Multi-voucher ticket checking device and ticket checking method

Abstract

The invention discloses a multi-voucher ticket checking device and a multi-voucher ticket checking method, and relates to the technical field of ticket checking. According to the multi-voucher ticket checking method, when a passenger checks a ticket, passing voucher state data and passenger ticket checking state data of a passenger waiting to pass are obtained, a passing credibility score is analyzed, and judgment and analysis are carried out on the passing credibility score and a preset credibility score interval; if the passing credibility score of the passenger waiting to pass is out of the preset credibility interval, the passenger is not allowed to pass; if the passing credibility score of the passenger waiting to pass is within a preset credibility interval, analyzing a comprehensive passing score; according to the method, the passing voucher state data and the passenger ticket checking state data of the passengers are acquired, the passing credibility score is comprehensively calculated, and the current ticket checking behavior score and the historical ticket checking behavior score are further combined for analysis, so that the multi-level analysis method can reduce misjudgment and missed judgment, efficient release of legal passengers can be ensured, and the efficiency of ticket checking is improved. Suspicious travelers can be accurately intercepted, and the safety and the intelligent level of the ticket checking system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of ticket checking, and in particular to a multi-certificate ticket checking device and a ticket checking method. Background Art

[0002] With the continuous development of scenarios such as public transportation, park management, and security access control, the ticket checking system plays a crucial role in modern intelligent access management. Currently, traditional ticket checking methods mainly rely on single certificate verification means, such as QR code scanning, IC card / NFC identification, or biometric identification (such as face recognition, fingerprint recognition, etc.). Although these technologies have improved the ticket checking efficiency to a certain extent, there are still many challenges in actual applications. For example, certificates may be forged, borrowed, or shared, making it difficult for the system to accurately identify the actual access behavior of passengers. In addition, single identity verification methods are difficult to prevent abnormal access behaviors such as tailgating, quick following and proxy swiping, and abnormal gait fraud, thus posing security risks.

[0003] In recent years, in order to improve the security and accuracy of the ticket checking system, some systems have introduced multiple identity verification mechanisms, such as combining biometric identification with certificate comparison to improve the uniqueness of the identity of passing personnel. However, these systems still lack in-depth analysis of passengers' ticket checking behaviors and are difficult to effectively judge the gait, hand operation stability, certificate holding situation, etc. of passengers during the access process, resulting in great limitations in abnormal behavior recognition.

[0004] The prior art, such as the multi-certificate ticket checking method, device, electronic device and medium disclosed in the invention patent application with the publication number of CN118447585A, wherein the method includes: obtaining user information and certificate information of the user terminal; judging whether the network with the cloud management platform is unobstructed; if the network is unobstructed, verifying the user terminal according to the user information or the certificate information. The multi-certificate ticket checking method provided by this application improves the ticket checking efficiency and user experience of the shuttle bus in the offline state of the shuttle bus device.

[0005] Based on the above solutions, it is found that the limitations of the prior art at least include the following problems. First, the current multi-certificate ticket checking method mainly relies on the matching degree of the certificate itself for identity verification, such as QR code, face recognition or magnetic card comparison, etc., without fully combining the dynamic behavior characteristics of passengers during the ticket checking process, such as gait, hand movements, face angles, etc. In this way, when a passenger engages in proxy swiping, following access, or abnormal operations, the system is difficult to identify the risks, resulting in unauthorized passengers possibly successfully passing the ticket check, bringing security risks. In addition, the existing methods usually rely on fixed rule matching and lack an adaptive mechanism for historical behavior analysis. Summary of the Invention

[0006] In view of the deficiencies of the prior art, the present invention provides a multi-certificate ticket checking device and a ticket checking method, which solve the problems of lack of comprehensive evaluation of passengers' ticket checking behaviors in the prior art, resulting in insufficient safety and accuracy.

[0007] To achieve the above objectives, the present invention is realized through the following technical solutions: A multi-certificate ticket checking method includes the following steps: When a passenger conducts ticket checking, obtain the status data of the passing certificate and the passenger ticket checking status data of the passenger to be passed, and perform preprocessing respectively; Based on the preprocessed status data of the passing certificate and the passenger ticket checking status data, analyze the passing credibility score of the passenger to be passed, and perform judgment analysis with a preset credibility score interval; If the passing credibility score of the passenger to be passed is outside the preset credibility interval, do not release; If the passing credibility score of the passenger to be passed is within the preset credibility interval, analyze the current ticket checking behavior score and the historical ticket checking behavior score of the passenger to be passed, and perform comprehensive analysis to obtain the comprehensive passing score of the passenger to be passed; Perform judgment analysis on the comprehensive passing score of the passenger to be passed with a preset passing interval; If the comprehensive passing score of the passenger to be passed is outside the preset passing interval, do not release; If the comprehensive passing score of the passenger to be passed is within the preset passing interval, give release; Among them, the specific formula for calculating the comprehensive passing score of the passenger to be passed is as follows: ; where is the comprehensive passing score of the passenger to be passed, is the current ticket checking behavior score of the passenger to be passed, is the current ticket checking behavior adjustment coefficient stored in the database, is the current ticket checking behavior influence coefficient stored in the database, is the historical ticket checking behavior score of the passenger to be passed, is the historical ticket checking behavior adjustment coefficient stored in the database, is the historical ticket checking behavior influence coefficient stored in the database, is the natural constant, is the ticket checking behavior combined influence coefficient stored in the database.

[0008] Further, the status data of the passing certificate includes the passing certificate matching degree, the internal capacitance value of the passing certificate, and the internal magnetic field strength value of the passing certificate, and the passenger ticket checking status data includes the ticket checking hand pressure value, the ticket checking hand friction value, and the ticket checking face angle value.

[0009] Furthermore, the specific steps for analyzing the passage credibility score of the passenger to pass are as follows: Obtain the ticket-checking hand heat distribution index, ticket-checking hand heat distribution reference index, internal capacitance reference value of the passage permit, and internal magnetic field strength reference value of the passage permit of the passenger to pass; comprehensively analyze the passage permit status data and passenger ticket-checking status data of the passenger to pass in combination with the ticket-checking hand heat distribution index, ticket-checking hand heat distribution reference index, internal capacitance reference value of the passage permit, and internal magnetic field strength reference value of the passage permit respectively to obtain the passage credibility score of the passenger to pass.

[0010] Furthermore, the specific steps for obtaining the ticket-checking hand heat distribution index of the passenger to pass are as follows: For the ticket-checking hand of the passenger to pass, randomly select several measurement position points and obtain the hand measurement temperature values respectively; comprehensively analyze the hand measurement temperature values of each measurement position point of the ticket-checking hand of the passenger to pass to obtain the ticket-checking hand heat distribution index of the passenger to pass.

[0011] Furthermore, the specific formula for calculating the passage credibility score of the passenger to pass is as follows: ; where is the passage credibility score of the passenger to pass, is the passage permit matching degree of the passenger to pass, is the matching adjustment coefficient stored in the database, is the ticket-checking hand pressure value of the passenger to pass, is the pressure adjustment coefficient stored in the database, is the ticket-checking hand friction value of the passenger to pass, is the friction adjustment coefficient stored in the database, is the natural constant, is the ticket-checking hand heat distribution index of the passenger to pass, is the ticket-checking hand heat distribution reference index of the passenger to pass, is the heat distribution adjustment coefficient stored in the database, is the ticket-checking face angle value of the passenger to pass, is the angle adjustment coefficient stored in the database, is the internal capacitance value of the passage permit of the passenger to pass, is the internal capacitance reference value of the passage permit of the passenger to pass, is the capacitance adjustment coefficient stored in the database, is the internal magnetic field strength value of the passage permit of the passenger to pass, is the internal magnetic field strength reference value of the passage permit of the passenger to pass, is the magnetic field strength adjustment coefficient stored in the database.

[0012] Further, the specific steps for analyzing the current ticket-checking behavior score of the to-be-passed passenger are as follows: Obtain the current movement state data of the to-be-passed passenger at several time points in the ticket-checking area, and analyze the current movement state parameter set of the to-be-passed passenger. The current movement state parameter set includes the current movement speed index, the current movement acceleration index, the current arm swing amplitude index, and the current arm swing amplitude change index; Read the passage credibility score of the to-be-passed passenger, and conduct a comprehensive analysis in combination with the current movement state parameter set of the to-be-passed passenger to obtain the current ticket-checking behavior score of the to-be-passed passenger.

[0013] Further, the current movement state data includes the movement speed value and the arm swing amplitude value. The specific steps for analyzing the current movement state parameter set of the to-be-passed passenger are as follows: Read the movement speed values of the to-be-passed passenger at several time points in the ticket-checking area, and conduct a comprehensive analysis to obtain the current movement speed index of the to-be-passed passenger; Conduct an acceleration analysis on the movement speed values of the to-be-passed passenger at several time points in the ticket-checking area to obtain several groups of movement acceleration values of the to-be-passed passenger in the ticket-checking area, and conduct a comprehensive analysis to obtain the current movement acceleration index of the to-be-passed passenger; Read the arm swing amplitude values of the to-be-passed passenger at several time points in the ticket-checking area, and conduct a comprehensive analysis to obtain the current arm swing amplitude index of the to-be-passed passenger; Conduct a change analysis on the arm swing amplitude values of the to-be-passed passenger at several time points in the ticket-checking area to obtain several groups of arm swing amplitude change rates of the to-be-passed passenger in the ticket-checking area, and conduct a comprehensive analysis to obtain the current arm swing amplitude change index of the to-be-passed passenger.

[0014] Further, the specific steps for calculating the current ticket-checking behavior score and the historical ticket-checking behavior score of the to-be-passed passenger are as follows: ; where is the current ticket-checking behavior score of the to-be-passed passenger, is the passage credibility score of the to-be-passed passenger, is the natural constant, is the current movement speed index of the to-be-passed passenger, is the movement speed influence coefficient stored in the database, is the current movement acceleration index of the to-be-passed passenger, is the movement acceleration influence coefficient stored in the database, is the current arm swing amplitude index of the to-be-passed passenger, is the swing amplitude influence coefficient stored in the database, is the current arm swing amplitude change index of the to-be-passed passenger, is the swing amplitude change influence coefficient stored in the database.

[0015] Further, the specific steps for analyzing the historical ticket-checking behavior score of the passenger to pass through are as follows: Obtain the historical sequential data of the historical movement states of the passenger to pass through in the ticket-checking area for several times and perform preprocessing. The historical sequential data of the historical movement states includes the historical movement speed values and historical arm swing amplitude values at several historical time points; perform comprehensive analysis on the historical sequential data of the historical movement states of the passenger to pass through in the ticket-checking area for several times after preprocessing to obtain the historical movement speed index, historical movement acceleration index, historical arm swing amplitude index, and historical arm swing amplitude change index of the passenger to pass through in the ticket-checking area; perform comprehensive analysis on the historical movement speed index, historical movement acceleration index, historical arm swing amplitude index, and historical arm swing amplitude change index of the passenger to pass through in the ticket-checking area for several times to obtain the historical ticket-checking behavior score of the passenger to pass through.

[0016] A multi-certificate ticket-checking device includes: a data acquisition module, configured to acquire the passing certificate status data and passenger ticket-checking status data of the passenger to pass through when the passenger performs ticket-checking and perform preprocessing on each of them; a credibility analysis module, configured to analyze the passing credibility score of the passenger to pass through based on the preprocessed passing certificate status data and passenger ticket-checking status data; a credibility judgment module, configured to perform judgment analysis on the passing credibility score of the passenger to pass through and a preset credibility score range. If the passing credibility score of the passenger to pass through is outside the preset credibility range, the passenger shall not be released; a passing analysis module, configured to analyze the current ticket-checking behavior score and historical ticket-checking behavior score of the passenger to pass through when the passing credibility score of the passenger to pass through is within the preset credibility range and perform comprehensive analysis to obtain the comprehensive passing score of the passenger to pass through; a release judgment module, configured to perform judgment analysis on the comprehensive passing score of the passenger to pass through and a preset passing range; if the comprehensive passing score of the passenger to pass through is outside the preset passing range, the passenger shall not be released; if the comprehensive passing score of the passenger to pass through is within the preset passing range, the passenger shall be released.

[0017] The present invention has the following beneficial effects: (1) The multi-certificate ticket checking method obtains the status data of the passenger's passing certificate, such as certificate matching degree, capacitance value, magnetic field strength, etc., and the passenger ticket checking status data, such as hand pressure, friction force, face angle, etc., comprehensively calculates the passing credibility score, and further analyzes it in combination with the current ticket checking behavior score and the historical ticket checking behavior score. Compared with the traditional ticket checking method that only relies on certificate matching, this method can effectively identify abnormal ticket checking behaviors, such as proxy swiping, following through, forging tickets, etc. In particular, the addition of the certificate capacitance value and magnetic field strength can be used to detect the authenticity of NFC cards or magnetic stripe cards, while the passenger behavior parameters can further verify whether the holder of the certificate is the person himself. This multi-level analysis method can reduce misjudgments and missed judgments, ensure that legal passengers can be efficiently released, and suspicious passers-by can be accurately intercepted, improving the security and intelligence level of the ticket checking system.

[0018] (2) When calculating the current ticket checking behavior score, the multi-certificate ticket checking method not only considers the certificate matching situation, but also combines the dynamic behavior data of the passenger, such as walking speed, gait acceleration, arm swing amplitude and its change rate. By comprehensively calculating these features, it is judged whether the passenger's passing behavior is reasonable. For example, when checking tickets normally, passengers usually maintain a stable walking speed and gait, while proxy swipers or abnormal passers-by may show abnormal acceleration or arm swing patterns. Through parameters such as the walking speed influence coefficient, walking acceleration influence coefficient, and swing amplitude influence coefficient stored in the database, the behavior state of the passenger can be accurately evaluated to prevent situations such as the ticket being stolen by others or illegal intrusion. In addition, the addition of the face angle and hand operation stability makes it difficult for passengers to avoid system detection through abnormal behaviors even if they hold legal certificates, further enhancing the ticket checking system's ability to identify abnormal behaviors.

[0019] (3) By introducing the historical ticket checking behavior score, the multi-certificate ticket checking method analyzes the time series data of the passenger's past multiple ticket checking behaviors, including historical gait data, arm swing data, etc., and calculates parameters such as the historical walking speed index, historical acceleration index, historical swing amplitude index, etc., to judge whether the passenger's behavior pattern is stable. Compared with the traditional ticket checking system that only relies on the current behavior for a single judgment, the present invention can establish a long-term behavior portrait of the passenger, so that when an abnormal behavior occurs, intelligent judgment can be made by comprehensively considering historical data. For example, if a certain passenger has always maintained a relatively consistent gait pattern during long-term ticket checking, but suddenly shows extreme changes in walking speed or swing amplitude during a certain time, this method can identify potential risks accordingly, such as the ticket being used by others or the safety hazards brought by the sudden change of the passenger's behavior. In addition, the historical behavior score can also be used to optimize personalized passing strategies, so that passengers with long-term compliance can enjoy a smoother ticket checking experience, while passengers with frequent abnormalities need more strict ticket checking verification, improving the overall ticket checking efficiency and security.

[0020] (4) The multi-certificate ticket checking device adopts a modular design architecture, splitting the ticket checking process into multiple independent functional modules such as data acquisition, trusted analysis, trusted judgment, passage analysis, and release judgment. This enables the entire system to have better scalability, stability, and maintainability. In traditional ticket checking systems, the various functions are usually tightly coupled in design. When the system is updated or new functions are added, it often requires significant modification of the original structure, affecting the stability of the system. Through the division of labor and cooperation of independent modules in this device, each module can be independently optimized according to actual needs. For example, the algorithm of the trusted analysis module can be upgraded separately to improve the ability to detect abnormal behaviors, or the strategy of the release judgment module can be adjusted to improve the passage efficiency of the system. In addition, the modular architecture also facilitates integration with third-party security authentication, payment systems, or other intelligent passage management systems to meet the ticket checking requirements in different scenarios, such as subways, buses, highway toll stations, etc., making the system have stronger adaptability and application value.

[0021] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flowchart of a multi-certificate ticket checking method according to the present invention.

[0023] Figure 2 It is a flowchart of the specific steps for analyzing the current ticket checking behavior score of a passenger to be passed in a multi-certificate ticket checking method according to the present invention.

[0024] Figure 3 It is a block diagram of a multi-certificate ticket checking device according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] Please refer to Figure 1 , an embodiment of the present invention provides a technical solution: a multi-certificate ticket checking method, including the following steps: when a passenger undergoes ticket checking, obtain the status data of the passage certificate and the ticket checking status data of the passenger to be passed, and perform preprocessing on them respectively; based on the preprocessed status data of the passage certificate and the ticket checking status data of the passenger, analyze the passage trust score of the passenger to be passed, and perform judgment and analysis with a preset trust score interval; if the passage trust score of the passenger to be passed is outside the preset trust interval, do not release; if the passage trust score of the passenger to be passed is within the preset trust interval, analyze the current ticket checking behavior score and the historical ticket checking behavior score of the passenger to be passed, and perform comprehensive analysis to obtain the comprehensive passage score of the passenger to be passed; perform judgment and analysis on the comprehensive passage score of the passenger to be passed with a preset passage interval; if the comprehensive passage score of the passenger to be passed is outside the preset passage interval, do not release; if the comprehensive passage score of the passenger to be passed is within the preset passage interval, give release.

[0026] Among them, the specific formula for calculating the comprehensive passage score of the to-be-passed passenger is as follows: ; among which, is the comprehensive passage score of the to-be-passed passenger, is the current ticket-checking behavior score of the to-be-passed passenger, is the current ticket-checking behavior adjustment coefficient stored in the database, is the current ticket-checking behavior influence coefficient stored in the database, is the historical ticket-checking behavior score of the to-be-passed passenger, is the historical ticket-checking behavior adjustment coefficient stored in the database, is the historical ticket-checking behavior influence coefficient stored in the database, is the natural constant, which takes the value of 2.71 in this embodiment, is the combined influence coefficient of ticket-checking behavior stored in the database.

[0027] It should be explained that the specific acquisition steps of the current ticket-checking behavior adjustment coefficient and the historical ticket-checking behavior adjustment coefficient are as follows: Collect the ticket-checking data of a large number of passengers, including key parameters such as the matching degree of the passage permit, the pressure of the hand when swiping the ticket, the friction force, the facial angle, etc., and combine dynamic behavior information such as walking speed and gait stability to form a complete ticket-checking behavior database. Then, use clustering analysis and statistical regression models to calculate the behavior characteristics under different ticket-checking modes, analyze their influence on the passage score, and extract the normal behavior range of passengers through data standardization methods. Next, through Bayesian estimation or dynamic weighted learning algorithms, combine real-time data to update and values to make them dynamically adapt to the behavior habits of different passengers. Finally, the system regularly optimizes and adjusts these adjustment coefficients based on long-term monitoring data to ensure the stability and accuracy of the ticket-checking scoring model.

[0028] The specific acquisition steps of the current ticket-checking behavior influence coefficient , the historical ticket-checking behavior influence coefficient , and the combined influence coefficient of ticket-checking behavior are as follows: Based on the real-time ticket-checking data of passengers, including factors such as swiping pressure, friction force, facial angle, gait, etc., use statistical regression analysis to calculate the influence degree of different behavior characteristics on the passage score, so as to determine the current ticket-checking behavior influence coefficient . Secondly, to obtain the historical ticket-checking behavior influence coefficient , perform time series analysis on the historical ticket-swiping records of passengers, evaluate the stability of their long-term behavior patterns, and assign higher weights to recent data through weighted average or exponential smoothing methods to reflect the habitual characteristics of passengers. Finally, to obtain the combined influence coefficient of ticket-checking behavior , through multivariate correlation analysis, the coupling degree between current and historical ticket-checking behaviors is evaluated to ensure that short-term anomalies will not overly affect long-term stability, while avoiding score distortion caused by long-term anomalies. All coefficients will be dynamically optimized through an adaptive learning algorithm during the system operation to ensure the reliability and accuracy of the scoring model.

[0029] The pass credential status data includes pass credential matching degree, internal capacitance value of the pass credential, and internal magnetic field strength value of the pass credential. The passenger ticket-checking status data includes ticket-checking hand pressure value, ticket-checking hand friction value, and ticket-checking face angle value.

[0030] Among them, the pass credential matching degree is used to measure the matching degree between the credential held by the passenger (such as an NFC card) and the records in the system database. It can obtain the unique ID of the card through an NFC reading chip and compare it with the system database to check for matching. If it matches, the pass credential matching degree is 1; if the matching degree is low (such as an invalid ticket or an expired ticket), the pass credential matching degree is 0.

[0031] The internal capacitance value of the pass credential can be measured and obtained through a capacitance sensor.

[0032] The internal magnetic field strength value of the pass credential can be measured and obtained through a magnetic induction sensor.

[0033] The ticket-checking hand pressure value can be measured and obtained through a pressure sensor.

[0034] The ticket-checking hand friction value can be measured and obtained through a friction sensor.

[0035] The ticket-checking face angle value can be measured and obtained through a face recognition camera.

[0036] Specifically, the specific steps for analyzing the passage credibility score of a to-be-passed passenger are as follows: Obtain the ticket-checking hand heat distribution index, ticket-checking hand heat distribution reference index, internal capacitance reference value of the pass credential, and internal magnetic field strength reference value of the pass credential of the to-be-passed passenger; comprehensively analyze the pass credential status data and passenger ticket-checking status data of the to-be-passed passenger in combination with the ticket-checking hand heat distribution index, ticket-checking hand heat distribution reference index, internal capacitance reference value of the pass credential, and internal magnetic field strength reference value of the to-be-passed passenger to obtain the passage credibility score of the to-be-passed passenger.

[0037] Among them, the ticket-checking hand heat distribution reference index is obtained by obtaining the hand measurement temperature reference value at each measurement position point of the ticket-checking hand of the to-be-passed passenger and performing mean analysis.

[0038] The internal capacitance reference value of the access permit is used to measure whether the access permit is forged. For example, if the access permit is an NFC card and its capacitance value range is 20−50 μF, the middle value is taken as the internal capacitance reference value of the access permit.

[0039] The internal magnetic field strength reference value of the access permit is used to measure whether the access permit is forged. For example, if the access permit is an NFC card and its magnetic field strength range is 10 −6 −10 −4 T, the middle value is taken as the internal magnetic field strength reference value of the access permit.

[0040] The specific steps to obtain the heat distribution index of the ticket-checking hand of the passenger to pass through are as follows: For the ticket-checking hand of the passenger to pass through, several measurement position points are randomly selected, and the hand measurement temperature values are obtained respectively; The hand measurement temperature values of each measurement position point of the ticket-checking hand of the passenger to pass through are comprehensively analyzed (i.e., mean analysis) to obtain the heat distribution index of the ticket-checking hand of the passenger to pass through.

[0041] Among them, the hand measurement temperature value can be measured and obtained through a temperature sensor.

[0042] The specific formula for calculating the access credibility score of the passenger to pass through is as follows: ; Among them, is the access credibility score of the passenger to pass through, is the matching degree of the access permit of the passenger to pass through, is the matching adjustment coefficient stored in the database, is the hand pressure value of the ticket-checking hand of the passenger to pass through, is the pressure adjustment coefficient stored in the database, is the hand friction value of the ticket-checking hand of the passenger to pass through, is the friction adjustment coefficient stored in the database, is the natural constant, which takes the value of 2.71 in this embodiment, is the heat distribution index of the ticket-checking hand of the passenger to pass through, is the heat distribution reference index of the ticket-checking hand of the passenger to pass through, is the heat distribution adjustment coefficient stored in the database, is the face angle value of the ticket-checking face of the passenger to pass through, is the angle adjustment coefficient stored in the database, is the internal capacitance value of the access permit of the passenger to pass through, is the internal capacitance reference value of the access permit of the passenger to pass through, is the capacitance adjustment coefficient stored in the database, is the internal magnetic field strength value of the access permit of the passenger to pass through, is the internal magnetic field strength reference value of the access permit of the passenger to pass through, The magnetic field strength adjustment coefficient stored in the database.

[0043] It should be explained that the matching adjustment coefficient stored in the database , pressure adjustment coefficient , friction adjustment coefficient , heat distribution adjustment coefficient , angle adjustment coefficient , capacitance adjustment coefficient , magnetic field strength adjustment coefficient The specific acquisition steps are as follows: Based on a large amount of historical ticket-checking data, statistical analysis and machine learning models are used to perform regression calculations on the influence degree of different parameters on the passage credibility score to determine the basic weights of each parameter. Secondly, through distribution fitting and anomaly detection algorithms, extreme abnormal data are eliminated, and the average influence value of each parameter is calculated. Then, for features such as matching degree, pressure, friction, heat distribution, angle, capacitance, and magnetic field, the system adopts an adaptive weighted algorithm to dynamically correct them in combination with different environments, time periods, and individual differences, so that it can be adjusted in real time according to the actual application situation. Finally, through long-term monitoring and model iteration optimization, the system continuously updates and optimizes each adjustment coefficient to ensure the accuracy and adaptability of the score, so that it can accurately reflect the influence of each feature on the passage credibility in different situations.

[0044] In this implementation plan, by introducing parameters such as the heat distribution of the ticket-checking hand, the internal capacitance of the passage permit, and the magnetic field strength, and combining multi-dimensional biometric data such as the matching degree of the passage permit, hand pressure, friction, and face angle, a more comprehensive passage credibility scoring system is constructed. Compared with the traditional ticket-checking method that only relies on voucher comparison, this method can effectively distinguish real passengers from abnormal passers-by and improve security. First, the hand heat distribution index can be obtained in real time through a temperature sensor to identify the biometric characteristics of the ticket holder and prevent mechanical arms or fake hands from swiping on behalf. Secondly, the internal capacitance value and magnetic field strength reference value of the passage permit can be used to detect the authenticity of NFC cards or magnetic stripe cards and identify forged tickets, thereby preventing illegal tampering or cloning of ticket information. Moreover, various adjustment coefficients stored in the database are dynamically adjusted based on big data statistical analysis and machine learning algorithms, enabling the system to adapt to different environments, time periods, and individual differences and improving the scoring accuracy. This method can not only dynamically adapt to the passage characteristics in different regions and different time periods, but also continuously improve the intelligence level of the ticket-checking system, realizing more efficient, accurate, and secure passenger identity verification and passage management.

[0045] Specifically, as Figure 2As shown in the figure, the specific steps for analyzing the current ticket-checking behavior score of the passenger to pass through are as follows: Obtain the current movement state data of the passenger to pass through at several time points in the ticket-checking area (i.e., from the starting point to the ending point of the ticket-checking area), and analyze the current movement state parameter set of the passenger to pass through. The current movement state parameter set includes the current movement speed index, the current movement acceleration index, the current arm swing amplitude index, and the current arm swing amplitude change index; Read the passage credibility score of the passenger to pass through, and conduct a comprehensive analysis in combination with the current movement state parameter set of the passenger to pass through to obtain the current ticket-checking behavior score of the passenger to pass through.

[0046] The current movement state data includes the movement speed value and the arm swing amplitude value. The specific steps for analyzing the current movement state parameter set of the passenger to pass through are as follows: Read the movement speed values of the passenger to pass through at several time points in the ticket-checking area, and conduct a comprehensive analysis (i.e., mean analysis) to obtain the current movement speed index of the passenger to pass through; Conduct an acceleration analysis on the movement speed values of the passenger to pass through at several time points in the ticket-checking area to obtain several groups of movement acceleration values (i.e., movement acceleration) of the passenger to pass through in the ticket-checking area, and conduct a comprehensive analysis (i.e., mean analysis) to obtain the current movement acceleration index of the passenger to pass through; Read the arm swing amplitude values of the passenger to pass through at several time points in the ticket-checking area, and conduct a comprehensive analysis (i.e., mean analysis) to obtain the current arm swing amplitude index of the passenger to pass through; Conduct a change analysis on the arm swing amplitude values of the passenger to pass through at several time points in the ticket-checking area to obtain several groups of arm swing amplitude change rates of the passenger to pass through in the ticket-checking area, and conduct a comprehensive analysis (i.e., mean analysis) to obtain the current arm swing amplitude change index of the passenger to pass through.

[0047] Among them, the movement speed value can be measured and obtained through a millimeter-wave radar sensor, an infrared lidar, etc.

[0048] The arm swing amplitude value can be measured and obtained through an inertial measurement unit (IMU, inertial sensor).

[0049] The specific steps for calculating the current ticket-checking behavior score and the historical ticket-checking behavior score of the passenger to pass through are as follows: ; Among them, is the current ticket-checking behavior score of the passenger to pass through, is the passage credibility score of the passenger to pass through, is the natural constant, and its value is 2.71 in this embodiment, is the current movement speed index of the passenger to pass through, is the movement speed influence coefficient stored in the database, is the current movement acceleration index of the passenger to pass through, is the movement acceleration influence coefficient stored in the database, is the current arm swing amplitude index of the passenger waiting to pass, The swing amplitude influence coefficient stored in the database, is the current arm swing amplitude change index of the passenger waiting to pass, The swing amplitude change influence coefficient stored in the database.

[0050] It needs to be explained that the travel speed influence coefficient stored in the database , Travel acceleration influence coefficient , Swing amplitude influence coefficient , Swing amplitude change influence coefficient The specific acquisition steps are as follows: collect a large number of passengers' walking data, including walking speed, acceleration, arm swing amplitude and its changes, and establish a benchmark model based on the behavior patterns under normal traffic conditions. Secondly, through cluster analysis and regression modeling, calculate the influence of different gait parameters on the ticket checking score to form an initial influence coefficient. Then, the system uses time series analysis and anomaly detection algorithms to eliminate invalid data and normalize individual characteristics to ensure that the influence coefficient is adaptable among different populations. Next, based on the dynamic weight adjustment mechanism and combined with real-time traffic data, the influence coefficient can be adaptively optimized as the passenger's behavior pattern changes. Finally, the system continuously iterates and optimizes each influence coefficient through a machine learning model to ensure that the scoring model can accurately reflect the actual impact of the walking status on the current ticket checking behavior score, thereby improving the intelligence and security of the ticket checking system.

[0051] In this implementation scheme, by analyzing the current ticket-checking behavior score of passengers and combining gait characteristics such as walking speed, walking acceleration, arm swing amplitude and change rate, the safety and intelligence level of the ticket-checking system are effectively improved. Compared with the traditional single ticket matching method, this method not only considers the authenticity of passengers' vouchers, but also conducts in-depth analysis based on gait behavior characteristics to ensure the rationality of passengers' passing behaviors. First of all, the current walking speed index and acceleration index can effectively detect abnormal gait behaviors, such as passing through rapidly or walking abnormally slowly, preventing malicious gate crashing or proxy swiping. Secondly, the arm swing amplitude index and swing change index can detect the naturalness of passengers when passing through. If the swing amplitude is too small or the change is abnormal, it may mean that the passenger is hiding the ticket, using a robotic arm for proxy swiping or there are abnormal behaviors. By collecting a large amount of historical walking data and combining clustering analysis, time series analysis and regression modeling, this method can establish a gait benchmark model and exclude individual differences through anomaly detection algorithms to ensure that the system is applicable to different populations. In addition, this method uses a dynamic weight adjustment mechanism to adaptively optimize by combining real-time passing data, ensuring that the scoring model can accurately evaluate the impact of the walking state on the ticket-checking behavior, enabling the ticket-checking device to optimize itself during continuous learning, improving the accuracy and safety of passengers' passing, reducing misjudgments and missed judgments. Finally, through the iterative optimization of machine learning algorithms, this method can improve the system stability in the long term and achieve more efficient and safer ticket-checking management.

[0052] Specifically, the specific steps for analyzing the historical ticket-checking behavior score of passengers to be passed are as follows: Obtain the historical time series data of the historical walking states of passengers to be passed in the ticket-checking area and perform preprocessing. The historical time series data of the historical walking states includes historical walking speed values and historical arm swing amplitude values at several historical time points; conduct comprehensive analysis on the historical time series data of the historical walking states of passengers to be passed in the ticket-checking area after preprocessing respectively to obtain the historical walking speed index, historical acceleration index, historical arm swing amplitude index, and historical arm swing amplitude change index of passengers to be passed in the ticket-checking area; conduct comprehensive analysis on the historical walking speed index, historical acceleration index, historical arm swing amplitude index, and historical arm swing amplitude change index of passengers to be passed in the ticket-checking area to obtain the historical ticket-checking behavior score of passengers to be passed, that is, first conduct mean analysis on the historical walking speed index, historical acceleration index, historical arm swing amplitude index, and historical arm swing amplitude change index of passengers to be passed in the ticket-checking area respectively, and conduct comprehensive analysis based on the mean analysis results.

[0053] Among them, the calculation logic for calculating the historical walking speed index is the same as that for calculating the current walking speed index.

[0054] The calculation logic for calculating the historical acceleration index is the same as that for calculating the current acceleration index.

[0055] The calculation logic for calculating the historical arm swing amplitude index is the same as that for calculating the current arm swing amplitude index.

[0056] The calculation logic for calculating the historical arm swing amplitude change index is the same as that for calculating the current arm swing amplitude change index.

[0057] In this implementation scheme, by analyzing the historical ticket-checking behavior scores of passengers and combining gait time-series features such as historical walking speed, historical acceleration, historical arm swing amplitude, and its change rate, the long-term behavior recognition ability and passage safety of the ticket-checking system are effectively improved. Compared with traditional ticket-checking systems that only make judgments based on single ticket-checking behaviors, this method introduces a time-series analysis mechanism, which can comprehensively evaluate the long-term passage habits of passengers and improve the recognition accuracy of abnormal behaviors. First, the historical walking speed index and acceleration index can help the system determine whether passengers maintain a stable gait in the long term. If a passenger has always passed stably in the historical records but shows abnormal behaviors (such as sudden changes in walking speed or abnormal acceleration) during a certain ticket-checking, this method can intelligently identify this situation and reduce misjudgments. Second, the historical arm swing amplitude index and change index can detect the stability of the arm movement pattern of passengers during long-term ticket-checking. If the historical data shows that its swing amplitude is stable in the long term but the current detected value is suddenly abnormal, it may mean ticket fraud, ticket transfer, or other suspicious behaviors. Through mean analysis, this method can quantify the gait characteristics of passengers during multiple ticket-checks and further optimize the scoring calculation logic by combining historical trend modeling. In addition, this method ensures that the calculation logic for historical gait parameters is consistent with that for current gait parameters, avoiding score distortion caused by different calculation methods, thereby improving the stability and applicability of the system. Finally, through long-term monitoring and time-series modeling optimization, it can not only effectively identify the habitual passage behaviors of passengers but also accurately warn against abnormal behaviors, ensuring that the system can quickly release normal passengers and accurately intercept potential risk personnel, improving the intelligence level and safety of the ticket-checking system.

[0058] Please refer to Figure 3, an embodiment of the present invention provides a technical solution: a multi-certificate ticket checking device, including: a data acquisition module, configured to acquire the status data of the access certificate and the passenger ticket checking status data of the passenger to be passed when the passenger checks the ticket, and perform preprocessing respectively; a trusted analysis module, configured to analyze the access trust score of the passenger to be passed based on the preprocessed status data of the access certificate and the passenger ticket checking status data; a trusted judgment module, configured to perform judgment analysis on the access trust score of the passenger to be passed and a preset trusted score range. If the access trust score of the passenger to be passed is outside the preset trusted range, the passenger will not be released; a passage analysis module, configured to analyze the current ticket checking behavior score and the historical ticket checking behavior score of the passenger to be passed when the access trust score of the passenger to be passed is within the preset trusted range, and perform comprehensive analysis to obtain the comprehensive passage score of the passenger to be passed; a release judgment module, configured to perform judgment analysis on the comprehensive passage score of the passenger to be passed and a preset passage range; if the comprehensive passage score of the passenger to be passed is outside the preset passage range, the passenger will not be released; if the comprehensive passage score of the passenger to be passed is within the preset passage range, the passenger will be released.

[0059] In summary, the present application has at least the following effects: By acquiring the status data of the access certificate of the passenger, such as certificate matching degree, capacitance value, magnetic field strength, etc., and the passenger ticket checking status data, such as hand pressure, friction, face angle, etc., comprehensively calculating the access trust score, and further analyzing in combination with the current ticket checking behavior score and the historical ticket checking behavior score. Compared with the traditional ticket checking method that only relies on certificate matching, this method can effectively identify abnormal ticket checking behaviors, such as proxy swiping, following through, forging tickets, etc. In particular, the addition of the certificate capacitance value and magnetic field strength can be used to detect the authenticity of NFC cards or magnetic stripe cards, while the passenger behavior parameters can further verify whether the holder of the certificate is the person himself. This multi-level analysis method can reduce misjudgment and missed judgment, ensure that legal passengers can be released efficiently, and accurately intercept suspicious passers-by, improving the security and intelligence level of the ticket checking system.

[0060] When calculating the current ticket-checking behavior score, not only the voucher matching situation is considered, but also the dynamic behavior data of passengers, such as walking speed, gait acceleration, arm swing amplitude and its change rate, is combined. Through the comprehensive calculation of these features, it is judged whether the passenger's passing behavior is reasonable. For example, when normally checking tickets, passengers usually maintain a stable walking speed and gait, while those who use tickets on behalf of others or pass abnormally may show abnormal acceleration or arm swing patterns. By parameters such as the walking speed influence coefficient, walking acceleration influence coefficient, and swing amplitude influence coefficient stored in the database, the behavior state of passengers is accurately evaluated to prevent situations such as tickets being stolen by others or illegal intrusion. In addition, the addition of facial angle and hand operation stability makes it difficult for passengers to avoid system detection through abnormal behaviors even if they hold legitimate vouchers, further improving the abnormal behavior recognition ability of the ticket-checking system.

[0061] By introducing the historical ticket-checking behavior score, by analyzing the time-series data of a passenger's past multiple ticket-checking behaviors, including historical gait data, arm swing data, etc., parameters such as the historical walking speed index, historical acceleration index, and historical swing amplitude index are calculated to judge whether the passenger's behavior pattern is stable. Compared with traditional ticket-checking systems that only rely on the current behavior for a single determination, the present invention can establish a long-term behavior portrait of passengers, so that when abnormal behaviors occur, historical data is comprehensively considered for intelligent judgment. For example, if a certain passenger has always maintained a relatively consistent gait pattern during long-term ticket-checking, but suddenly shows extreme changes in walking speed or swing amplitude on a certain occasion, this method can identify potential risks accordingly, such as the risk of tickets being used by others or the safety hazards brought by sudden changes in passenger behavior. In addition, this historical behavior score can also be used to optimize personalized passing strategies, enabling passengers with long-term compliance to enjoy a smoother ticket-checking experience, while passengers with frequent abnormalities require more strict ticket-checking verification, improving the overall ticket-checking efficiency and safety.

[0062] Adopting a modular design architecture, the ticket-checking process is split into multiple independent functional modules such as data acquisition, trusted analysis, trusted judgment, passing analysis, and release judgment, making the entire system have better scalability, stability, and maintainability. In traditional ticket-checking systems, the functions are usually tightly coupled in design. When the system is updated or new functions are added, the original structure often needs to be significantly modified, affecting the stability of the system. Through the division of labor and cooperation of independent modules in this device, each module can be independently optimized according to actual needs. For example, the algorithm of the trusted analysis module can be upgraded alone to improve the abnormal behavior detection ability, or the strategy of the release judgment module can be adjusted to improve the system passing efficiency. In addition, the modular architecture also facilitates integration with third-party security authentication, payment systems, or other intelligent passing management systems to adapt to ticket-checking requirements in different scenarios, such as subways, buses, highway toll stations, etc., making the system have stronger adaptability and application value.

[0063] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made to these embodiments by those skilled in the art once they learn of the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.

[0064] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A multi-certificate ticket checking method, characterized in that, It includes the following steps: When a passenger undergoes ticket checking, obtain the status data of the access credential of the passenger to pass and the ticket checking status data of the passenger, and perform preprocessing on them respectively; Based on the preprocessed status data of the access credential and the ticket checking status data of the passenger, analyze the access credibility score of the passenger to pass, and make a judgment and analysis with a preset credibility score range; If the access credibility score of the passenger to pass is outside the preset credibility range, do not let the passenger pass; If the access credibility score of the passenger to pass is within the preset credibility range, analyze the current ticket checking behavior score and the historical ticket checking behavior score of the passenger to pass, and conduct a comprehensive analysis to obtain the comprehensive access score of the passenger to pass; Make a judgment and analysis on the comprehensive access score of the passenger to pass with a preset access range; If the comprehensive access score of the passenger to pass is outside the preset access range, do not let the passenger pass; If the comprehensive access score of the passenger to pass is within the preset access range, let the passenger pass; Among them, the specific formula for calculating the comprehensive access score of the passenger to pass is as follows: ； Among them, , , are respectively the comprehensive passage score, the current ticket inspection behavior score, and the historical ticket inspection behavior score of the passengers to pass through, , are respectively the current ticket inspection behavior adjustment coefficient and the historical ticket inspection behavior adjustment coefficient stored in the database, , , are respectively the current ticket inspection behavior influence coefficient, the historical ticket inspection behavior influence coefficient, and the combined influence coefficient of ticket inspection behavior stored in the database, is the natural constant.

2. The multi-certificate ticket checking method according to claim 1, wherein, The status data of the access credential includes the access credential matching degree, the internal capacitance value of the access credential, and the internal magnetic field strength value of the access credential, and the ticket checking status data of the passenger includes the ticket checking hand pressure value, the ticket checking hand friction value, and the ticket checking face angle value.

3. The multi-certificate ticket checking method according to claim 2, wherein The specific steps for analyzing the access credibility score of the passenger to pass are as follows: Obtain the ticket checking hand heat distribution index, the ticket checking hand heat distribution reference index, the internal capacitance reference value of the access credential, and the internal magnetic field strength reference value of the access credential of the passenger to pass; Comprehensively analyze the status data of the access credential and the ticket checking status data of the passenger to pass respectively in combination with the ticket checking hand heat distribution index, the ticket checking hand heat distribution reference index, the internal capacitance reference value of the access credential, and the internal magnetic field strength reference value of the access credential of the passenger to pass to obtain the access credibility score of the passenger to pass.

4. The multi-certificate ticket checking method according to claim 3, wherein The specific steps for obtaining the ticket checking hand heat distribution index of the passenger to pass are as follows; For the ticket checking hand of the passenger to pass, randomly select several measurement position points and obtain the hand measurement temperature values respectively; Comprehensively analyze the hand measurement temperature values of each measurement position point of the ticket checking hand of the passenger to pass to obtain the ticket checking hand heat distribution index of the passenger to pass.

5. The multi-certificate ticket checking method according to claim 3, wherein The specific formula for calculating the access credibility score of the passenger to pass is as follows: ； Among them, , , , , , , , , , , are, in sequence, the passage credibility score of the passenger to pass, the matching degree of the passage certificate, the ticket-checking hand pressure value, the ticket-checking hand friction value, the ticket-checking hand heat distribution index, the ticket-checking hand heat distribution reference index, the ticket-checking face angle value, the internal capacitance value of the passage certificate, the internal capacitance reference value of the passage certificate, the internal magnetic field strength value of the passage certificate, and the internal magnetic field strength reference value of the passage certificate, , , , , , , are, in sequence, the matching adjustment coefficient, the pressure adjustment coefficient, the friction adjustment coefficient, the heat distribution adjustment coefficient, the angle adjustment coefficient, the capacitance adjustment coefficient, and the magnetic field strength adjustment coefficient stored in the database, is the natural constant.

6. The multi-certificate ticket checking method according to claim 1, characterized in that, The specific steps for analyzing the current ticket checking behavior score of the passenger to pass are as follows: Obtain the current movement status data of the passenger to pass at several time points in the ticket checking area, and analyze the current movement status parameter set of the passenger to pass. The current movement status parameter set includes the current movement speed index, the current movement acceleration index, the current arm swing amplitude index, and the current arm swing amplitude change index; Read the access credibility score of the passenger to pass, and conduct a comprehensive analysis in combination with the current movement status parameter set of the passenger to pass to obtain the current ticket checking behavior score of the passenger to pass.

7. The multi-certificate ticket inspection method according to claim 6, characterized in that The current movement status data includes the movement speed value and the arm swing amplitude value. The specific steps for analyzing the current movement status parameter set of the passenger to pass are as follows: Read the traveling speed values of the passenger to pass through the ticket checking area at several time points, and conduct comprehensive analysis to obtain the current traveling speed index of the passenger to pass through; Conduct acceleration analysis on the traveling speed values of the passenger to pass through the ticket checking area at several time points, obtain several groups of traveling acceleration values of the passenger to pass through the ticket checking area, and conduct comprehensive analysis to obtain the current traveling acceleration index of the passenger to pass through; Read the arm swing amplitude values of the passenger to pass through the ticket checking area at several time points, and conduct comprehensive analysis to obtain the current arm swing amplitude index of the passenger to pass through; Conduct change analysis on the arm swing amplitude values of the passenger to pass through the ticket checking area at several time points, obtain several groups of arm swing amplitude change rates of the passenger to pass through the ticket checking area, and conduct comprehensive analysis to obtain the current arm swing amplitude change index of the passenger to pass through.

8. The multi-certificate ticket checking method according to claim 6, characterized in that, The specific steps for calculating the current ticket checking behavior score and historical ticket checking behavior score of the passenger to pass through are as follows: ； Among them, , , , , , are, in sequence, the current ticket-checking behavior score, the passage credibility score, the current traveling speed index, the current traveling acceleration index, the current arm swing amplitude index, and the current arm swing amplitude change index of the passengers waiting to pass, , , , are, in sequence, the traveling speed influence coefficient, the traveling acceleration influence coefficient, the swing amplitude influence coefficient, and the swing amplitude change influence coefficient stored in the database, is the natural constant.

9. The multi-certificate ticket checking method according to claim 1, wherein The specific steps for analyzing the historical ticket checking behavior score of the passenger to pass through are as follows: Obtain the historical sequential data of the traveling state of the passenger to pass through the ticket checking area for several times in the past, and conduct preprocessing. The historical sequential data of the traveling state includes the historical traveling speed values and historical arm swing amplitude values at several historical time points; Conduct comprehensive analysis on the historical sequential data of the traveling state of the passenger to pass through the ticket checking area for several times in the past after preprocessing, and obtain the historical traveling speed index, historical traveling acceleration index, historical arm swing amplitude index, and historical arm swing amplitude change index of the passenger to pass through the ticket checking area for several times in the past; Conduct comprehensive analysis on the historical traveling speed index, historical traveling acceleration index, historical arm swing amplitude index, and historical arm swing amplitude change index of the passenger to pass through the ticket checking area for several times in the past, and obtain the historical ticket checking behavior score of the passenger to pass through.

10. A multi-certificate ticket checking device that applies the multi-certificate ticket checking method according to any one of claims 1-9, characterized in that Include: A data acquisition module, used to obtain the status data of the passing certificate and the passenger ticket checking status data of the passenger to pass through when the passenger conducts ticket checking, and conduct preprocessing respectively; A credibility analysis module, used to analyze the passing credibility score of the passenger to pass through based on the preprocessed status data of the passing certificate and the passenger ticket checking status data; A credibility judgment module, used to conduct judgment analysis on the passing credibility score of the passenger to pass through and a preset credibility score interval. If the passing credibility score of the passenger to pass through is outside the preset credibility interval, do not release; A passing analysis module, used to analyze the current ticket checking behavior score and historical ticket checking behavior score of the passenger to pass through when the passing credibility score of the passenger to pass through is within the preset credibility interval, and conduct comprehensive analysis to obtain the comprehensive passing score of the passenger to pass through; A release judgment module, used to conduct judgment analysis on the comprehensive passing score of the passenger to pass through and a preset passing interval; if the comprehensive passing score of the passenger to pass through is outside the preset passing interval, do not release; if the comprehensive passing score of the passenger to pass through is within the preset passing interval, give release.

Images