Unregistered household room attribution prediction method based on two-way access control and related equipment

Abstract

The application relates to the technical field of intelligent access control and community management, and particularly discloses a registered household room attribution prediction method based on a two-way access control and related equipment. The technical scheme of the application collects access records through a two-way access control terminal, identifies a same-traveling tailing event of an unregistered person and a registered household, constructs an undirected weighted graph, quantifies a same-traveling tailing correlation strength according to a same-traveling frequency ratio, a time period coverage and a node coverage, calculates a probability of attribution of the unregistered person to each candidate room by fusing time rules, in-building time lengths and access frequency characteristics, and outputs a verification list, solves the problems that a traditional one-way access control cannot perceive an unregistered person, cannot obtain complete in-out trajectories and lacks access behavior analysis, and improves the registered household room attribution prediction accuracy in a city village, so as to provide accurate telephone verification or on-site verification clues for grid staff.

Description

Technical Field

[0001] This invention relates to the field of intelligent access control and community management technology, and in particular to a method and related equipment for predicting the ownership of unregistered resident rooms based on two-way access control. Background Technology

[0002] Urban villages are a unique residential form in China's urbanization process, widely distributed in major and medium-sized cities. These areas are characterized by extremely high population mobility, frequent resident moves in and out, and lagging registration information updates. They also exhibit extremely high population density, with a single building typically containing dozens of rooms, making it difficult for landlords or property management companies to fully grasp the actual number of residents. Due to the combined effects of these factors, nearly half of the residents in urban villages have not completed real-name registration, creating a serious management blind spot and posing a severe challenge to grassroots governance work such as community security, fire safety, and public health. Establishing a correspondence between unregistered residents and their specific rooms, providing grid workers with accurate leads for telephone verification or door-to-door verification, has become a core issue that urgently needs to be addressed for the refined management of urban villages.

[0003] Although access control systems are widely deployed in urban villages, traditional access control systems have significant shortcomings in practical applications: First, the system only records the door-opening behavior of registered personnel, completely failing to detect the passage of unregistered individuals; second, the equipment uses a one-way data collection mode, deployed only at entrances or exits, unable to capture complete entry and exit trajectories; third, the system lacks the ability to analyze passage behavior, making it difficult to extract valuable information from massive amounts of passage data. These deficiencies mean that existing access control technology cannot support the need for predicting room ownership for unregistered residents.

[0004] Therefore, there is an urgent need to provide a technical solution to address the above problems. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a method and related equipment for predicting the ownership of unregistered resident rooms based on two-way access control.

[0006] In a first aspect, the present invention provides a method for predicting the ownership of unregistered resident rooms based on two-way access control, the technical solution of which is as follows: Based on the access records collected by the two-way access control terminal, identify the following events between unregistered persons and registered residents, and construct an undirected weighted graph with persons as nodes and the number of events as edge weights; Based on the edge weights in the undirected weighted graph, the peer-to-peer following association strength between the unregistered personnel and each of the registered households is determined by the peer-to-peer frequency ratio, time period coverage, and node coverage. Extract the following association strength, time pattern characteristics, building duration characteristics, and passage frequency characteristics of the unregistered personnel; Obtain the set of registered residents in each candidate room. Calculate a first component based on the following association strength between the unregistered person and each registered resident in the set of registered residents. Calculate a second component based on the similarity between the temporal pattern characteristics of the unregistered person and the temporal pattern characteristics of each registered resident in the set of registered residents. Calculate a third component based on the unregistered person's time spent in the building. Calculate a fourth component based on the unregistered person's passage frequency characteristics. Sum the first, second, third, and fourth components with weights to obtain the probability that the unregistered person belongs to the candidate room. Sort all candidate room ownership probabilities from highest to lowest and output a checklist containing candidate room identifiers and their ownership probabilities.

[0007] The beneficial effects of the method for predicting the room ownership of unregistered residents based on two-way access control according to the present invention are as follows: The method of this invention collects access records through a two-way access control terminal, identifies events of unregistered persons following registered residents, and constructs an undirected weighted graph. Based on the ratio of the number of times they follow each other, the coverage of time periods, and the coverage of nodes, the association strength of following each other is quantified. By integrating time patterns, duration of stay in the building, and access frequency characteristics, the probability of unregistered persons belonging to each candidate room is calculated and a verification list is output. This solves the problems of traditional one-way access control systems being unable to detect unregistered persons, having difficulty obtaining complete entry and exit trajectories, and lacking access behavior analysis. It improves the accuracy of predicting room ownership for unregistered residents in urban villages and provides grid workers with accurate clues for telephone verification or door-to-door verification.

[0008] Based on the above solution, the method for predicting the ownership of unregistered resident rooms based on two-way access control can be further improved as follows.

[0009] In one alternative approach, the steps for identifying tailgating events between unregistered individuals and registered residents based on access records collected by the two-way access control terminal include: When an unregistered person in the passage record is at the same access control node as a registered resident, the passage time difference is less than a preset time threshold, and the passage direction is the same, they are determined to be traveling together. When the time difference between the unregistered person in the passage record and the registered resident is less than the preset time threshold, the spatial distance between the two people in the video is less than the preset distance threshold, and the unregistered person does not open the door independently, it is determined to be a tailgating relationship.

[0010] The advantages of adopting the above optional methods are as follows: further refine the identification steps of peer tailing events, determine peer relationship by the same access control node, passage time difference and passage direction, and determine tailing relationship by combining spatial distance and non-independent door opening operation, distinguish the two association modes from multiple dimensions, reduce misjudgment, and provide a more reliable edge weight data foundation for the construction of undirected weighted graph.

[0011] In one alternative approach, the step of determining the peer-to-peer trailing association strength between the unregistered person and each of the registered households based on the edge weights in the undirected weighted graph, using peer frequency ratio, time period coverage, and node coverage, includes: Based on the edge weights in the undirected weighted graph, the sum of the number of times the unregistered person travels together and the number of times the unregistered person follows the registered household is calculated as the ratio of the number of times the unregistered person travels together to the total number of times the unregistered person travels together, which is used as the ratio of the number of times the unregistered person travels together. The proportion of the number of different hour segments covered by the unregistered person and the registered household to the total number of hour segments covered by the unregistered person is calculated as the time period coverage. The node coverage is calculated as the proportion of the number of different access control nodes involved in the passage of the unregistered person and the registered resident to the total number of access control nodes involved in the passage of the unregistered person. The weighted sum of the peer-to-peer frequency ratio, the time period coverage, and the node coverage yields the peer-to-peer trailing association strength between the unregistered person and the registered household.

[0012] The beneficial effects of adopting the above-mentioned optional methods are: further quantifying the strength of peer following association from three dimensions of frequency, time period and space, and weighting and integrating peer frequency ratio, time period coverage and node coverage, so as to make the assessment of the closeness of association between unregistered persons and each registered household more comprehensive and objective, and lay a solid data foundation for subsequent attribution probability calculation.

[0013] In one alternative approach, the time pattern feature is a daily travel time distribution vector, and the similarity is the cosine similarity between the daily travel time distribution vector of the unregistered person and the daily travel time distribution vector of each registered household in the set of registered households.

[0014] The beneficial effects of adopting the above-mentioned optional methods are as follows: the time pattern characteristics are further defined as the distribution vector of the passage time throughout the day, and the cosine similarity is used to measure the consistency of time behavior between unregistered persons and each registered household, making the quantification of time dimension similarity more clear and standardized, and providing a stable and reliable time pattern basis for the calculation of attribution probability.

[0015] In one alternative approach, the time spent in the building is nighttime; the step of calculating the third component based on the time spent in the building by the unregistered person includes: The ratio of the nighttime duration of the unregistered person to the maximum nighttime duration of all residents is taken as the third component.

[0016] The beneficial effects of adopting the above-mentioned optional method are as follows: further taking the nighttime duration in the building as a feature of the duration in the building, calculating the third component by the ratio of the nighttime duration in the building of unregistered persons to the maximum nighttime duration in the building of all households, using nighttime stay behavior to reflect residential stability, and providing intuitive duration dimension support for room ownership determination.

[0017] In one optional approach, the passage frequency characteristic is the cumulative number of passages; the step of calculating the fourth component based on the passage frequency characteristic of the unregistered persons includes: The fourth component is obtained by normalizing the cumulative number of passages of the unregistered personnel after performing a logarithmic transformation.

[0018] The beneficial effects of adopting the above-mentioned optional method are as follows: by further using the cumulative number of passages as the passage frequency feature, and by normalizing the calculation of the fourth component after logarithmic transformation, the excessive influence of extreme passage frequencies on the attribution probability is reduced, so that the passage frequency feature maintains a reasonable weight in the probability calculation and avoids high-frequency records dominating the judgment result.

[0019] In one alternative approach, it also includes: After sorting all candidate room ownership probabilities from high to low, the highest ownership probability is selected from the sorting results, and the verification priority is determined based on the confidence interval in which the highest ownership probability falls.

[0020] The beneficial effects of adopting the above optional method are as follows: after outputting the verification list, the verification priority is determined according to the confidence interval of the highest attribution probability, so that grid members can reasonably arrange the verification order according to the probability confidence level, concentrate limited verification resources on high confidence clues, and optimize the execution order of verification work.

[0021] Secondly, the present invention provides a system for predicting the ownership of unregistered resident rooms based on two-way access control. The technical solution of the system is as follows: The module is used to identify tailgating events between unregistered persons and registered residents based on the access records collected by the two-way access control terminal, and to construct an undirected weighted graph with persons as nodes and event counts as edge weights. The determination module is used to determine the peer trailing association strength between the unregistered persons and each of the registered households based on the edge weights in the undirected weighted graph, through peer frequency ratio, time period coverage, and node coverage. The extraction module is used to extract the following association strength, time pattern characteristics, building duration characteristics, and passage frequency characteristics of the unregistered personnel. The calculation module is used to obtain the set of registered residents in each candidate room, calculate a first component based on the following association strength between the unregistered person and each registered resident in the set of registered residents, calculate a second component based on the similarity between the time pattern characteristics of the unregistered person and the time pattern characteristics of each registered resident in the set of registered residents, calculate a third component based on the time spent in the building of the unregistered person, calculate a fourth component based on the frequency of passage of the unregistered person, and then sum the first, second, third, and fourth components by weight to obtain the probability of the unregistered person belonging to the candidate room. The output module sorts all candidate room ownership probabilities from high to low and outputs a checklist containing candidate room identifiers and their ownership probabilities.

[0022] The beneficial effects of the unregistered resident room ownership prediction system based on two-way access control of the present invention are as follows: The system of this invention collects access records through a two-way access control terminal, identifies events of unregistered persons following registered residents, and constructs an undirected weighted graph. Based on the ratio of the number of times they follow each other, the coverage of time periods, and the coverage of nodes, the system quantifies the correlation strength of the following behavior. It integrates time patterns, duration of stay in the building, and access frequency characteristics to calculate the probability of unregistered persons belonging to each candidate room and outputs a verification list. This solves the problems of traditional one-way access control systems, which cannot detect unregistered persons, have difficulty obtaining complete entry and exit trajectories, and lack access behavior analysis. It improves the accuracy of predicting room ownership for unregistered residents in urban villages and provides grid workers with accurate clues for telephone verification or door-to-door verification.

[0023] Thirdly, the technical solution of an electronic device according to the present invention is as follows: The system includes a memory, a processor, and a program stored in the memory and running on the processor, wherein the processor executes the program to implement the steps of the method for predicting the ownership of unregistered resident rooms based on two-way access control as described in this invention.

[0024] Fourthly, the technical solution of a computer-readable storage medium provided by the present invention is as follows: The computer-readable storage medium stores instructions that, when read, cause the computer-readable storage medium to perform the steps of the method for predicting the ownership of unregistered resident rooms based on two-way access control as described in this invention.

[0025] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0026] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a flowchart illustrating an embodiment of the method for predicting the ownership of unregistered resident rooms based on two-way access control according to the present invention. Figure 2 This is a schematic diagram of an embodiment of the unregistered resident room ownership prediction system based on two-way access control according to the present invention; Figure 3 This is a schematic diagram of an embodiment of an electronic device according to the present invention. Detailed Implementation

[0027] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0028] Figure 1 This diagram illustrates a flowchart of an embodiment of a method for predicting the ownership of unregistered resident rooms based on two-way access control, provided by the present invention. This method can be executed by electronic devices such as terminal devices or servers. The terminal device can be any fixed or mobile terminal, such as user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, vehicle-mounted device, or wearable device. The server can be a single server or a server cluster consisting of multiple servers. Any electronic device can implement the method for predicting the ownership of unregistered resident rooms based on two-way access control by having its processor call computer-readable instructions stored in its memory. Figure 1 As shown, it includes the following steps: S1. Based on the access records collected by the two-way access control terminal, identify the following events between unregistered personnel and registered residents, and construct an undirected weighted graph with personnel as nodes and event counts as edge weights.

[0029] A two-way access control terminal refers to an intelligent device deployed at building entrances and exits that simultaneously collects data on personnel passage in both directions (entry and exit). It can record access triggered by facial recognition for registered residents, as well as facial images and videos of unregistered individuals. For example, a two-way intelligent access control terminal installed at the entrance of a building in a village in City C records a passage record when registered resident A enters via facial recognition. When unregistered resident B follows A in, a facial image and video of B are also captured via a camera. A passage record refers to each personnel passage event data collected by the two-way access control terminal, which includes at least the person's identifier, passage time, passage direction, and the corresponding access control node identifier. For example, a passage record might be: Person ID "Unknown_001", Passage Time "May 1, 2026, 20:35:22", Passage Direction "Enter", Access Control Node Identifier "Building F Entrance".

[0030] Unregistered persons refer to individuals who have not completed real-name registration in the access control system but whose access behavior is recorded by the access control terminal. For example, tenant B has just moved into Building F in the urban village and has not yet registered his identity information with the property management office. Every time B enters or exits the building, he is recorded as an unregistered person by the access control terminal. Registered residents refer to individuals who have completed real-name registration in the access control system and can automatically open doors through facial recognition. For example, B's roommate A has registered his identity information with the property management office. Every time he enters or exits the building, he triggers door opening through facial recognition, and the access control system records A's access behavior.

[0031] Among them, a peer-to-peer tailing event refers to the behavior of two people passing through the same access control node in the same direction within a similar time frame, where at least one person does not open the door independently but follows the other. This includes peer-to-peer and tailing relationships. For example, if unregistered person B and registered resident A are at the same access control node, with a time difference of less than 30 seconds and both entering in the same direction, and B follows A directly into the access control node without facial recognition, this event is judged as a peer-to-peer tailing event. An undirected weighted graph is a graph structure constructed with people as nodes and the number of peer-to-peer tailing events between people as edge weights, where the edges are not directional. For example, if there are 32 peer-to-peer tailing events between people A and B, then there is an edge between nodes A and B in the graph with an edge weight of 32.

[0032] S2. Based on the edge weights in the undirected weighted graph, determine the peer-following association strength between the unregistered personnel and each of the registered households through peer frequency ratio, time period coverage, and node coverage.

[0033] In this context, edge weight refers to the numerical value attached to the edge connecting two nodes in an undirected weighted graph. This value is equal to the total number of trailing events between the two individuals. For example, if the total number of trailing events between person A and person B is 32, then the edge weight connecting A and B is 32.

[0034] The following metrics are used to determine the frequency of unregistered individuals traveling together: **Follow-up frequency ratio:** This refers to the proportion of the total number of times an unregistered person and a registered resident travel together to the total number of times an unregistered person passes through a property. For example, if unregistered person B has 100 total passages, and 32 of those times they followed registered resident A, then the frequency ratio of B to A is 0.32. **Time period coverage:** This refers to the proportion of the number of different hour periods covered by unregistered individuals traveling together with registered residents to the total number of hour periods covered by unregistered individuals. For example, if B's ​​passage covers 18 different hour periods, and B's passage with A covers 10 hour periods, then the time period coverage is 10 / 18. **Node coverage:** This refers to the proportion of the number of different access control nodes involved in unregistered individuals traveling together with registered residents to the total number of access control nodes involved in unregistered individuals' passages. For example, if B's ​​passage involves 5 access control nodes, and B's passage with A involves 3 access control nodes, then the node coverage is 3 / 5.

[0035] Among them, the peer-to-peer following association strength refers to a comprehensive indicator that quantifies the closeness of the peer-to-peer following relationship between unregistered persons and registered residents. It is obtained by weighted summation of peer-to-peer frequency ratio, time period coverage, and node coverage. For example, the peer-to-peer frequency ratio of B to A is 0.32, the time period coverage is 10 / 18, and the node coverage is 3 / 5. Different association strength values ​​will be obtained by using different weighting coefficients.

[0036] Specifically, the edge weight is defined as: ,in Personnel With personnel The total number of trailing events between the same group. The ratio of the number of events between the same group is defined as: ,in Personnel Total number of passages. Time period coverage is defined as: ,in Personnel With personnel The number of different hourly segments covered by peers, Personnel Total number of hourly segments covered by the passage. Node coverage is defined as: ,in Personnel With personnel The number of different access control nodes involved in the same industry Personnel Total number of access control nodes involved in the passage. Same-line following correlation strength. Calculated using the following formula: ;in, , , These are preset weighting coefficients, used to adjust the contribution of peer frequency ratio, time period coverage, and node coverage to association strength.

[0037] For example, the total number of tailgating incidents between unregistered person B and registered resident A. Total number of passes for B The ratio of the number of times each person travels in the same row is 0.32; the number of different hour segments covered by B and A in the same row. Total number of hour segments covered by B-passage Then the time period coverage is The number of different access control nodes involved in B and A traveling together. The total number of access control nodes involved in passage B Then the node coverage is ;Pick , , The correlation strength was calculated. In practical applications, the weights can be adjusted according to the scenario.

[0038] S3. Extract the following association strength, time pattern characteristics, building duration characteristics, and passage frequency characteristics of the unregistered personnel.

[0039] Among them, the temporal regularity characteristic refers to a vector describing the distribution characteristics of personnel passage behavior over time, specifically the daily passage time distribution vector; for example, in B's daily passage time distribution vector, the number of passages during the nighttime period (22:00-06:00) accounts for 0.7 of the total number of passages, the early morning period (06:00-09:00) accounts for 0.2, and the remaining time periods account for 0.1. The building dwelling duration characteristic refers to the length of time a person stays in the building after entering it each time, specifically the nighttime dwelling duration; for example, B's average dwelling time after entering the building each night is 8.5 hours, and B's nighttime dwelling duration is 8.5 hours. The passage frequency characteristic refers to the frequency with which a person enters and exits the building within the statistical period, specifically the cumulative number of passages; for example, B's cumulative number of passages in the past 30 days is 100.

[0040] S4. Obtain the set of registered residents in each candidate room. Calculate a first component based on the following association strength between the unregistered person and each registered resident in the set of registered residents. Calculate a second component based on the similarity between the temporal pattern characteristics of the unregistered person and the temporal pattern characteristics of each registered resident in the set of registered residents. Calculate a third component based on the unregistered person's time spent in the building. Calculate a fourth component based on the unregistered person's passage frequency characteristics. Sum the first, second, third, and fourth components with weights to obtain the probability that the unregistered person belongs to the candidate room.

[0041] Here, "candidate room" refers to a room in the target building that may have unregistered residents, i.e., a room whose attribution probability needs to be calculated. For example, if the target building has 20 rooms, rooms 101, 102, and 103 are candidate rooms that B may reside in. "Registered resident set" refers to the set of all residents in the candidate rooms who have completed real-name registration. For example, the registered resident set for room 101 is {A, C}, and the registered resident set for room 102 is {D}.

[0042] The first component refers to the component contributed by the peer-following association strength in the attribution probability calculation. Specifically, it is the average peer-following association strength between unregistered persons and all registered residents in the candidate room. For example, if the association strength between B and A in room 101 is 0.65 and the association strength between B and C is 0.30, then the first component is (0.65 + 0.30) / 2 = 0.475. The second component refers to the component contributed by the temporal pattern similarity in the attribution probability calculation. Specifically, it is the average cosine similarity between the all-day travel time distribution vector of unregistered persons and the all-day travel time distribution vector of registered residents in the candidate room. For example, if the cosine similarity between B and A is 0.9 and the cosine similarity between B and C is 0.7, then the second component is (0.9 + 0.7) / 2 = 0.8. The third component refers to the component contributed by the duration of time spent in the building in the attribution probability calculation. Specifically, it is the ratio of the nighttime duration of unregistered persons to the maximum nighttime duration of all residents. For example, if B's ​​nighttime duration is 8.5 hours and the maximum nighttime duration of all residents is 10 hours, then the third component is 8.5 / 10 = 0.85. The fourth component refers to the component contributed by the frequency of passage in the attribution probability calculation. Specifically, it is the normalized value after logarithmic transformation of the cumulative number of passages of unregistered persons. For example, if B's ​​cumulative number of passages is 100 and the maximum cumulative number of passages is 500, then the fourth component after logarithmic transformation is approximately 0.76.

[0043] The probability of belonging to a candidate room refers to the likelihood that an unregistered person belongs to a certain candidate room. It is obtained by weighted summation of the first, second, third, and fourth components. For example, the probability of B belonging to room 101 is 0.45×0.475+0.20×0.8+0.20×0.85+0.15×0.76=0.658.

[0044] Specifically, rooms are set up The registered households are Unregistered personnel Belonging to the room probability of belonging Calculated using the following formula: in, , , , To preset weights, As the first component, For the second component, The third component, This is the fourth component.

[0045] The calculation formulas for each component are as follows: First component: This indicates unregistered personnel. With the room The average strength of peer trailing association among all registered households in the area, of which For the room The number of registered households.

[0046] Second component: This indicates unregistered personnel. All-day travel time distribution vector With the room Resident travel time distribution vector Cosine similarity (in actual calculation, for unregistered personnel) With the room The average cosine similarity of the daily travel time distribution vectors of all registered residents.

[0047] Third component: ,in For unregistered persons The length of time spent in the building at night, This represents the longest nighttime duration of any resident in the building.

[0048] Fourth component: ,in For unregistered persons The cumulative number of passes, This represents the maximum cumulative number of passes among all personnel.

[0049] For example, the set of registered residents for candidate room 101 is The strength of the association between unregistered person B and A The strength of the association with C Then the first component The cosine similarity of the time patterns of B and A is 0.9, and that of B and C is 0.7. Therefore, the second component... B's nighttime hours in the building Hours, maximum nighttime duration in the building Hours, then the third component B's cumulative number of passes Maximum cumulative number of passes Then the fourth component Take weights , , , Then the probability of belonging Approximately 0.658.

[0050] S5. Sort all candidate room ownership probabilities from high to low and output a checklist containing candidate room identifiers and their ownership probabilities.

[0051] The checklist refers to the list of candidate room information output after sorting the room by ownership probability from high to low, which includes the candidate room identifier and its corresponding ownership probability; for example, the checklist output for B is: Room 101 (0.658), Room 102 (0.320), Room 103 (0.150).

[0052] The technical solution of this embodiment collects access records through a two-way access control terminal, identifies unregistered persons and registered residents following each other, and constructs an undirected weighted graph. Based on the ratio of the number of times they follow each other, the time period coverage, and the node coverage, the strength of the following association is quantified. By integrating time patterns, time spent in the building, and access frequency characteristics, the probability of unregistered persons belonging to each candidate room is calculated and a verification list is output. This solves the problems of traditional one-way access control that cannot detect unregistered persons, has difficulty obtaining complete entry and exit trajectories, and lacks access behavior analysis. It improves the accuracy of predicting the room ownership of unregistered residents in urban villages and provides grid workers with accurate clues for telephone verification or door-to-door verification.

[0053] In one alternative approach, the steps for identifying tailgating events between unregistered individuals and registered residents based on access records collected by the two-way access control terminal include: When an unregistered person in the passage record is at the same access control node as a registered resident, the time difference between their passage is less than a preset time threshold, and they are traveling in the same direction, they are determined to be traveling together.

[0054] The preset time threshold refers to the maximum allowable time difference when determining whether two people are traveling in the same direction or following each other. A time condition is met when the time difference between two people is less than this threshold. For example, if the preset time threshold is set to 30 seconds, the time difference between unregistered person B and registered resident A is 15 seconds, which is less than 30 seconds, thus meeting the time condition. A traveling in the same direction refers to the shared passage behavior of two people at the same access control point, with a time difference less than the preset time threshold and traveling in the same direction. For example, if B and A are at the same access control point, with a time difference of 15 seconds and both traveling in the same direction, they are determined to be traveling in the same direction.

[0055] When the time difference between the unregistered person in the passage record and the registered resident is less than the preset time threshold, the spatial distance between the two people in the video is less than the preset distance threshold, and the unregistered person does not open the door independently, it is determined to be a tailgating relationship.

[0056] The preset distance threshold refers to the maximum allowable spatial distance when determining a tailgating relationship. A spatial condition is met when the spatial distance between two people in the video frame is less than this threshold. For example, if the preset distance threshold is set to 0.5 meters, the spatial distance between unregistered person B and registered resident A in the video frame is 0.3 meters, which is less than 0.5 meters, thus meeting the spatial condition. A tailgating relationship refers to a following behavior formed when the time difference between the tailgating person and the person opening the door is less than a preset time threshold, the spatial distance between the two people in the video frame is less than the preset distance threshold, and the tailgating person does not independently open the door. For example, if B follows A into the building with a time difference of 10 seconds, and B is close to A in the video frame without B using facial recognition, then a tailgating relationship is determined.

[0057] Among the above-mentioned optional methods, the identification steps for peer tailing events are further refined. Peer relationships are determined by the same access control node, passage time difference, and passage direction. Tailing relationships are determined by spatial distance and failure to open the door independently. The two association modes are distinguished from multiple dimensions, reducing misjudgment and providing a more reliable edge weight data foundation for the construction of undirected weighted graphs.

[0058] In one alternative approach, the step of determining the peer-to-peer trailing association strength between the unregistered person and each of the registered households based on the edge weights in the undirected weighted graph, using peer frequency ratio, time period coverage, and node coverage, includes: Based on the edge weights in the undirected weighted graph, the ratio of the sum of the number of times the unregistered person travels together and the number of times the unregistered person follows the registered household to the total number of times the unregistered person travels together is calculated as the number of times the unregistered person travels together.

[0059] The proportion of different hourly segments covered by the unregistered person and the registered household to the total number of hourly segments covered by the unregistered person is calculated as the time period coverage.

[0060] The number of different access control nodes involved in the passage between the unregistered person and the registered resident is calculated as the proportion of the total number of access control nodes involved in the passage of the unregistered person, and this proportion is used as the node coverage.

[0061] The weighted sum of the peer-to-peer frequency ratio, the time period coverage, and the node coverage yields the peer-to-peer trailing association strength between the unregistered person and the registered household.

[0062] Among the above-mentioned optional methods, the strength of peer-following association is further quantified from three dimensions: frequency, time period, and space. The peer frequency ratio, time period coverage, and node coverage are weighted and integrated to make the assessment of the closeness of association between unregistered persons and each registered household more comprehensive and objective, laying a solid data foundation for subsequent attribution probability calculation.

[0063] In one alternative approach, the time pattern feature is a daily travel time distribution vector, and the similarity is the cosine similarity between the daily travel time distribution vector of the unregistered person and the daily travel time distribution vector of each registered household in the set of registered households.

[0064] The all-day passage time distribution vector refers to the vector formed by dividing a 24-hour day into several time periods and counting the percentage of passages in each time period. For example, if B divides a day into 24-hour periods, the percentage of passages between 10 PM and 11 PM is 0.1, and the percentage between 11 PM and midnight is 0.2. Then the all-day passage time distribution vector is a vector of length 24.

[0065] Among the above-mentioned optional methods, the time pattern characteristics are further defined as the distribution vector of travel time throughout the day. Cosine similarity is used to measure the consistency of time behavior between unregistered persons and each registered household, making the quantification of time dimension similarity more clear and standardized, and providing a stable and reliable time pattern basis for the calculation of attribution probability.

[0066] In one alternative approach, the time spent in the building is nighttime; the step of calculating the third component based on the time spent in the building by the unregistered person includes: The ratio of the nighttime duration of the unregistered person to the maximum nighttime duration of all residents is taken as the third component.

[0067] The nighttime building stay refers to the average length of time an individual stays in the building each time they enter during the nighttime period, which is from 22:00 to 06:00 the next day. For example, if person B enters the building 10 times during the nighttime period, with each stay lasting 8 hours, 9 hours, 8.5 hours, etc., the average nighttime building stay is 8.5 hours. The maximum nighttime building stay refers to the maximum nighttime building stay among all the individuals recorded in the target building. For example, the maximum nighttime building stay among all individuals in the building is 10 hours.

[0068] Among the above-mentioned optional methods, the duration of nighttime stay in the building is further used as a feature of the duration of nighttime stay. The third component is calculated by the ratio of the duration of nighttime stay in the building of unregistered persons to the maximum duration of nighttime stay in the building of all households. The nighttime stay behavior reflects the stability of residence and provides an intuitive duration dimension to support the determination of room ownership.

[0069] In one optional approach, the passage frequency characteristic is the cumulative number of passages; the step of calculating the fourth component based on the passage frequency characteristic of the unregistered persons includes: The fourth component is obtained by normalizing the cumulative number of passages of the unregistered personnel after performing a logarithmic transformation.

[0070] In the above-mentioned optional methods, the cumulative number of passages is further used as the passage frequency feature. The fourth component is calculated by normalization after logarithmic transformation, which reduces the excessive influence of extreme passage frequencies on the attribution probability, so that the passage frequency feature maintains a reasonable weight in the probability calculation and avoids high-frequency records dominating the judgment result.

[0071] In one alternative approach, it also includes: After sorting all candidate room ownership probabilities from high to low, the highest ownership probability is selected from the sorting results, and the verification priority is determined based on the confidence interval in which the highest ownership probability falls.

[0072] As shown in Table 1, the confidence interval refers to the confidence level divided according to the numerical range of the highest attribution probability, used to judge the reliability of the estimation result, including high confidence interval, medium confidence interval, and low confidence interval; for example, a highest attribution probability greater than or equal to 0.7 belongs to the high confidence interval, between 0.5 and 0.7 belongs to the medium confidence interval, and less than 0.5 belongs to the low confidence interval. Verification priority refers to the grid worker verification order determined according to the confidence interval of the highest attribution probability. A high confidence interval corresponds to immediate and proactive push to grid workers, a medium confidence interval corresponds to entering the observation queue and continuously accumulating data, and a low confidence interval corresponds to not pushing but continuing to accumulate passage data; for example, if B's ​​highest attribution probability is 0.85, which belongs to the high confidence interval, then the verification priority is the highest, and the grid worker should receive the push and prioritize verifying the room where B lives.

[0073] Table 1: In the above-mentioned optional methods, after outputting the verification list, the verification priority is further determined according to the confidence interval of the highest attribution probability, so that grid members can reasonably arrange the verification order according to the probability confidence level, concentrate limited verification resources on high confidence clues, and optimize the execution order of verification work.

[0074] In one alternative approach, the method further includes: clustering the undirected weighted graph using the Louvain community detection algorithm to identify closely related peer groups. The Louvain community detection algorithm divides nodes into different communities through modularity optimization, maximizing the sum of edge weights between nodes within the same community, thereby identifying groups of people with high-frequency peer-following behavior.

[0075] In another optional approach, the method further includes: receiving verification feedback results for candidate rooms in the verification list, and updating the calculation parameters of the peer-following association strength or the attribution probability based on the verification feedback results. Specifically, when the grid worker reports that the actual residence room of an unregistered person matches the predicted result, the edge weight between the unregistered person and the corresponding registered household is increased; when the feedback is inconsistent, the edge weight is decreased or the probability fusion weight coefficient is adjusted.

[0076] Figure 2 This diagram illustrates a structural schematic of an embodiment of a two-way access control-based unregistered resident room allocation prediction system 200 provided by the present invention. Figure 2 As shown, the unregistered resident room ownership prediction system 200 based on two-way access control includes: Module 201 is used to identify the following events between unregistered persons and registered residents based on the access records collected by the two-way access control terminal, and to construct an undirected weighted graph with persons as nodes and the number of events as edge weights. The determination module 202 is used to determine the peer trailing association strength between the unregistered persons and each of the registered households based on the edge weights in the undirected weighted graph, through the peer frequency ratio, time period coverage, and node coverage. Extraction module 203 is used to extract the following association strength, time pattern characteristics, building duration characteristics, and passage frequency characteristics of the unregistered personnel; The calculation module 204 is used to obtain the set of registered residents in each candidate room, calculate a first component based on the following association strength between the unregistered person and each registered resident in the set of registered residents, calculate a second component based on the similarity between the time pattern characteristics of the unregistered person and the time pattern characteristics of each registered resident in the set of registered residents, calculate a third component based on the time duration characteristics of the unregistered person, calculate a fourth component based on the passage frequency characteristics of the unregistered person, and sum the first component, second component, third component, and fourth component by weight to obtain the probability of the unregistered person belonging to the candidate room; Output module 205 is used to sort all candidate room ownership probabilities from high to low and output a checklist containing candidate room identifiers and their ownership probabilities.

[0077] In an alternative embodiment, the building module 201 is specifically used for: When an unregistered person in the passage record is at the same access control node as a registered resident, the passage time difference is less than a preset time threshold, and the passage direction is the same, they are determined to be traveling together. When the time difference between the unregistered person in the passage record and the registered resident is less than the preset time threshold, the spatial distance between the two people in the video is less than the preset distance threshold, and the unregistered person does not open the door independently, it is determined to be a tailgating relationship.

[0078] In an alternative embodiment, the determining module 202 is specifically used for: Based on the edge weights in the undirected weighted graph, the sum of the number of times the unregistered person travels together and the number of times the unregistered person follows the registered household is calculated as the ratio of the number of times the unregistered person travels together to the total number of times the unregistered person travels together, which is used as the ratio of the number of times the unregistered person travels together. The proportion of the number of different hour segments covered by the unregistered person and the registered household to the total number of hour segments covered by the unregistered person is calculated as the time period coverage. The node coverage is calculated as the proportion of the number of different access control nodes involved in the passage of the unregistered person and the registered resident to the total number of access control nodes involved in the passage of the unregistered person. The weighted sum of the peer-to-peer frequency ratio, the time period coverage, and the node coverage yields the peer-to-peer trailing association strength between the unregistered person and the registered household.

[0079] In one alternative approach, the time pattern feature is a daily travel time distribution vector, and the similarity is the cosine similarity between the daily travel time distribution vector of the unregistered person and the daily travel time distribution vector of each registered household in the set of registered households.

[0080] In one alternative approach, the time spent in the building is defined as nighttime time spent in the building; the calculation module 204 is specifically used for: The ratio of the nighttime duration of the unregistered person to the maximum nighttime duration of all residents is taken as the third component.

[0081] In one alternative approach, the passage frequency characteristic is the cumulative number of passages; the calculation module 204 is specifically used for: The fourth component is obtained by normalizing the cumulative number of passages of the unregistered personnel after performing a logarithmic transformation.

[0082] In one alternative approach, it also includes: The selection module is used to sort all candidate rooms by their ownership probability from high to low, select the highest ownership probability from the sorting results, and determine the verification priority based on the confidence interval in which the highest ownership probability is located.

[0083] It should be noted that the beneficial effects of the unregistered resident room ownership prediction system 200 based on two-way access control provided in the above embodiments are the same as those of the unregistered resident room ownership prediction method based on two-way access control, and will not be repeated here. Furthermore, the system provided in the above embodiments is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to the actual situation to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process is detailed in the method embodiments, and will not be repeated here.

[0084] The unregistered resident room allocation prediction system 200 based on two-way access control of the present invention can be a computer program (including program code) running on a computer device. For example, the unregistered resident room allocation prediction system 200 based on two-way access control of the present invention is an application software that can be used to execute the corresponding steps in the unregistered resident room allocation prediction method based on two-way access control of the present invention.

[0085] In some embodiments, the unregistered resident room ownership prediction system 200 based on two-way access control of the present invention can be implemented in a combination of hardware and software. As an example, the unregistered resident room ownership prediction system 200 based on two-way access control of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the unregistered resident room ownership prediction method based on two-way access control of the present invention. For example, the processor in the form of a hardware decoding processor can be one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0086] The modules described in the embodiments of this invention can be implemented in software or hardware. The names of the modules are not, in some cases, limiting the scope of the module itself.

[0087] An electronic device according to an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the above-mentioned methods for predicting the ownership of unregistered resident rooms based on two-way access control. That is, an electronic device according to an embodiment of the present invention may include, but is not limited to: a processor and a memory; the memory is used to store the computer program; the processor is used to execute the method for predicting the ownership of unregistered resident rooms based on two-way access control as shown in any embodiment of the present invention by calling the computer program.

[0088] In one alternative embodiment, an electronic device is provided, such as Figure 3 As shown, Figure 3 The illustrated electronic device 4000 includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0089] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0090] Bus 4002 may include a path for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus 4002 is represented by only one thick line, but this does not mean that there is only one bus or one type of bus.

[0091] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0092] The memory 4003 stores application code (computer program) for executing the present invention, and its execution is controlled by the processor 4001. The processor 4001 executes the application code stored in the memory 4003 to implement the content shown in the foregoing method embodiments.

[0093] Among them, electronic devices can also be terminal devices. A terminal device can be any terminal device that can install applications and access web pages through applications, including at least one of smartphones, tablets, laptops, desktop computers, smart speakers, smartwatches, smart TVs, and smart in-vehicle devices.

[0094] It should be noted that, Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0095] An embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the above-mentioned methods for predicting the ownership of unregistered resident rooms based on two-way access control.

[0096] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.

[0097] In an exemplary embodiment, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the aforementioned method for predicting the ownership of unregistered resident rooms based on two-way access control.

[0098] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0099] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0100] The computer-readable storage medium provided in this invention can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0101] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the method shown in the above embodiments.

[0102] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

[0103] It should be noted that the terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and represent a limitation on a specific order or sequence. Where appropriate, the order of use for similar objects can be interchanged so that the embodiments of this application described herein can be implemented in an order other than that shown or described.

[0104] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this invention can be specifically implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, this invention can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0105] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for predicting the ownership of unregistered resident rooms based on two-way access control, characterized in that, include: Based on the access records collected by the two-way access control terminal, identify the following events between unregistered persons and registered residents, and construct an undirected weighted graph with persons as nodes and the number of events as edge weights; Based on the edge weights in the undirected weighted graph, the peer-to-peer following association strength between the unregistered personnel and each of the registered households is determined by the peer-to-peer frequency ratio, time period coverage, and node coverage. Extract the following association strength, time pattern characteristics, building duration characteristics, and passage frequency characteristics of the unregistered personnel; Obtain the set of registered residents in each candidate room. Calculate a first component based on the following association strength between the unregistered person and each registered resident in the set of registered residents. Calculate a second component based on the similarity between the temporal pattern characteristics of the unregistered person and the temporal pattern characteristics of each registered resident in the set of registered residents. Calculate a third component based on the unregistered person's time spent in the building. Calculate a fourth component based on the unregistered person's passage frequency characteristics. Sum the first, second, third, and fourth components with weights to obtain the probability that the unregistered person belongs to the candidate room. Sort all candidate room ownership probabilities from highest to lowest and output a checklist containing candidate room identifiers and their ownership probabilities.

2. The method for predicting the ownership of unregistered resident rooms based on two-way access control according to claim 1, characterized in that, Based on the access records collected by the two-way access control terminal, the steps for identifying tailgating events between unregistered persons and registered residents include: When an unregistered person in the passage record is at the same access control node as a registered resident, the passage time difference is less than a preset time threshold, and the passage direction is the same, they are determined to be traveling together. When the time difference between the unregistered person in the passage record and the registered resident is less than the preset time threshold, the spatial distance between the two people in the video is less than the preset distance threshold, and the unregistered person does not open the door independently, it is determined to be a tailgating relationship.

3. The method for predicting the ownership of unregistered resident rooms based on two-way access control according to claim 2, characterized in that, The steps for determining the peer-to-peer trailing association strength between the unregistered persons and each of the registered households based on the edge weights in the undirected weighted graph, through peer frequency ratio, time period coverage, and node coverage, include: Based on the edge weights in the undirected weighted graph, the sum of the number of times the unregistered person travels together and the number of times the unregistered person follows the registered household is calculated as the ratio of the number of times the unregistered person travels together to the total number of times the unregistered person travels together, which is used as the ratio of the number of times the unregistered person travels together. The proportion of the number of different hour segments covered by the unregistered person and the registered household to the total number of hour segments covered by the unregistered person is calculated as the time period coverage. The node coverage is calculated as the proportion of the number of different access control nodes involved in the passage of the unregistered person and the registered resident to the total number of access control nodes involved in the passage of the unregistered person. The weighted sum of the peer-to-peer frequency ratio, the time period coverage, and the node coverage yields the peer-to-peer trailing association strength between the unregistered person and the registered household.

4. The method for predicting the ownership of unregistered resident rooms based on two-way access control according to claim 1, characterized in that, The time pattern feature is the daily travel time distribution vector, and the similarity is the cosine similarity between the daily travel time distribution vector of the unregistered person and the daily travel time distribution vector of each registered household in the set of registered households.

5. The method for predicting the ownership of unregistered resident rooms based on two-way access control according to claim 1, characterized in that, The duration of time spent in the building refers to the duration of time spent in the building at night. The step of calculating the third component based on the building dwelling duration characteristics of the unregistered persons includes: The ratio of the nighttime duration of the unregistered person to the maximum nighttime duration of all residents is taken as the third component.

6. The method for predicting the ownership of unregistered resident rooms based on two-way access control according to claim 1, characterized in that, The passage frequency characteristic is the cumulative number of passages; The step of calculating the fourth component based on the passage frequency characteristics of the unregistered persons includes: The fourth component is obtained by normalizing the cumulative number of passages of the unregistered personnel after performing a logarithmic transformation.

7. The method for predicting the ownership of unregistered resident rooms based on two-way access control according to any one of claims 1 to 6, characterized in that, Also includes: After sorting all candidate room ownership probabilities from high to low, the highest ownership probability is selected from the sorting results, and the verification priority is determined based on the confidence interval in which the highest ownership probability falls.

8. A system for predicting the ownership of unregistered resident rooms based on two-way access control, characterized in that, include: The module is used to identify tailgating events between unregistered persons and registered residents based on the access records collected by the two-way access control terminal, and to construct an undirected weighted graph with persons as nodes and event counts as edge weights. The determination module is used to determine the peer trailing association strength between the unregistered persons and each of the registered households based on the edge weights in the undirected weighted graph, through peer frequency ratio, time period coverage, and node coverage. The extraction module is used to extract the following association strength, time pattern characteristics, building duration characteristics, and passage frequency characteristics of the unregistered personnel. The calculation module is used to obtain the set of registered residents in each candidate room, calculate a first component based on the following association strength between the unregistered person and each registered resident in the set of registered residents, calculate a second component based on the similarity between the time pattern characteristics of the unregistered person and the time pattern characteristics of each registered resident in the set of registered residents, calculate a third component based on the time spent in the building of the unregistered person, calculate a fourth component based on the passage frequency characteristics of the unregistered person, and then sum the first, second, third, and fourth components by weight to obtain the probability of the unregistered person belonging to the candidate room. The output module sorts all candidate room ownership probabilities from high to low and outputs a checklist containing candidate room identifiers and their ownership probabilities.

9. An electronic device, characterized in that, The electronic device includes a processor coupled to a memory storing at least one computer program, which is loaded and executed by the processor to enable the electronic device to implement the method for predicting the ownership of unregistered resident rooms based on two-way access control as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one computer program, which, when executed by a processor, implements the method for predicting the ownership of unregistered resident rooms based on two-way access control as described in any one of claims 1 to 7.

Images