A smart park self-adaptive identity collection and supplementary recording supervision method

Abstract

This application relates to the field of smart park management technology, and in particular to a method for adaptive identity collection and supplementary registration supervision in smart parks. The method includes: determining the applicant's electronic identity authentication information based on self-applied identity information; matching the self-applied identity information with the electronic identity authentication information to obtain an identity matching value; when the identity matching value is not higher than a preset matching threshold, retrieving the applicant's historical access behavior information and determining the applicant's identity credibility index based on the historical access behavior information; determining supplementary registration supervision parameters based on the identity credibility index and generating supplementary registration supervision instructions based on the supplementary registration supervision parameters; and when it is detected that the applicant has arrived at the smart park's access control equipment to perform offline identity supplementary registration, supervising the applicant's supplementary registration behavior at the access control equipment according to the supplementary registration supervision instructions. This application facilitates improvements in the efficiency and credibility of the identity collection and supplementary registration stages.

Description

Technical Field

[0001] This application relates to the field of smart park management technology, and in particular to a method for adaptive identity collection and supplementary recording supervision in smart parks. Background Technology

[0002] With the continuous advancement of smart city and industrial park digitalization, smart parks have gradually achieved integrated operation in scenarios such as personnel access, area control, security patrols, and collaborative office work. Among these, personnel identity authentication and access control, as the core component of the smart park security system, directly determine the internal operational order, asset security, and personnel management efficiency of the park. In park environments characterized by dense populations, complex scenarios, and multi-departmental collaboration, accurate, efficient, and reliable identity collection and access control mechanisms are not only a fundamental barrier to regulate personnel entry and exit and prevent unauthorized personnel from arbitrarily entering, but also a key support for achieving tiered control of key areas, tracking of movement trajectories, and early warning of abnormal behavior.

[0003] Currently, in the process of collecting personnel identities and authenticating permissions in smart parks, the identity information collection process relies heavily on offline submissions and manual entry, resulting in long collection cycles and high error rates. Although some parks have introduced external electronic identity information for auxiliary comparison, they still mainly rely on simple information verification and lack in-depth verification of the authenticity and validity of identity information. This not only increases the cost of normal personnel entering the park, but also makes it impossible to accurately control high-risk personnel. Consequently, there are loopholes in park security and low management efficiency, which has long put great pressure on park security management. Summary of the Invention

[0004] To improve the efficiency and reliability of the identity collection and supplementation stages and reduce the security management pressure of smart parks, this application provides an adaptive identity collection and supplementation supervision method for smart parks.

[0005] This application provides a smart park adaptive identity collection and supplementary recording supervision method, which adopts the following technical solution: A smart park adaptive identity collection and supplementary recording supervision method includes: Obtain the self-application identity information provided by the applicant, and determine the applicant's electronic identity authentication information based on the self-application identity information; The self-application identity information is matched with the electronic identity authentication information to obtain an identity matching value; When the identity matching value is not higher than the preset matching threshold, the applicant's historical access behavior information is retrieved from the smart park's full-domain access log, and the applicant's identity credibility index is determined based on the historical access behavior information. The supplementary registration supervision parameters are determined based on the identity credibility index, and a supplementary registration supervision instruction is generated based on the supplementary registration supervision parameters. The supplementary registration supervision parameters include the supplementary registration location and the supplementary registration dwell time. When the applicant arrives at the access control device of the smart park to perform offline identity registration, the registration behavior of the applicant at the access control device is supervised according to the registration supervision instruction.

[0006] By adopting the above technical solution, and through two-way matching and verification of self-applied identity information and electronic identity authentication information, authoritative verification of identity information can be achieved from the source, improving the reliability and credibility of identity authentication. When the matching does not reach the preset threshold, the credibility of the identity is quantified to achieve refined judgment of identity risks, effectively distinguishing between unintentional errors in filling in information and malicious identity spoofing. Under the premise of ensuring security, the efficiency of identity collection and supplementation process is improved. At the same time, based on the credibility index, the supervision parameters such as supplementation location and stay duration are dynamically configured to implement targeted supervision at the access control terminal, enhancing the standardization and controllability of offline supplementation. Overall, the efficiency and credibility of the identity collection and supplementation stage are improved, reducing security risks such as identity theft and unauthorized access, reducing the risk of management oversight from the front end, and effectively alleviating the security management pressure of smart parks.

[0007] In one possible implementation, determining the applicant's identity credibility index based on the historical access behavior information includes: Based on the historical passage behavior information, the applicant's historical frequency of appearance, historical passage trajectory, and historical companion behavior information are determined for each historical passage period within the preset analysis time period. Based on the historical frequency of occurrence corresponding to each historical passage period, the stability rate of the historical frequency of occurrence of the applicant corresponding to the preset analysis period is determined; Based on the historical travel trajectory corresponding to each historical travel period, a historical stable travel trajectory is determined, and based on the historical travel trajectory corresponding to each historical travel period and the historical stable travel trajectory, the stability rate of the applicant's historical travel trajectory corresponding to the preset analysis period is determined; Based on the historical passage trajectory corresponding to each historical passage period and the passage trajectory stability rate corresponding to the preset analysis period, as well as the preset key areas within the smart park, the compliance of the applicant in the key areas corresponding to the preset analysis period is determined. Based on the historical travel trajectory and the behavior information of the historical companions corresponding to each historical travel period, the correlation degree of the applicant's historical companions corresponding to the preset analysis period is determined; Based on the stability rate of historical occurrence frequency, the stability rate of historical travel trajectory, the compliance of proximity to key areas, and the correlation of historical companions, the credibility index of the applicant's identity is determined.

[0008] By adopting the above technical solution and performing multi-dimensional analysis of historical travel behavior information, the stability rate of the applicant's historical appearance frequency, the stability rate of historical travel trajectory, the compliance of proximity to key areas, and the correlation with historical companions were determined. This enabled the quantitative calculation and accurate assessment of the identity credibility index. Compared with single-dimensional behavioral analysis, the multi-dimensional feature integration assessment method can more comprehensively and objectively reflect the authenticity and credibility of the applicant's identity, effectively avoiding the assessment bias caused by single feature analysis. At the same time, by accurately quantifying various behavioral characteristics, it is easier to further refine the identity risk level, accurately distinguish between unintentional reporting errors and malicious identity spoofing, and provide a scientific and reliable basis for the dynamic configuration of supplementary monitoring parameters.

[0009] In one possible implementation, determining the stability rate of the applicant's historical travel trajectory within the preset analysis time period based on the historical travel trajectory corresponding to each historical travel period and the historical stable travel trajectory includes: The historical travel trajectory corresponding to each historical travel period and the historical stable travel trajectory are subjected to trajectory feature quantization processing to obtain the historical travel trajectory feature value corresponding to each historical travel period and the historical stable travel trajectory feature value corresponding to the historical stable travel trajectory. The historical travel trajectory stability rate is determined based on the historical travel trajectory feature value corresponding to each historical travel period, the historical stable travel trajectory feature value, and the preset trajectory stability rate formula.

[0010] By adopting the above technical solution, and by quantifying the trajectory features of each historical travel trajectory and historical stable travel trajectory, it is easy to transform abstract trajectory information into standardized and calculable trajectory feature values. By using a preset trajectory stability rate formula to uniformly calculate the above feature values, the stability rate of historical travel trajectories can be accurately quantified, avoiding the subjectivity and errors caused by manual judgment or rough statistics, and making the assessment results of trajectory stability more objective and reliable.

[0011] In one possible implementation, determining the applicant's proximity to compliance in the key area corresponding to the preset analysis time period based on the historical travel trajectory corresponding to each historical travel period and the travel trajectory stability rate corresponding to the preset analysis time period, as well as the preset key areas within the smart park, includes: Based on the stability rate of the traffic trajectory corresponding to the preset analysis time period, the sudden traffic trajectory is determined from all the historical traffic trajectories; Based on the historical stable travel trajectory and the sudden change travel trajectory, the observation travel trajectory is determined; Based on the preset key areas within the smart park and the observed passage trajectory, the historical passage coverage of the applicant in the preset key areas within the preset analysis time period is determined. When the historical access coverage rate is higher than the preset coverage threshold, the historical body behavior data of the applicant when he / she is near the preset key area during the preset analysis time period is obtained, and the suspicion of the historical behavior is determined based on the historical body behavior data. Based on the historical traffic coverage and the historical behavior suspiciousness, the proximity compliance of the key areas is determined.

[0012] By adopting the above technical solution, and by combining the stability rate of the passage trajectory to identify abrupt changes in the passage trajectory and determine the observation passage trajectory, it is convenient to accurately capture the abnormal passage characteristics of applicants in the park, and achieve effective screening of approaching behavior in key areas. Based on the preset key areas and the observed passage trajectory, the historical passage coverage is calculated, and the body behavior data is further introduced in combination with the coverage threshold to determine the suspiciousness of the behavior. This allows for multi-level and refined compliance verification of approaching behavior in key areas, avoiding misjudgments caused by relying solely on trajectory information. By integrating passage coverage and behavioral suspiciousness to determine the compliance of approaching key areas, it is easier to more accurately identify potential risks such as unauthorized approaching and intent to break in, and further improve the accuracy of the identity credibility index.

[0013] In one possible implementation, when the correlation between the historical peers is higher than a preset correlation threshold, the method further includes: Obtain historical association behavior information of historical association companions, and determine the stability rate of the associated travel trajectory of the historical association companions in the preset analysis time period; Identify the period of sudden change in the travel trajectory corresponding to the applicant, and determine the associated sudden change travel trajectory corresponding to the historical associated travel trajectories based on the period of sudden change in travel trajectory and the stability rate of the associated travel trajectories of the historical associated travel trajectories in the preset analysis period. The historical traffic coverage is optimized based on the associated mutation traffic trajectory.

[0014] By adopting the above technical solutions, and introducing behavioral analysis of related peers when the correlation between them is high, it is easier to fully explore the impact of peer behavior on the determination of applicants' trajectories, thereby further improving the comprehensiveness of behavioral analysis. By determining the stability rate of related travel trajectories and identifying related abrupt change travel trajectories in conjunction with the applicant's travel abrupt change period, it is possible to effectively eliminate trajectory interference caused by abnormal behavior of peers, avoid the deviation in coverage calculation caused by relying solely on individual trajectories, and optimize historical travel coverage based on related abrupt change travel trajectories. This makes the calculation results of compliance in key areas more consistent with real travel scenarios, improves the accuracy and rationality of the identity credibility index, and makes subsequent supplementary registration and supervision strategies more targeted and reliable.

[0015] In one possible implementation, the method also includes Based on the applicant’s historical access images and recognition logs, easily confused behavioral features are extracted, including face lateralization habits, posture stability, and historical recognition confusion frequency. Personalized supplementary reinforcement items are generated based on the aforementioned easily confused behavioral characteristics; The personalized supplementary registration enhancement items are integrated into the supplementary registration supervision instructions. When it is detected that the applicant is performing offline identity supplementary registration, targeted supervision is carried out based on the personalized supplementary registration enhancement items.

[0016] By adopting the above technical solution, and extracting easily confused behavioral features such as facial lateralization habits, posture stability, and historical recognition confusion frequency from historical images and recognition logs, it is easy to accurately locate the weak points of applicants who are easily misidentified or imitated during the identity recognition process. Based on the above features, personalized supplementary recording reinforcement items are generated and supplementary recording supervision instructions are integrated. This allows offline identity supplementary recording to no longer adopt a uniform and rigid collection standard, but to implement differentiated and targeted supervision based on individual identification risk points, effectively avoiding recognition errors and impersonation opportunities caused by fixed collection angles and standard postures.

[0017] In summary, this application includes at least one of the following beneficial technical effects: By performing two-way matching and verification of self-applied identity information and electronic identity authentication information, authoritative verification of identity information can be achieved from the source, improving the reliability and credibility of identity authentication. When the matching does not reach the preset threshold, the credibility of the identity is quantified to achieve refined judgment of identity risks, effectively distinguishing between unintentional errors in filling in information and malicious identity spoofing. Under the premise of ensuring security, the efficiency of identity collection and supplementation process is improved. At the same time, based on the credibility index, the supervision parameters such as supplementation location and stay duration are dynamically configured to implement targeted supervision at the access control terminal, enhancing the standardization and controllability of offline supplementation. Overall, the efficiency and credibility of the identity collection and supplementation stage are improved, reducing security risks such as identity theft and unauthorized access, reducing the risk of management oversight from the front end, and effectively alleviating the security management pressure of smart parks.

[0018] By analyzing historical travel behavior information from multiple dimensions, the stability rate of applicants' historical appearance frequency, the stability rate of their historical travel trajectory, the compliance of their proximity to key areas, and the correlation with their historical companions were determined. This enabled the quantitative calculation and accurate assessment of the identity credibility index. Compared to single-dimensional behavioral analysis, the multi-dimensional feature integration assessment method can more comprehensively and objectively reflect the authenticity and credibility of applicants' identities, effectively avoiding assessment biases caused by single-feature analysis. At the same time, by accurately quantifying various behavioral characteristics, it is easier to further refine the identity risk level, accurately distinguish between unintentional reporting errors and malicious identity spoofing, and provide a scientific and reliable basis for the dynamic configuration of supplementary monitoring parameters. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating a smart park adaptive identity collection and supplementary recording supervision method in an embodiment of this application; Figure 2 This is a schematic diagram of a process for determining the credibility index of an applicant's identity in an embodiment of this application. Detailed Implementation

[0020] The following is in conjunction with the appendix Figures 1 to 2 This application will be described in further detail.

[0021] After reading this specification, those skilled in the art may make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application.

[0022] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] It should be noted that, in the optional embodiments of this application, the data related to object information, when applied to specific products or technologies, requires the permission or consent of the object. Furthermore, the collection, use, and processing of this data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. In other words, if the embodiments of this application involve data related to an object, it must be obtained with the object's authorization and consent, the authorization and consent of relevant departments, and in accordance with the relevant laws, regulations, and standards of the country and region. If the embodiments involve personal information, the acquisition of all personal information requires the individual's consent. If sensitive information is involved, the separate consent of the information subject is required. The embodiments also need to be implemented with the object's authorization and consent.

[0024] Specifically, this application provides a method for adaptive identity collection and supplementation supervision in smart parks. This method is applied to a supervision system, which can execute a smart park adaptive identity collection and supplementation supervision program. The supervision system can be a single server, a server cluster consisting of multiple servers, or a cloud computing service center. (Reference) Figure 1 , Figure 1 This is a flowchart illustrating a smart park adaptive identity collection and supplementary recording supervision method according to an embodiment of this application. The method includes steps S110-S150, wherein: Step S110: Obtain the self-application identity information provided by the applicant, and determine the applicant's electronic identity authentication information based on the self-application identity information.

[0025] Specifically, applicants can log in to their accounts through the smart park mobile application or mini-program, and proactively enter and submit their name, ID number, and headshot, among other identity-related information, to form their self-application identity information, which is then uploaded to the monitoring system. Upon receiving this information, the monitoring system can send the identity identifier fields to the official electronic identity authentication service platform for information retrieval and request through a pre-defined data interface. The official authentication platform verifies and queries the applicant's identity identifier, returning electronic identity authentication information uniquely bound to that identity. This electronic identity authentication information may include name, ID number, ID photo, issuing authority, and validity period, among other things; specific details are not limited in this embodiment. The monitoring system receives and parses the returned results, performs data format standardization processing, and identifies it as the authoritative electronic identity authentication information corresponding to the current applicant for subsequent matching and verification.

[0026] Step S120: Match the self-application identity information with the electronic identity authentication information to obtain the identity matching value.

[0027] Specifically, the self-application identity information and electronic identity authentication information undergo data standardization processing, unifying field formats, character encoding, and image feature dimensions to eliminate interference from format differences in the matching results. First, consistency verification is performed on text-based identity information. The name and ID number in the self-application identity information are compared character-by-character with the corresponding fields in the electronic identity authentication information to determine if they belong to the same person. If the text identity information matches, facial image features from the self-application identity information and authoritative facial features stored in the electronic identity authentication information are extracted. A preset feature similarity algorithm is used to compare and calculate the two sets of facial features, generating a normalized numerical result, which is the identity matching value. If the text identity information does not match, the identity matching value is directly determined to be below the minimum threshold, eliminating the need for facial feature comparison and proceeding directly to the subsequent anomaly handling process.

[0028] Step S130: When the identity matching value is not higher than the preset matching threshold, retrieve the applicant's historical access behavior information from the smart park's full-domain access log, and determine the applicant's identity credibility index based on the historical access behavior information.

[0029] Specifically, the preset matching threshold can be set by relevant technical personnel according to actual needs, and the specific value is not specifically limited in this application embodiment. If the identity matching value is higher than the preset matching threshold, it is determined that the identity information submitted by the applicant in this self-application meets the consistency requirements with the authoritative electronic identity authentication information, and the identity verification is passed. The supervision system can directly complete the establishment of the park identity file for the applicant based on the verification result, and grant corresponding access permissions. A globally unique identity identifier is generated for an applicant and a standardized identity file is established. At the same time, according to the permission rules of the employee's company and department, the system automatically grants access permissions to the corresponding building, floor and office area. The permission data is synchronized to all access control devices in the park. Employees can directly achieve seamless access to the park by facial recognition, mini-program code or electronic ID card code, without having to perform offline identity information supplementation and manual permission configuration processes.

[0030] If the identity matching value is not higher than the preset matching threshold, the self-application for identity verification is deemed unsuccessful. The monitoring system can automatically initiate a behavior-assisted analysis process, which involves retrieving the applicant's access records within a preset analysis time period from the smart park's full-domain access log database. This extracts historical access behavior information, including frequency of occurrence, access trajectory, relationships with companions, and access to key areas. The preset analysis time period is a period prior to the current moment, and its duration can be 24 hours or 48 hours, encompassing multiple consecutive and non-overlapping historical access periods. Multi-dimensional quantitative analysis is performed on the historical access behavior information, and the calculation results from multiple dimensions are weighted and fused or comprehensively scored to ultimately obtain a quantitative indicator representing the applicant's credibility, namely, the identity credibility index. Further, to improve the accuracy of determining the applicant's identity credibility index, the index is determined based on historical access behavior information, specifically including steps S1301-S1306, such as... Figure 2 As shown, where: Step S1301: Based on historical passage behavior information, determine the applicant's historical frequency of appearance, historical passage trajectory, and historical companion behavior information for each historical passage period within the preset analysis time period.

[0031] Specifically, based on the self-application information provided by the applicant, a corresponding identity identifier can be determined. Using this identifier as a search index, all access records of the applicant within a preset analysis time period can be filtered from the smart park's overall access log. These records are then sorted chronologically to determine each historical access period. Based on each historical access period and its corresponding location, the historical frequency of the applicant within the preset analysis time period can be calculated. The applicant's historical access trajectory can be constructed by connecting the access control device codes, park area codes, and access point information corresponding to each historical access period. This historical trajectory represents the applicant's path within the smart park, formed by connecting multiple areas and access control points during a single access, thus characterizing the applicant's activity routes and behavioral habits within the smart park. By correlating and matching information with other individuals within the same historical travel period and area, records of individuals appearing alongside the applicant are extracted to form historical companion behavior information. This information refers to the identities, frequency, and duration of other individuals who appeared with or accompanied the applicant during the same or similar historical travel period and area. This information reflects the applicant's social connections and travel companion characteristics. The aforementioned historical frequency of appearance, historical travel trajectory, and historical companion behavior information are then structured and organized as the foundational data for subsequent calculations of stability rates, compliance, and correlation.

[0032] Step S1302: Based on the historical frequency of occurrence corresponding to each historical passage period, determine the stability rate of the historical frequency of occurrence of applicants in the preset analysis period.

[0033] Specifically, based on the historical frequency of each historical access period, the historical frequency of the applicant within the preset analysis period is statistically analyzed, i.e., the number of accesses within each historical access period. Based on the historical frequency of each historical access period, the average frequency of all historical access periods is calculated, and the absolute value of the deviation between the historical frequency of each historical access period and the average value is calculated. Then, the average deviation of all absolute deviations is calculated and normalized to obtain the stability rate of the applicant's historical frequency within the preset analysis period. The closer the value is to 1, the more stable the applicant's appearance pattern in the park at different times, and the higher the credibility of the behavior.

[0034] Step S1303: Determine the historical stable passage trajectory based on the historical passage trajectory corresponding to each historical passage period, and determine the stability rate of the applicant's historical passage trajectory in the preset analysis period based on the historical passage trajectory and historical stable passage trajectory corresponding to each historical passage period.

[0035] Specifically, path matching and frequency statistics are performed on all historical travel routes. The most frequently occurring habitual travel routes are identified as historical stable travel routes. Each historical travel route is then compared with a historical stable travel route, and the number of identical points, overlap length, and deviation are counted. Based on the overlap and deviation, a preset trajectory stability rate formula is used to quantify and calculate the historical travel route stability rate for the applicant within a preset analysis period. The specific process may include: The historical travel trajectory and historical stable travel trajectory corresponding to each historical travel period are subjected to trajectory feature quantification to obtain the historical travel trajectory feature value corresponding to each historical travel period and the historical stable travel trajectory feature value corresponding to the historical stable travel trajectory. Based on the historical travel trajectory feature value, the historical stable travel trajectory feature value and the preset trajectory stability rate formula corresponding to each historical travel period, the historical travel trajectory stability rate is determined.

[0036] Specifically, features such as passage points, area numbers, passage order, and point intervals in each historical passage trajectory and historical stable passage trajectory can be extracted based on a preset feature recognition algorithm. The unstructured path information is converted into computable numerical features, and the historical passage trajectory feature value corresponding to each historical passage trajectory and the historical stable passage trajectory feature value corresponding to each historical stable passage trajectory are obtained. The specific preset feature recognition algorithm is not specifically limited in this embodiment of the application.

[0037] The historical travel trajectory feature values ​​and historical stable travel trajectory feature values ​​corresponding to each historical travel period are imported into a preset trajectory stability rate formula to determine the historical travel trajectory stability rate. The preset trajectory stability rate formula is as follows: ; Among them, S t The historical travel trajectory stability rate (value range 0-1); n is the total number of historical passage periods within the preset analysis time period. P t，i The historical passage trajectory feature value corresponding to the i-th historical passage period; P 稳定 The historical stable traffic trajectory feature values ​​are used for the preset analysis time period; |P t，i –P 稳定 | represents the absolute deviation between the historical travel trajectory feature value and the historical stable travel trajectory feature value for the i-th historical travel period.

[0038] Step S1304: Based on the historical passage trajectory corresponding to each historical passage period and the passage trajectory stability rate corresponding to the preset analysis period, as well as the preset key areas in the smart park, determine the applicant's compliance level in the key areas corresponding to the preset analysis period.

[0039] Specifically, based on the stability rate of travel trajectories, trajectories that deviate from the usual route, have poor stability, or exhibit abnormal changes are identified from all historical travel trajectories and designated as key screening targets. Each historical travel trajectory is then matched with the spatial location and boundaries of pre-defined key areas to determine whether the applicant has approached, entered, or covered these key areas. Pre-defined key areas are sensitive areas within the smart park that require enhanced security control, such as equipment rooms, core R&D areas, data centers, control rooms, and financial areas. These can be pre-defined by relevant technical personnel based on actual needs. The compliance rate for approaching key areas is a quantitative compliance indicator obtained by comprehensively considering trajectory stability, key area approach behavior, and abnormal trajectory characteristics. It is used to assess whether there is an abnormal risk when the applicant approaches key areas. The specific process for determining the applicant's compliance rate for approaching key areas within a pre-defined analysis time period may include: Based on the stability rate of the traffic trajectory corresponding to the preset analysis time period, the abrupt traffic trajectory is identified from all historical traffic trajectories; based on the historical stable traffic trajectory and the abrupt traffic trajectory, the observation traffic trajectory is determined; based on the preset key areas in the smart park and the observation traffic trajectory, the historical traffic coverage of the applicant in the preset key areas within the preset analysis time period is determined; when the historical traffic coverage rate is higher than the preset coverage threshold, the historical body language data of the applicant when approaching the preset key areas within the preset analysis time period is obtained, and the historical body language data is used to determine the historical behavior suspiciousness; based on the historical traffic coverage and historical behavior suspiciousness, the compliance of approaching the key areas is determined.

[0040] Specifically, based on the stability rate of traffic trajectories corresponding to a preset analysis period, historical traffic trajectories that differ significantly from historical stable trajectories, deviate from the normal path, or exceed the normal fluctuation range are screened and identified as abruptly changing traffic trajectories. For example, historical traffic trajectories corresponding to the historical period in which the stability rate of traffic trajectories changes the most can be identified as abruptly changing traffic trajectories. The historical stable traffic trajectories and abruptly changing traffic trajectories are then merged, deduplicated, and integrated to form observational traffic trajectories for focused analysis.

[0041] The monitoring system pre-stores spatial feature information of preset key areas. This spatial feature information can include the area code, boundary coordinates, covered access control points, and access range of the preset key areas. The observed passage trajectory is decomposed into a continuous sequence of access points. Each access point sequence includes a device number, area code, and location information. The system determines whether each access point in the trajectory falls within the boundary of the preset key area, whether it passes through the preset key area, and whether statistical key features appear within a preset distance near the preset key area. Key features include, but are not limited to, the number of trajectories passing through / entering the preset key area, the number of times it passes through / enters the preset key area, and the total number of observed passage trajectories / total number of times. Based on the statistical results, a quantitative calculation is performed according to preset coverage calculation rules to obtain a historical access coverage between 0 and 1. The closer the value is to 1, the higher the degree to which the applicant's observed passage trajectory passes through, approaches, and enters the preset key area.

[0042] The preset coverage threshold can be set by relevant technical personnel according to actual needs, and the specific value is not specifically limited in this application embodiment. When the historical passage coverage rate is higher than the preset coverage threshold, it indicates that the applicant has abnormally and frequently approached, passed through or entered the preset key area within the preset analysis period. The coverage of the key area by the applicant's passage trajectory exceeds the reasonable passage range of normal trusted personnel, which poses a potential security risk and requires further risk identification by combining body behavior data.

[0043] Based on the spatial range of a preset key area, the system can extract images and behavioral records of applicants approaching, passing through, or entering the preset key area within a preset analysis period from the smart park's full-area access image acquisition equipment, video recognition logs, and access control capture records. This data can be analyzed to obtain historical body behavior data, including but not limited to: the duration of stay when approaching the preset key area; the number of times the applicant lingered or turned back around the preset key area; whether the applicant looked around or frequently turned their head; whether the applicant covered their face with their hands / objects; and whether the applicant exhibited abnormal pauses, peered through doors, or attempted to detour. Based on the extracted historical body behavior data, a quantitative score can be obtained according to the preset abnormal behavior scoring rules to obtain the historical behavior suspicion level. The value range is 0-1. The closer the value is to 1, the more abnormal the applicant's behavior is near the preset key area and the higher the risk. The specific preset abnormality scoring rules are not specifically limited in this application embodiment. If the applicant exhibits abnormal body behaviors such as staying continuously for more than the preset time, repeatedly turning back and wandering, frequently looking around, covering the face with hands or clothing, deliberately avoiding the camera area, or leaning against the access control or doors and windows to observe, then points will be added item by item according to the degree of abnormality. The more abnormal behaviors and the more obvious the manifestation, the higher the historical behavior suspicion level score. If the applicant only walks normally at a constant speed, without stopping, wandering, covering, or abnormal posture, then all scores are at a low level, and the historical behavior suspicion level is correspondingly low.

[0044] Finally, the historical access coverage and historical behavior suspiciousness are quantitatively summed to obtain the compliance of approaching key areas. By integrating access coverage and behavior suspiciousness to determine the compliance of approaching key areas, it is easier to more accurately identify potential risks such as unauthorized approach and intent to break in, and further improve the accuracy of the identity credibility index.

[0045] Step S1305: Based on the historical travel trajectory and historical companion behavior information corresponding to each historical travel period, determine the correlation degree of the applicant's historical companions in the preset analysis period.

[0046] Specifically, analyzing the correlation of historical companions aims to verify whether applicants are resident, trustworthy, and engaged in normal activities within the park by observing the regularity and consistency of their accompanying passages. This improves the accuracy of identity verification and reduces security risks associated with impersonation, intrusion, and abnormal identities. Using each historical passage period within a preset analysis timeframe as a unit, the historical passage trajectory of the applicant for each historical passage period is sequentially obtained, along with information on all passersby recorded in the overall passage log for each historical passage period. For each historical passage period, the applicant's historical passage trajectory is compared with the passage trajectories of other individuals within the same period. Individuals with highly overlapping passage periods, identical passage points, similar passage routes, and identical passage sequences are identified as companions during that period. For each historical travel period, the characteristics of the companions identified are analyzed. These characteristics include, but are not limited to, the number of times the companions and the applicant appear together, the overlap between the travel periods and the applicant's time, and the overlap between the travel trajectories and the applicant's paths. The analysis is then performed quantitatively according to a preset correlation calculation rule. The correlation of the applicant's historical companions within the preset analysis period is calculated, with a value ranging from 0 to 1. The closer the value is to 1, the more fixed the companion relationship is and the more regular and reliable the behavior is.

[0047] When the correlation of historical companions exceeds a preset correlation threshold, it indicates that the applicant has formed a long-term, fixed, and highly synchronized companionship relationship with some individuals, and their travel behaviors are highly intertwined. If the applicant exhibits unsafe, abnormal, or probing travel behavior, their highly correlated historical companions may also pose potential security risks. Therefore, it is necessary to analyze the trajectories of such companions synchronously to improve the comprehensiveness and accuracy of risk identification. Thus, when the correlation of historical companions exceeds the preset correlation threshold, it specifically also includes: Obtain historical travel behavior information of historically associated travel companions and determine the stability rate of their associated travel trajectories within a preset analysis period; identify the abrupt change time periods of the applicant's corresponding abrupt travel trajectory, and determine the abrupt travel trajectories of historically associated travel companions based on the abrupt travel time periods and the stability rate of their associated travel trajectories within the preset analysis period; optimize historical travel coverage based on the abrupt travel trajectories.

[0048] Specifically, when the correlation of historical companions exceeds a preset correlation threshold, individuals who frequently and consistently travel with the applicant can be identified as historically associated companions. The travel trajectory, time period distribution, and behavioral records of these historically associated companions are obtained within a preset analysis period. Using the same method as for the applicant, the stability rate of their associated travel trajectory for each historical travel period is calculated to determine whether their own trajectory is regular or exhibits abnormal fluctuations within the preset analysis period.

[0049] Based on the historical travel trajectory stability rate of the applicant for each historical travel period, the period in which the historical travel trajectory stability rate changed the most was determined, and this period was designated as the travel abrupt change period. Based on the historical travel trajectory stability rate of related personnel in each historical travel period, multiple initial travel periods in which the related travel stability rate changed were determined, and the stability rate change magnitude corresponding to each initial travel period was identified. The time interval between each initial travel period and the applicant's travel abrupt change period was calculated. The stability rate change magnitude and time interval corresponding to each initial travel period were quantified and summed to obtain a time score for each initial travel period. The related travel trajectory corresponding to the initial travel period with the highest time score was designated as the related abrupt change travel trajectory.

[0050] The identified historically associated travel trajectories of fellow travelers are temporally aligned and spatially overlaid with the applicant's own aberration travel trajectory to form a joint trajectory that includes the abnormal trajectories of both individuals. Then, following the aforementioned method of determining the applicant's historical travel coverage of the preset key areas within the smart park based on the observed travel trajectories, the historical travel coverage is recalculated and determined based on this joint trajectory. This optimizes the historical travel coverage rate determined in the above embodiments. Optimizing the historical travel coverage based on the associated aberration travel trajectory makes the calculation results of the compliance of key areas more closely match the actual travel scenario, improving the accuracy and rationality of the identity credibility index, thereby making the subsequent supplementary registration and supervision strategies more targeted and reliable.

[0051] Step S1306: Determine the credibility index of the applicant's identity based on the stability rate of historical occurrence frequency, the stability rate of historical travel trajectory, the compliance of proximity to key areas, and the correlation with historical companions.

[0052] Specifically, based on the actual needs of security management in the smart park, corresponding preset weight coefficients can be configured for each credibility indicator. Each weight coefficient is a non-negative number, and the sum of the weights is 1, reflecting the influence of different behavioral characteristics on identity credibility. A weighted summation method is used to comprehensively calculate the above multiple indicators. Each indicator value is multiplied by its corresponding weight coefficient and then summed to obtain a preliminary comprehensive score. The preliminary comprehensive score is then normalized to ensure that the final result falls within the [0, 1] interval, forming the identity credibility index. The closer the identity credibility index is to 1, the more regular, compliant, and stable the applicant's various access behaviors are, and the higher the probability that the applicant is a trusted resident in the smart park.

[0053] In this embodiment of the application, by performing multi-dimensional analysis of historical travel behavior information, the stability rate of the applicant's historical appearance frequency, the stability rate of historical travel trajectory, the compliance of proximity to key areas, and the correlation of historical companions are determined. This enables the quantitative calculation and accurate assessment of the identity credibility index. Compared with single-dimensional behavior analysis, the multi-dimensional feature fusion assessment method is more comprehensive and objective in reflecting the authenticity and credibility of the applicant's identity, effectively avoiding the assessment bias caused by single feature analysis. At the same time, by accurately quantifying various behavioral characteristics, it is easier to further refine the identity risk level, accurately distinguish between unintentional reporting errors and malicious identity spoofing, and provide a scientific and reliable basis for the dynamic configuration of supplementary monitoring parameters.

[0054] Step S140: Determine the supplementary recording supervision parameters based on the identity credibility index, and generate a supplementary recording supervision instruction based on the supplementary recording supervision parameters. The supplementary recording supervision parameters include the supplementary recording location and the supplementary recording dwell time.

[0055] Specifically, the supplementary registration supervision parameters corresponding to the identity credibility index can be determined based on a preset supervision parameter mapping relationship. The preset supervision parameter mapping relationship is the correspondence between the identity credibility index and the supplementary registration supervision parameters. Among them, the supplementary registration supervision parameters include the supplementary registration location and the supplementary registration duration. The specific content is not specifically limited in this embodiment of the application. For example, the preset supervision parameter mapping relationship can be: If the identity credibility index is ≥0.8 (high credibility): the supplementary registration location should be selected from key nodes on the applicant's usual route (such as near the gate or around key areas), and the supplementary registration time should be set to 0-15 seconds (only simple verification is required to reduce redundant operations). If 0.5 ≤ Identity Credibility Index < 0.8 (Medium Credibility): The supplementary recording location should focus on the preset key areas and surrounding areas, and the supplementary recording time should be set to 15-20 seconds (strengthen the investigation of anomalies and ensure no omissions). If the identity credibility index is <0.5 (low credibility): the supplementary recording location will focus on the preset key area and the surrounding 3-meter range, and the supplementary recording time will be set to 20-30 seconds (to comprehensively check for risks and avoid missing abnormal behavior).

[0056] Step S150: When it is detected that the applicant has arrived at the access control equipment of the smart park to perform offline identity supplementation, the supplementation behavior of the applicant at the access control equipment shall be supervised in accordance with the supplementation supervision instruction.

[0057] Specifically, the smart park access control equipment captures people's approach movements in real time, accurately identifying when an applicant arrives at the access control equipment and prepares to perform offline identity registration. The registration supervision process is triggered only when the applicant initiates the registration operation, without interfering with normal passage. The smart park access control equipment can be turnstiles, facial recognition terminals, etc. By automatically calling the generated registration supervision command, it is synchronously sent to the corresponding data collection module of the smart park access control equipment to record the applicant's registration behavior throughout. If the applicant does not stay at the designated registration location as required, the abnormal registration situation can be reported to the security control terminal so that relevant review personnel can promptly detect abnormal data entry.

[0058] In this embodiment of the application, by performing bidirectional matching and verification of self-applied identity information and electronic identity authentication information, authoritative verification of identity information can be achieved from the source, improving the reliability and credibility of identity authentication. When the matching does not reach the preset threshold, the identity credibility is quantified to achieve refined identification of identity risks, effectively distinguishing between unintentional errors in filling out forms and malicious identity spoofing. Under the premise of ensuring security, the efficiency of identity collection and supplementation processes is improved. At the same time, based on the credibility index, the supplementation location, stay duration and other supervision parameters are dynamically configured to implement targeted supervision at the access control terminal, enhancing the standardization and controllability of offline supplementation. Overall, the efficiency and credibility of the identity collection and supplementation stages are improved, reducing security risks such as identity theft and unauthorized access, reducing the risk of management oversights from the front end, and effectively alleviating the security management pressure of smart parks.

[0059] Furthermore, in order to effectively avoid recognition errors and misuse opportunities caused by fixed acquisition angles and standard postures, the method provided in this application embodiment may further include: Based on the applicant's historical access images and recognition logs, easily confused behavioral features are extracted, including facial lateralization habits, posture stability, and historical recognition confusion frequency. Personalized supplementary registration reinforcement items are generated based on these features. These personalized supplementary registration reinforcement items are integrated into the supplementary registration supervision instructions. When it is detected that the applicant is performing offline identity supplementary registration, targeted supervision is carried out based on the personalized supplementary registration reinforcement items.

[0060] Specifically, historical images and recognition logs of the individuals to be collected are retrieved, and the image and behavioral data are analyzed frame by frame. Three types of easily confused behavioral features are extracted and clearly labeled as such. These easily confused behavioral features include: Facial tilting habits: The angle and frequency of facial tilting can be recorded by statistically analyzing the applicant's daily facial orientation (such as habitual left or right tilting) as a characteristic of facial tilting habits; Postural stability: Postural fluctuation values ​​can be calculated by analyzing the applicant's daily walking posture (such as walking speed and arm swing amplitude) and used as a characteristic of postural stability. Identify confusion records: Review historical identification logs to identify confusion records between applicants and other personnel, and count the frequency and scenarios of confusion as features of historical identification confusion frequency.

[0061] When generating personalized supplementary recording enhancements based on easily confused behavioral features, we can focus on capturing facial images at the corresponding side angles during supplementary recording to ensure that the supplementary images are consistent with daily facial side angle habits and avoid recognition confusion caused by facial angle deviations. We can also focus on capturing the normal posture of the person being recorded during supplementary recording to ensure that the posture data is consistent with daily life and reduce posture confusion. In addition, we can increase feature collection (such as fingerprints and facial details) during supplementary recording to reduce the probability of recognition confusion with other people.

[0062] Personalized supplementary registration enhancements can be integrated into the existing supplementary registration supervision instructions, clarifying the focus of the registration. When an applicant arrives at the smart park access control equipment to perform offline identity supplementation, the personalized supplementary registration enhancements are automatically retrieved to monitor the applicant's registration behavior. If the monitoring process identifies a mismatch between the registration behavior and the personalized supplementary registration enhancements, voice / interface prompts can be generated to remind the applicant to readjust their posture or facial orientation. If multiple corrections fail to meet the requirements, the automatic registration channel is locked, and manual verification is initiated. Once the registration behavior fully complies with the personalized supplementary registration enhancements, the registration is confirmed as valid. At this point, a park identity file can be created for the applicant, and corresponding access permissions can be granted.

[0063] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0064] The above description is only a partial embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A smart park adaptive identity collection and supplementary recording supervision method, characterized in that, include: Obtain the self-application identity information provided by the applicant, and determine the applicant's electronic identity authentication information based on the self-application identity information; The self-application identity information is matched with the electronic identity authentication information to obtain an identity matching value; When the identity matching value is not higher than the preset matching threshold, the applicant's historical access behavior information is retrieved from the smart park's full-domain access log, and the applicant's identity credibility index is determined based on the historical access behavior information. The supplementary registration supervision parameters are determined based on the identity credibility index, and a supplementary registration supervision instruction is generated based on the supplementary registration supervision parameters. The supplementary registration supervision parameters include the supplementary registration location and the supplementary registration dwell time. When the applicant arrives at the access control device of the smart park to perform offline identity registration, the registration behavior of the applicant at the access control device is supervised according to the registration supervision instruction.

2. The method for adaptive identity collection and supplementary recording supervision in a smart park according to claim 1, characterized in that, The process of determining the applicant's identity credibility index based on the historical access behavior information includes: Based on the historical passage behavior information, the applicant's historical frequency of appearance, historical passage trajectory, and historical companion behavior information are determined for each historical passage period within the preset analysis time period. Based on the historical frequency of occurrence corresponding to each historical passage period, the stability rate of the historical frequency of occurrence of the applicant corresponding to the preset analysis period is determined; Based on the historical travel trajectory corresponding to each historical travel period, a historical stable travel trajectory is determined, and based on the historical travel trajectory corresponding to each historical travel period and the historical stable travel trajectory, the stability rate of the applicant's historical travel trajectory corresponding to the preset analysis period is determined; Based on the historical passage trajectory corresponding to each historical passage period and the passage trajectory stability rate corresponding to the preset analysis period, as well as the preset key areas within the smart park, the compliance of the applicant in the key areas corresponding to the preset analysis period is determined. Based on the historical travel trajectory and the behavior information of the historical companions corresponding to each historical travel period, the correlation degree of the applicant's historical companions corresponding to the preset analysis period is determined; Based on the stability rate of historical occurrence frequency, the stability rate of historical travel trajectory, the compliance of proximity to key areas, and the correlation of historical companions, the credibility index of the applicant's identity is determined.

3. The method for adaptive identity collection and supplementary recording supervision in a smart park according to claim 2, characterized in that, The step of determining the stability rate of the applicant's historical travel trajectory within the preset analysis time period based on the historical travel trajectory corresponding to each historical travel period and the historical stable travel trajectory includes: The historical travel trajectory corresponding to each historical travel period and the historical stable travel trajectory are subjected to trajectory feature quantization processing to obtain the historical travel trajectory feature value corresponding to each historical travel period and the historical stable travel trajectory feature value corresponding to the historical stable travel trajectory. The historical travel trajectory stability rate is determined based on the historical travel trajectory feature value corresponding to each historical travel period, the historical stable travel trajectory feature value, and the preset trajectory stability rate formula.

4. The method for adaptive identity collection and supplementary recording supervision in a smart park according to claim 2, characterized in that, The determination of the applicant's proximity to compliance in the key area corresponding to the preset analysis time period, based on the historical travel trajectory corresponding to each historical travel period and the travel trajectory stability rate corresponding to the preset analysis time period, as well as the preset key areas within the smart park, includes: Based on the stability rate of the traffic trajectory corresponding to the preset analysis time period, the sudden traffic trajectory is determined from all the historical traffic trajectories; Based on the historical stable travel trajectory and the sudden change travel trajectory, the observation travel trajectory is determined; Based on the preset key areas within the smart park and the observed passage trajectory, the historical passage coverage of the applicant in the preset key areas within the preset analysis time period is determined. When the historical access coverage rate is higher than the preset coverage threshold, the historical body behavior data of the applicant when he / she is near the preset key area during the preset analysis time period is obtained, and the suspicion of the historical behavior is determined based on the historical body behavior data. Based on the historical traffic coverage and the historical behavior suspiciousness, the proximity compliance of the key areas is determined.

5. The method for adaptive identity collection and supplementary recording supervision in a smart park according to claim 4, characterized in that, When the correlation of the historical peers is higher than a preset correlation threshold, the following is also included: Obtain historical association behavior information of historical association companions, and determine the stability rate of the associated travel trajectory of the historical association companions in the preset analysis time period; Identify the period of sudden change in the travel trajectory corresponding to the applicant, and determine the associated sudden change travel trajectory corresponding to the historical associated travel trajectories based on the period of sudden change in travel trajectory and the stability rate of the associated travel trajectories of the historical associated travel trajectories in the preset analysis period. The historical traffic coverage is optimized based on the associated mutation traffic trajectory.

6. The method for adaptive identity collection and supplementary recording supervision in a smart park according to claim 1, characterized in that, Also includes: Based on the applicant’s historical access images and recognition logs, easily confused behavioral features are extracted, including face lateralization habits, posture stability, and historical recognition confusion frequency. Personalized supplementary reinforcement items are generated based on the aforementioned easily confused behavioral characteristics; The personalized supplementary registration enhancement items are integrated into the supplementary registration supervision instructions. When it is detected that the applicant is performing offline identity supplementary registration, targeted supervision is carried out based on the personalized supplementary registration enhancement items.

Images