can be seen that in the image recognition process, the perception mechanism must exclude the input redundant information and extract the key information. At the same time, there must be a mechanism in the brain responsible for integrating information, which can organize the information obtained in stages into a complete perceptual image.
  • Fingerprint recognition includes both overall recognition and local recognition. Overall identification refers to features that are directly observable by the human eye. Including the shape, pattern area, core points, triangle points and lines. On the basis of long-term practice, striated fingerprint experts generally divide fingerprints into three categories according to the direction and distribution of ridge lines—ring, bow, and spiral.
  • the pattern area that is, the area on the fingerprint that includes the overall feature, from which it is possible to distinguish which type of fingerprint the file belongs to. Some fingerprint recognition algorithms only use data from the pattern area, while others use the complete fingerprint obtained.
  • the core point is located at the progressive center of the fingerprint texture, which serves as a reference point when reading fingerprints and comparing fingerprints. Many algorithms are based on core points, that is, they can only process and identify fingerprints with core points.
  • the triangle point is located at the first branch point or breakpoint from the core point, or the two stripe roads converge, isolate, turn, or point to these singular points.
  • the triangle point provides the beginning of the count tracking of the fingerprint texture.
  • the number of lines is the number of fingerprint lines in the pattern area.
  • a local feature refers to a feature of a node on a fingerprint. These nodes with certain characteristics are called detail features or feature points. Two fingerprints often have the same overall characteristics, but their details are not exactly the same. Fingerprint lines are not continuous, smooth and straight, but often break, fork or turn. These breakpoints, bifurcation points, and turning points are called "feature points”. These feature points provide confirmation information about the uniqueness of the fingerprint. The most typical ones are the endpoints and the bifurcation points. Others include the divergence points and isolated points. , ring points, short lines, etc.
  • the parameters of the feature points include: direction (the node can be oriented in a certain direction), curvature (describes the speed at which the direction of the grain changes), and position (the position of the node is described by x/y coordinates, which may be absolute or relative to Triangle point or feature point).
  • Activity information contains multiple attributes of the activity, including name, time, location, number of people, and so on. At the same time, according to the feedback information of the number of participating users, collecting the evaluation of activities, attributes and other characteristics, through the methods of data mining and natural language processing to improve the activity attribute label, the curriculum is diversified perception and performance.
  • the module is the core and key of the present invention.
  • the invention is based on a multi-factor decision-making mechanism, applying the idea of a decision tree, and making decisions on the overall sign-in.
  • the specific implementation ideas are as follows: First, the check-in factor decision tree is constructed. The structure of the tree is shown in Figure 2. Then, using the perceptual information, the decision tree leaf nodes are obtained under the rules of the decision tree, that is, the decision result; The result is output.
  • the module is mainly based on the output of the check-in verification, and performs weighted sorting on the users who have successfully checked in, but the accuracy is relatively low and the sign-in is unsuccessful, but the accuracy is relatively high, and then the user's secondary extraction verification is performed.
  • the module is mainly for administrator users, and realizes statistics and analysis of user check-in information, so as to keep track of the attendance of the event and the participation status of the user. At the same time, the statistical results of this module are also fed back to our intelligent verification module and decision tree decision-making mechanism.
  • the key points and points of protection of the present invention mainly have the following aspects:
  • Sign-in information sensing technology based on mobile terminal utilizes the characteristics of the intelligent mobile terminal to realize the perception of related factors, including location, scene (image), fingerprint and course information.
  • the multiple positioning technologies such as GPS, WiFi and IP address, the user's location information is accurately perceived.
  • Real-time perception of scene (image) information is realized by camera photographing technology.
  • the fingerprint identification technology is used to realize the fingerprint identification of the sign-in user. Use the perception of time information to achieve the association of course information.
  • the multi-source real-time perception of the sign-in information of the mobile terminal is completed. So as to avoid the occurrence of things on behalf of the user.
  • Multi-factor decision-making mechanism based on decision tree structure:
  • the invention's perception of the sign-in information of the mobile terminal includes many dimensions, including location, scene, fingerprint and course information. However, the acquisition of different dimensions has certain error and noise, therefore, it is required Comprehensive consideration of the various factors to achieve the accuracy of the check-in judgment.
  • the invention adopts the structure of the decision tree, and determines the multi-factors for determining whether the sign-in is successful, and can ensure that the accuracy of the check-in determination is improved in the absence of certain factors.
  • the overall process of the user attendance verification technology based on the intelligent terminal innovatively proposes, based on the sensing technology of the intelligent mobile terminal, the multi-factor decision making mechanism and the check-in verification process under the smart verification technology, and implements the process and Applies to the user's check-in system.
  • the invention applies the idea of "perception-decision-verification-analysis" to the teaching of a smart campus. It not only realizes the informationization of the campus, but also improves the efficiency of classroom teaching. It can also be applied to company attendance, which not only reduces the cost of attendance equipment, but also provides accurate attendance for out-of-office employees.
  • Perception of multiple information of intelligent terminals Traditional check-in verification often uses only one or two kinds of information to perform check-in.
  • the present invention utilizes multiple sensing technologies of intelligent terminals to realize location, scene, fingerprint and course information. Dimensional sign-in information perception. Effectively improve the accuracy of the check-in, while avoiding the emergence of cheating.
  • Decision-making mechanism based on decision tree structure Multi-dimensional decision not only brings the validity and accuracy of verification, but also challenges the perception of the terminal. Not all terminals will contain the perceptual information of all dimensions. Therefore, the advantage of the present invention over other technologies is that the decision method of the decision tree structure is adopted, and the lack of relevant factors is allowed on the basis of ensuring the accuracy of the check-in determination. Therefore, the decision mechanism has a certain flexibility.
  • Intelligent verification function The present invention not only provides a solution for sign-in, but also provides an intelligent verification function compared to the prior art. This function is based on the output of the decision mechanism, enabling random selection of the sign-in user for actual verification. This feature cleverly combines online and offline to ensure the authenticity and reliability of the check-in data.
  • the solution of the present invention registers and adds an activity (in the experiment: the course) by means of experimental simulation, and completes the check-in function within the time limit of the check-in. Through comparison experiments, it is verified that the combination of location, content and time is accurate and accurate.
  • the check-in result table is shown in Table 1.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Collating Specific Patterns (AREA)

Abstract

一种基于图像、指纹、位置、时间、内容的多因素交叉验证的用户身份识别技术，属于信息技术领域，首先通过用户基本信息管理模块完成用户个人信息的管理、通过用户活动管理模块实现活动信息的录入和管理、通过用户签到信息感知模块实现信息的感知；其次通过用户签到决策模块进行签到决策；再次通过智能验证模块进行智能验证；最后通过统计分析模块对用户签到信息进行统计分析。通过多源相关信息感知技术、多因素交叉验证技术和智能随机验证及反馈技术，在保证用户签到信息的可靠性与准确性的基础上，实现了低成本高效率的应用；避免了用户作弊、迟到行为的发生，对督促用户养成自觉自律的良好习惯具有重要意义。

Description

一种基于多因素交叉验证的用户签到身份识别方法 技术领域
本发明属于信息技术领域，具体涉及一种基于多因素交叉验证的用户签到身份识别方法。
背景技术
现有签到技术包括传统人工签到、指纹识别签到、人脸识别签到等方案；其技术缺点主要体现在以下几个方面：
传统人工签到方案无法解决他人代签的行为，随着活动任务不断增多，对于管理者来说，无法完全对每一次活动的出勤情况进行统计，而且，他人代签的行为无法预防。
指纹识别签到技术是通过用户录取指纹来统计出勤情况，而指纹识别设备成本较高，无法覆盖全部课程，对于实现统计工作的服务器端压力极大，同时，指纹录取技术效率极低，严重影响用户活动时间。
当前人脸识别技术包括两类方案：一类是根据人脸图像的处理结果进行面部关键点提取，而后进行对比分析；另一类是通过基于开放平台API接口调用人脸对比接口并获取分析结果。
第一类方法以图像作为起点，对其中的人脸图像特征进行提取。人脸识别系统可使用的特征通常分为视觉特征、像素统计特征、人脸图像变换系数特征、人脸图像代数特征等。人脸特征提取就是针对人脸的某些特征进行的，是对人脸进行特征建模的过程。人脸特征提取的方法归纳起来分为两大类：一种是基于知识的表征方法；另外一种是基于代数特征或统计学习的表征方法。
提取的人脸图像的特征数据与数据库中存储的特征模板进行搜索匹配，通过设定一个阈值，当相似度超过这一阈值，则把匹配得到的结果输出。人脸识别就是将待识别的人脸特征与已得到的人脸特征模板进行比较，根据相似程度对人脸的身份信息进行判断。这一过程又分为两类：一类是确认，是一对一进行图像比较的过程；另一类是辨认，是一对多进行图像匹配对比的过程。
第二类方法通过开放平台API，调用其人脸验证功能的接口，根据返回的结果判断是否为同一人。此方法优点是开发成本低，操作简单快捷，效率高。但开放平台的人脸识别率并不稳定，调用接口的系统开销较大。当获取结果失败时，无补救措施。
综合分析两类方法，第一类方法更具有针对性，可以根据需求进行个性化设计。但是开发难度较大，涉及的领域较为广泛。第二类方法开发难度低，适用性强。但从整体来看本发明所提出的技术与思路是创新的，是现有签到方法无法实现的。
单因素签到技术，是基于时间签到或者签到的位置进行简单的签到验证，但是，容易出 现作弊，签到漏洞较多。
发明内容
针对现有技术中存在的上述技术问题，本发明提出了一种基于多因素交叉验证的用户签到身份识别方法，设计合理，克服了现有技术的不足，具有良好的效果。
一种基于多因素交叉验证的用户签到身份识别方法，采用用户基本信息管理模块、用户活动管理模块、用户签到信息感知模块、用户签到决策模块、智能验证模块和统计分析模块；
所述的基于多因素交叉验证的用户签到身份识别方法，具体包括如下步骤：
步骤1：通过用户基本信息管理模块完成用户个人信息的管理，通过用户活动管理模块实现活动信息的录入和管理，通过用户签到信息感知模块实现信息的感知；
步骤2：通过用户签到决策模块进行签到决策，计算多因素下用户签到成功的概率；
步骤3：通过智能验证模块进行智能验证，智能抽取部分用户的签到信息进行二次验证；
步骤4：通过统计分析模块对用户签到信息进行统计分析，并将分析结果反馈至智能验证模块，实现对用户考勤信息的管理。
优选地，用户基本信息管理模块，被配置为用于获取用户的各项身份信息，同时获取本人人脸图像作为验证凭据；
用户活动管理模块，被配置为用于完成用户活动信息的录入、编辑、删除、更新；
用户签到信息感知模块，被配置为用于完成用户签到信息的感知，包括位置信息的感知、活动场景或图像信息的感知、指纹信息的感知和活动信息的感知；
用户签到决策模块，被配置为用于对整体签到进行决策；
智能验证模块，被配置为用于对签到成功但准确率相对较低的用户，以及签到未成功但准确率相对较高的用户进行加权排序后进行用户的二次抽取验证；
统计分析模块，被配置为用于实现用户签到信息的统计和分析，随时掌握活动的出勤情况和用户的参与状态。
优选地，在步骤1中，所述信息感知包括位置信息感知、图像信息感知、指纹信息感知以及活动信息感知。
优选地，在步骤2中，具体包括如下步骤：
步骤2.1：构建签到因素决策树；
步骤2.2：利用感知信息，在决策树的规则下，获取决策树叶子节点，即决策结果；
步骤2.3：将决策结果输出。
优选地，在步骤3中，具体包括如下步骤：
步骤3.1：选取验证规则；
步骤3.2：进行多因素交叉验证；
步骤3.3：基于签到准确率以及反馈结果进行二次验证。
优选地，在步骤4中，具体包括如下步骤：
步骤4.1：存储统计结果；
步骤4.2：将统计结果反馈给智能验证模块和决策树的决策机制中。
本发明所带来的有益技术效果：
本发明通过多源相关信息感知、多因素交叉验证技术和智能验证技术，在保证用户签到信息的可靠性与准确性的基础上，实现了低成本高效率的应用；具体如下：
1、智能终端的多项信息的感知：本发明利用智能终端的多项感知技术，实现位置、场景、指纹和课程信息等多维度签到信息的感知，有效地提高了签到的准确性，同时也避免了作弊现象的出现。
2、基于决策树结构的签到决策机制：多维度的判定既带来了验证的有效性和准确性，同时也为终端的感知提出了挑战，本发明采用决策树结构的判定方法，在保证签到判定准确性的基础上，允许存在相关因素的缺失，该判定机制具有一定的灵活性。
3、智能的验证功能：本发明不仅为签到提供了解决方案，还提供了智能的验证功能，该功能基于决策机制的输出，实现签到用户的随机选取，进行实际验证，该功能巧妙的将线上和线下相结合，保证了签到数据的真实性和可靠性。
附图说明
图1为本发明一种基于多因素交叉验证的用户签到身份识别方法的流程图。
图2为本发明中签到因素决策树的结构图。
图3为本发明的原理框架图。
图4为本发明的功能模块图。
具体实施方式
下面结合附图以及具体实施方式对本发明作进一步详细说明：
1、本发明要解决的技术问题
本发明需要解决的关键技术问题包括三个方面：
第一、智能移动终端信息的感知技术；
第二、多因素交叉验证技术；
第三、智能验证技术。
解决这三个方面的问题能够避免和过滤掉诸多用户作弊代签行为(例如，用户可以在较近的其他位置进行签到；用户也可以通过网络文件传输让其他用户代替验证等等)。
因此，本发明要解决的具体关键问题是：
关键技术问题1：智能移动终端多源相关信息的感知技术
位置信息的准确识别技术：定位功能可采用IP定位、GPS定位、无线网络定位等技术实现。由于IP定位技术实现简单，但需要独立固定的IP地址，对于移动设备的数据连接以及无线网络功能所分配的动态IP来说，IP定位技术无法获取准确位置。而GPS定位技术，是智能移动设备的主要获取定位方法。但GPS定位技术的缺点是当设备位于室内时，定位会发生偏移。因此，如何使GPS定位更加精确，是需要解决的关键难题。而通过无线网络进行定位对于需要在教室内获取位置的移动设备来说，是最佳的定位技术，但获取无线网络定位工作量庞大，成本高。因此，解决GPS定位的准确可靠性问题，显得尤为关键。
签到主体图像的识别技术：由于每一张图片都包含许多干扰因素，比如背景、亮度以及人脸的变化等，因此，使用单纯的图片对比技术无法满足需要。而通过图片关键点提取技术，将人脸的轮廓，五官的相对位置以及形状作为关键信息进行提取，并进行对比，人脸验证的准确性将大幅度提高。因此，如何解决人脸关键点提取与对比也是完成签到功能的关键问题。
签到主体的指纹识别技术：随着移动终端设备智能化的高速发展，指纹识别技术正在逐步普及，目前指纹识别技术主要用于移动终端的解锁、支付等方面。指纹以其唯一性的特点，可以将其应用到签到领域。因此，如何将指纹识别技术应用到签到领域成为签到过程中，个体信息感知的重要部分。
关键技术问题2：多因素交叉验证技术
单一因素很难准确验证用户签到的真实性，因此需要综合多种感知信息，对信息进行处理并根据处理结果的综合分析，来判断验证结果。
多因素验证包括位置、图像、内容等因素，其中位置因素需要根据IP定位，基站定位，GPS定位，无线网络定位等多种定位方式，基于位置吻合度交叉综合验证。图像因素包括对签到用户的感知以及周围环境的感知，根据对图像感知获得的数据综合判断签到用户以及签到环境的真实性。多种因素交叉综合判断，获取验证后的签到准确度，以此判定签到结果。
关键技术问题3：智能验证技术
为了保证签到验证的准确性，传统的方法是通过人工进行二次验证，该方法是基于用户随机抽取，但是，存在一定的误差，且有效性较差。如何基于多因素决策中验证概率，且基于累积数据有签到失败等信息的用户进行智能抽取，通过综合因素的分析，提高验证用户的有效性成为本发明的关键技术问题。
2、本发明技术方案的基本内容
本发明以“感知-决策-验证-统计分析”为技术主线，实现在用户活动签到功能。
本发明首先利用移动终端的感知技术，实现用户位置的定位、活动信息(时间、地点、内容)的获取、用户头像信息的获取、用户指纹信息的获取等；其次，利用获取到的多维度签到信息，构建多因素签到判定机制，实现用户签到信息的验证，该机制能够有效避免各种作弊方法；再次，利用智能验证算法，实现验证用户的智能抽取；最后，本发明还为管理员端提供了有效的统计分析功能，监测和统计用户的活动出勤情况。本发明的流程图如图1所示，详细的整体技术方案如图3所示。
3、本发明技术方案的详细阐述
本发明从感知出发，获取签到的所有信息；之后是决策，计算多因素下用户签到成功的概率；然后验证，智能抽取部分用户签到信息进行二次判定；最后分析，对用户签到信息进行统计分析。因此，本发明基于方案的基本内容，从功能角度出发给出详细的功能模块，并对每个功能模块给出详细的实现技术方案。本发明的主要功能模块(如图4所示)包括：用户信息管理模块、用户课程信息管理模块、用户签到信息感知模块、用户签到决策模块、智能验证模块和统计分析模块。
3.1、用户基本信息管理模块
该模块主要完成目标是获取用户的各项身份信息，同时获取本人人脸图像作为验证凭据的技术。主要解决的问题是快速获取标识身份的信息，作为日后签到的依据。本发明采用的是数据库存储技术与文件存储技术共同完成。其中，用户信息注册技术利用数据库连接技术，将所有基本信息存入数据库，例如姓名，性别，年龄，兴趣等基本信息；用户脸部图像采集技术利用文件流技术，将图片存储于服务期内，同时，将文件存储路径存入数据库中对应用户基本信息元组。对应后面的签到验证模块，人脸注册信息将会很容易获取。
3.2、用户活动管理模块
该模块主要完成用户活动信息的录入、编辑、删除、更新等功能，同时也是签到验证的关键模块。其中还包括：管理员终端的活动设置模块。
3.3、用户签到信息感知模块
该模块主要完成用户签到信息的感知技术，包括位置信息的感知、活动场景(图像)信息的感知、指纹信息的感知和活动信息的感知。具体的实现方法如下。
位置信息的感知：IP定位的基本原理是,利用IP设备的名字、注册信息或时延信息等来估计其地理位置。由于IP定位技术精度不是很高，因此，可以将其作为模糊判断或概率判断的条件之一。GPS全球卫星定位导航系统，开始时只用于军事目的，后转为民用被广泛应用于商业和科学研究上。传统的GPS定位技术在户外运转良好，但在室内或卫星信号无法覆盖的地方效果较差。WiFi热点(也就是AP，或者无线路由器)越来越多，在城市中更趋向于空 间任何一点都能接收到至少一个AP的信号。热点只要通电，不管它怎么加密的，都一定会向周围发射信号。信号中包含此热点的唯一全球ID。即使距离此热点比较远，无法建立连接，但还是可以侦听到它的存在。热点一般都是很少变位置的，比较固定。这样，定位端只要侦听一下附近都有哪些热点，检测一下每个热点的信号强弱，然后把这些信息发送给Skyhook的服务器。服务器根据这些信息，查询每个热点在数据库里记录的坐标，进行运算，就能知道客户端的具体位置了，再把坐标告诉客户端。只要收到的AP信号越多，定位就会越准。
活动场景(图像)信息的感知：在场景信息感知中，主要采用了图像识别与处理技术。图像识别技术可能是以图像的主要特征为基础的。每个图像都有它的特征,如字母A有个尖，P有个圈、而Y的中心有个锐角等。对图像识别时眼动的研究表明，视线总是集中在图像的主要特征上，也就是集中在图像轮廓曲度最大或轮廓方向突然改变的地方，这些地方的信息量最大。而且眼睛的扫描路线也总是依次从一个特征转到另一个特征上。由此可见，在图像识别过程中，知觉机制必须排除输入的多余信息,抽出关键的信息。同时,在大脑里必定有一个负责整合信息的机制，它能把分阶段获得的信息整理成一个完整的知觉映象。
在人类图像识别系统中，对复杂图像的识别往往要通过不同层次的信息加工才能实现。对于熟悉的图形,由于掌握了它的主要特征，就会把它当作一个单元来识别，而不再注意它的细节了。这种由孤立的单元材料组成的整体单位叫做组块，每一个组块是同时被感知的。
指纹信息的感知：当今，移动智能设备几乎都具有指纹识别传感器，其中包括电容式传感器以及超声波传感器等等。指纹识别包括总体识别与局部识别两方面。总体识别是指那些用人眼直接就可以观察到的特征。包括纹形、模式区、核心点、三角点和纹数等。纹形指纹专家在长期实践的基础上，根据脊线的走向与分布情况一般将指纹分为三大类——环型、弓形、螺旋形。模式区即指纹上包括了总体特征的区域，从此区域就能够分辨出指纹是属于哪一种类型的。有的指纹识别算法只使用模式区的数据，有的则使用所取得的完整指纹。核心点位于指纹纹路的渐进中心，它在读取指纹和比对指纹时作为参考点。许多算法是基于核心点的，即只能处理和识别具有核心点的指纹。三角点位于从核心点开始的第一个分叉点或者断点，或者两条纹路会聚处、孤立点、折转处，或者指向这些奇异点。三角点提供了指纹纹路的计数跟踪的开始之处。纹数即模式区内指纹纹路的数量。在计算指纹的纹路时，一般先连接核心点和三角点，这条连线与指纹纹路相交的数量即可认为是指纹的纹数。
局部特征是指指纹上节点的特征，这些具有某种特征的节点称为细节特征或特征点。两枚指纹经常会具有相同的总体特征，但它们的细节特征，却不可能完全相同。指纹纹路并不是连续的、平滑笔直的，而是经常出现中断、分叉或转折。这些断点、分叉点和转折点就称为"特征点"，就是这些特征点提供了指纹唯一性的确认信息，其中最典型的是终结点和分叉 点，其他还包括分歧点、孤立点、环点、短纹等。特征点的参数包括：方向(节点可以朝着一定的方向)、曲率(描述纹路方向改变的速度)、位置(节点的位置通过x/y坐标来描述，可以是绝对的，也可以是相对于三角点或特征点的)。
活动信息感知：活动信息包含了活动的多个属性，其中包括名称，时间，地点，人数等等。同时根据参与用户人数的反馈信息，收集活动的评价，属性等多方面的特点，通过数据挖掘与自然语言处理等方法完善活动属性标签，对课程进行多样化感知与表现。
3.4、用户签到决策模块
该模块是本发明的核心也是关键，本发明基于多因素的决策机制，应用决策树的思想，对整体签到进行决策。具体的实现思路如下：首先，构建签到因素决策树，该树的结构如图2所示；然后利用感知信息，在决策树的规则下，获取到决策树叶子节点，即决策结果；最后将决策结果输出。
3.5、智能验证模块
该模块主要是基于签到验证的输出结果，对签到成功，但准确率相对较低的和签到未成功，但准确率相对较高的用户进行加权排序，而后，进行用户的二次抽取验证。
3.6、统计分析模块
该模块主要面向管理员用户，实现用户签到信息的统计和分析，从而随时掌握活动的出勤情况和用户的参与状态。同时，该模块的统计结果也反馈到我们的智能验证模块和决策树的决策机制中。
4、本发明的关键点和欲保护点
本发明关键点和欲保护点主要有以下几个方面：
基于移动终端的签到信息感知技术：本发明利用智能移动终端的特点，实现签到相关因素的感知，包括位置，场景(图像)，指纹和课程信息等。通过GPS，WiFi和IP地址等多重定位技术，实现用户位置信息的精准感知。利用摄像头拍照技术，实现场景(图像)信息的实时感知。利用指纹识别技术，实现签到用户的指纹识别。利用时间信息的感知，实现课程信息的关联。最后，完成移动终端签到信息的多源实时感知。从而避免用户代签到事情的发生。
基于决策树结构的多因素决策机制：本发明对移动终端签到信息的感知包括很多维度，包括位置、场景、指纹和课程信息等，然而，不同维度的获取具有一定的误差和噪音，因此，需要综合考虑各因素的情况，实现签到判定的准确性。本发明采用决策树的结构，将决定签到是否成功的多因素进行树形化判定，就可以保证在某些因素缺失的情况下，提高签到判定的准确性。
基于智能终端的用户考勤验证技术的整体流程：本发明创新性的提出了，基于智能移动终端的感知技术、多因素决策判定机制和智能验证技术下的签到验证流程，并将该流程进行实现且应用到用户的签到系统中。本发明把“感知-判定-验证-分析”的思想应用到智慧校园的教学当中。既实现了校园的信息化，同时又提高了课堂教学的效率。还可以应用到公司考勤当中，既减少考勤设备的成本，还能够为外出员工提供准确的考勤。
5、与现有的技术相比，本发明的优点主要体现以下几个方面：
智能终端的多项信息的感知：传统的签到验证，往往只采用一种或两种信息进行签到的判定，本发明利用智能终端的多项感知技术，实现位置、场景、指纹和课程信息等多维度签到信息的感知。有效的提高了签到的准确性，同时也避免了作弊现象的出现。
基于决策树结构的签到决策机制：多维度的判定既带来了验证的有效性和准确性，同时也为终端的感知提出了挑战，并不是所有的终端都会包含所有维度的感知信息。因此，本发明优于其他技术的地方就是：采用决策树结构的判定方法，在保证签到判定准确性的基础上，允许存在相关因素的缺失。因此，该判定机制具有一定的灵活性。
智能的验证功能：本发明不仅为签到提供了解决方案，和之前的技术相比，本发明还提供了智能的验证功能。该功能基于决策机制的输出，实现签到用户的随机选取，进行实际验证。该功能巧妙的将线上和线下相结合，保证了签到数据的真实性和可靠性。
6、本发明是否经过实验、模拟、使用而证明可行，结果如何
本发明的方案通过实验模拟的方式，注册并添加活动(实验中是：课程)，在签到时限内，完成签到功能。通过对比实验，验证了位置、内容、时间相结合的方式进行签到准确无误。签到结果表如表1所示。
表1 签到结果表
Figure PCTCN2018072532-appb-000001
Figure PCTCN2018072532-appb-000002

Claims (6)

  1. 一种基于多因素交叉验证的用户签到身份识别方法，其特征在于：采用用户基本信息管理模块、用户活动管理模块、用户签到信息感知模块、用户签到决策模块、智能验证模块和统计分析模块；
    所述的基于多因素交叉验证的用户签到身份识别方法，具体包括如下步骤：
    步骤1：通过用户基本信息管理模块完成用户个人信息的管理，通过用户活动管理模块实现活动信息的录入和管理，通过用户签到信息感知模块实现信息的感知；
    步骤2：通过用户签到决策模块进行签到决策，计算多因素下用户签到成功的概率；
    步骤3：通过智能验证模块进行智能验证，智能抽取部分用户的签到信息进行二次验证；
    步骤4：通过统计分析模块对用户签到信息进行统计分析，并将分析结果反馈至智能验证模块，实现对用户考勤信息的管理。
  2. 根据权利要求1所述的基于多因素交叉验证的用户签到身份识别方法，其特征在于：
    用户基本信息管理模块，被配置为用于获取用户的各项身份信息，同时获取本人人脸图像作为验证凭据；
    用户活动管理模块，被配置为用于完成用户活动信息的录入、编辑、删除、更新；
    用户签到信息感知模块，被配置为用于完成用户签到信息的感知，包括位置信息的感知、活动场景或图像信息的感知、指纹信息的感知和活动信息的感知；
    用户签到决策模块，被配置为用于对整体签到进行决策；
    智能验证模块，被配置为用于对签到成功但准确率相对较低的用户，以及签到未成功但准确率相对较高的用户进行加权排序后进行用户的二次抽取验证；
    统计分析模块，被配置为用于实现用户签到信息的统计和分析，随时掌握活动的出勤情况和用户的参与状态。
  3. 根据权利要求1所述的基于多因素交叉验证的用户签到身份识别方法，其特征在于：在步骤1中，所述信息感知包括位置信息感知、图像信息感知、指纹信息感知以及活动信息感知。
  4. 根据权利要求1所述的基于多因素交叉验证的用户签到身份识别方法，其特征在于：在步骤2中，具体包括如下步骤：
    步骤2.1：构建签到因素决策树；
    步骤2.2：利用感知信息，在决策树的规则下，获取决策树叶子节点，即决策结果；
    步骤2.3：将决策结果输出。
  5. 根据权利要求1所述的基于多因素交叉验证的用户签到身份识别方法，其特征在于：在步骤3中，具体包括如下步骤：
    步骤3.1：选取验证规则；
    步骤3.2：进行多因素交叉验证；
    步骤3.3：基于签到准确率以及反馈结果进行二次验证。
  6. 根据权利要求1所述的基于多因素交叉验证的用户签到身份识别方法，其特征在于：在步骤4中，具体包括如下步骤：
    步骤4.1：存储统计结果；
    步骤4.2：将统计结果反馈给智能验证模块和决策树的决策机制中。
PCT/CN2018/072532 2017-03-13 2018-01-13 一种基于多因素交叉验证的用户签到身份识别方法 Ceased WO2018166291A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710144517.1 2017-03-13
CN201710144517.1A CN107067486A (zh) 2017-03-13 2017-03-13 一种基于多因素交叉验证的用户签到身份识别方法

Publications (1)

Publication Number Publication Date
WO2018166291A1 true WO2018166291A1 (zh) 2018-09-20

Family

ID=59622260

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/072532 Ceased WO2018166291A1 (zh) 2017-03-13 2018-01-13 一种基于多因素交叉验证的用户签到身份识别方法

Country Status (2)

Country Link
CN (1) CN107067486A (zh)
WO (1) WO2018166291A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108960219A (zh) * 2018-09-28 2018-12-07 广州翠花信息科技有限公司 一种采用签到机制的人脸识别系统
CN110046870A (zh) * 2019-04-16 2019-07-23 中山大学 一种基于地理位置和人脸特征的签到方法及系统
US20220253751A1 (en) * 2020-05-09 2022-08-11 Northwestern Polytechnical University Human identification method based on expert feedback mechanism
CN115496469A (zh) * 2022-09-23 2022-12-20 福州大学 一种面向移动终端线下签到的可疑度计算方法
CN116311645A (zh) * 2022-08-15 2023-06-23 武汉警官职业学院 一种人员信息查验方法及系统

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107067486A (zh) * 2017-03-13 2017-08-18 山东科技大学 一种基于多因素交叉验证的用户签到身份识别方法
CN107705381A (zh) * 2017-08-25 2018-02-16 宁波纷享软件科技有限公司 学生考勤监控设备与控制方法
CN109274683A (zh) * 2018-10-30 2019-01-25 国网安徽省电力有限公司信息通信分公司 一种交叉组合认证系统及其认证方法
CN109636935A (zh) * 2018-12-07 2019-04-16 苏州科达科技股份有限公司 人员签到方法、装置及存储介质
CN109636936B (zh) * 2018-12-12 2021-05-28 泰康保险集团股份有限公司 一种考勤系统、方法、介质和电子设备
CN109829688A (zh) * 2019-01-04 2019-05-31 平安科技（深圳）有限公司 客户端、服务器、移动考勤方法及计算机可读存储介质
US20230239291A1 (en) * 2020-03-30 2023-07-27 Iq Works Limited Multi step authentication method and system
CN115104094A (zh) * 2020-06-05 2022-09-23 华为技术有限公司 用于自动验证因素注册的设备和方法以及多因素验证装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102819875A (zh) * 2012-08-01 2012-12-12 福州瑞芯微电子有限公司 基于人脸识别与gps的考勤系统及其方法
CN102819877A (zh) * 2012-08-18 2012-12-12 吴迪 基于位置的考勤系统及方法
CN103337100A (zh) * 2013-06-20 2013-10-02 汉王科技股份有限公司 一种生物特征考勤方法和移动设备
US20150332275A1 (en) * 2012-12-20 2015-11-19 Unicredit S.P.A. Method for biometric recognition with clustering of registered data for pos/atm applications
CN105740683A (zh) * 2016-01-20 2016-07-06 北京信安盟科技有限公司 基于多因素、多引擎、人机相结合的身份验证方法与系统
CN107067486A (zh) * 2017-03-13 2017-08-18 山东科技大学 一种基于多因素交叉验证的用户签到身份识别方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7424618B2 (en) * 2001-03-14 2008-09-09 Paladin Electronic Services, Inc. Biometric access control and time and attendance network including configurable system-on-chip (CSOC) processors with embedded programmable logic
CN103729902B (zh) * 2012-10-15 2016-06-29 金蝶软件（中国）有限公司 考勤签到方法、考勤登记方法、考勤终端和考勤服务器
CN106056087A (zh) * 2016-06-03 2016-10-26 济源维恩科技开发有限公司 一种基于多种模式识别的签到方法
CN106375279A (zh) * 2016-08-22 2017-02-01 珠海格力电器股份有限公司 基于移动设备的考勤方法、装置和系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102819875A (zh) * 2012-08-01 2012-12-12 福州瑞芯微电子有限公司 基于人脸识别与gps的考勤系统及其方法
CN102819877A (zh) * 2012-08-18 2012-12-12 吴迪 基于位置的考勤系统及方法
US20150332275A1 (en) * 2012-12-20 2015-11-19 Unicredit S.P.A. Method for biometric recognition with clustering of registered data for pos/atm applications
CN103337100A (zh) * 2013-06-20 2013-10-02 汉王科技股份有限公司 一种生物特征考勤方法和移动设备
CN105740683A (zh) * 2016-01-20 2016-07-06 北京信安盟科技有限公司 基于多因素、多引擎、人机相结合的身份验证方法与系统
CN107067486A (zh) * 2017-03-13 2017-08-18 山东科技大学 一种基于多因素交叉验证的用户签到身份识别方法

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108960219A (zh) * 2018-09-28 2018-12-07 广州翠花信息科技有限公司 一种采用签到机制的人脸识别系统
CN110046870A (zh) * 2019-04-16 2019-07-23 中山大学 一种基于地理位置和人脸特征的签到方法及系统
CN110046870B (zh) * 2019-04-16 2023-10-20 中山大学 一种基于地理位置和人脸特征的签到方法及系统
US20220253751A1 (en) * 2020-05-09 2022-08-11 Northwestern Polytechnical University Human identification method based on expert feedback mechanism
CN116311645A (zh) * 2022-08-15 2023-06-23 武汉警官职业学院 一种人员信息查验方法及系统
CN115496469A (zh) * 2022-09-23 2022-12-20 福州大学 一种面向移动终端线下签到的可疑度计算方法

Also Published As

Publication number Publication date
CN107067486A (zh) 2017-08-18

Similar Documents

Publication Publication Date Title
WO2018166291A1 (zh) 一种基于多因素交叉验证的用户签到身份识别方法
CN104581630B (zh) 一种基于位置服务和二维码技术的自助防作弊签到方法
CN113515988B (zh) 掌纹识别方法、特征提取模型训练方法、设备及介质
WO2020000906A1 (zh) 人脸识别身份验证方法、装置、电子设备
Kamelia et al. Real-time online attendance system based on fingerprint and GPS in the smartphone
WO2018192406A1 (zh) 身份验证方法及装置、存储介质
CN104167025A (zh) 基于动态人脸识别与wifi定位的移动考勤系统及其方法
CN105206041B (zh) 一种考虑时序dbscan的智能手机轨迹链簇识别方法
CN107483416A (zh) 身份验证的方法及装置
CN105512627A (zh) 一种关键点的定位方法及终端
CN107633558A (zh) 一种基于人像与身份证比对识别的自助检票方法和设备
CN111639879B (zh) 智能化安保人员信息管理方法、装置及系统、存储介质、服务器
CN109656973B (zh) 一种目标对象关联分析方法及装置
CN103699677A (zh) 一种基于人脸识别技术的罪犯行踪地图绘制系统及其方法
CN109509269A (zh) 一种电子签到方法、计算机可读存储介质及服务器
CN112738725B (zh) 半封闭区域目标人群的实时识别方法、装置、设备和介质
WO2025039693A1 (zh) 业务处理方法、装置、设备、存储介质及程序产品
US20140025624A1 (en) System and method for demographic analytics based on multimodal information
CN113445829B (zh) 一种具备面部识别功能的储物柜智能锁及使用方法
CN107798312A (zh) 一种基于视觉头部检测的自动考勤方法
CN114722365B (zh) 一种身份信息识别的方法、相关装置、设备及存储介质
CN209728746U (zh) 一种基于蓝牙辅助的用户身份识别系统
CN108335029A (zh) 一种基于抽象场景和互信息的广义签到方法与系统
CN119693004B (zh) 公交乘车使用掌静脉和掌纹智慧支付方法、系统及存储介质
CN111400442A (zh) 常驻地址分析方法、装置、设备及可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18767697

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18767697

Country of ref document: EP

Kind code of ref document: A1