A resident safety control method and system based on smart community

By conducting access control verification, behavior information collection and matching analysis of verified users in smart communities, detailed monitoring and verification of user behavior is achieved, and the reliability of household safety control is improved, and the poor safety control in traditional methods is solved. The problem.

CN117238070BActive Publication Date: 2024-11-19CHENGDU TIANCHENG TECH CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202311230245.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-09-21
Publication Date
2024-11-19
Estimated Expiration
2043-09-21

AI Technical Summary

Technical Problem

The reliability of household safety control in smart communities is mainly due to the inability of traditional access control control methods to effectively monitor and verify user behavior, resulting in security risks.

Method used

By performing access control and control verification for verified users, collecting their current and historical behavior information in the smart community, conducting behavior matching degree analysis, and performing security control operations based on the matching degree, including video surveillance and user monitoring to improve the reliability of security control.

Benefits of technology

The reliability of safety control of households in smart communities has been improved. Through the analysis of behavior matching degree and corresponding safety control measures, security risks have been reduced and user behavior monitoring and verification capabilities have been enhanced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117238070B_ABST
    Figure CN117238070B_ABST
Patent Text Reader

Abstract

The present invention provides a method and system for resident security management and control based on a smart community, which relates to the field of data processing technology. In the present invention, based on the target verification action determined by the verification action determination operation for the user to be verified, the access control verification operation is performed on the user to be verified, and when the user to be verified has the target verification action, the access control verification is passed; when it is determined based on the target verification action that the user to be verified has passed the access control verification, the current behavior information of the user to be verified in the target smart community is collected, and the historical behavior information of the user to be verified in the target smart community is extracted; the current behavior information and the historical behavior information are matched and determined, and the behavior matching degree between the current behavior information and the historical behavior information is output; based on the behavior matching degree, the security management and control operation is performed on the user to be verified. Based on the above method, the reliability of resident security management and control can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a resident safety management and control method and system based on a smart community. Background Art

[0002] Smart community can also be called smart community, which means making full use of the integrated application of new generation information technology such as Internet of Things, cloud computing, mobile Internet, etc. to provide community residents with a safe, comfortable, convenient, modern and intelligent living environment, thus forming a new management form of community based on information and intelligent social management and service. On this basis, it is generally believed that smart community is an organic combination of people (merchants, residents, property and community staff), services and intelligence. Intelligent intelligence should be close to life and truly bring convenience to people. Smart community mainly includes video surveillance, access management (personnel access, vehicle access, visitor management, welcome management), security alarm, smart door lock, video intercom, fire alarm, smart life, etc. Video surveillance can keep a picture of people passing by, whether it is active monitoring or post-event tracing, it can play a very important role. Community security monitoring system is indispensable, and traditional monitoring systems have the characteristics of unclear pictures and easy damage. Nowadays, intelligent monitoring system has clear pictures and automatic recognition and alarm functions. It is mainly used in public places, parking lots, entrances and exits, squares outside the door, entrances and exits of residential buildings and public areas of residential buildings in the community. Theft, fire, robbery, car scratching, littering, illegal parking and other phenomena can be monitored through the intelligent monitoring system, all suspicious people and things can be monitored, the harm to the residents' lives and property can be reduced, the property management of the community can be facilitated, problems in the community can be discovered in a timely manner, and there are also automatic early warning and alarm functions. Smart cameras can intelligently identify suspicious people and suspicious behaviors, and automatically send an early warning to the security monitoring room of the community after identification. When danger occurs, it can automatically alarm, quickly and efficiently ensure the emergency work of the community, and can also reduce the work of the community security personnel, save labor costs, trace back to the source of everything that happens in the community, and strengthen the community's security system.

[0003] In the process of realizing smart communities, in order to ensure the safety of residents, generally only the access control is controlled or verified, which leads to the problem of poor reliability of security control. Summary of the invention

[0004] In view of this, an object of the present invention is to provide a resident safety management method and system based on a smart community to improve the reliability of resident safety management.

[0005] To achieve the above objectives, the embodiments of the present invention adopt the following technical solutions:

[0006] A resident safety management and control method based on a smart community, comprising:

[0007] Based on the target verification action determined by the verification action determination operation for the user to be verified, a door access control verification operation is performed on the user to be verified, wherein the door access control verification operation includes prompting the user to be verified based on the target verification action, and passing the door access control verification when the user to be verified has the target verification action;

[0008] When it is determined based on the target verification action that the user to be verified has passed the access control verification, current behavior information of the user to be verified in the target smart community is collected, and historical behavior information of the user to be verified in the target smart community is extracted;

[0009] Performing behavior matching determination on the current behavior information and the historical behavior information, and outputting a behavior matching degree between the current behavior information and the historical behavior information;

[0010] Based on the behavior matching degree, security management and control operations are performed on the user to be verified.

[0011] In some preferred embodiments, in the above-mentioned resident safety management method based on smart community, when it is determined based on the target verification action that the user to be verified has passed the access control verification, the step of collecting the current behavior information of the user to be verified in the target smart community and extracting the historical behavior information of the user to be verified in the target smart community includes:

[0012] In the case where it is determined based on the target verification action that the user to be verified has passed the access control verification, determining a pre-configured target duration;

[0013] Based on the target duration, the current behavior of the user to be verified in the target smart community is monitored by video to collect corresponding current behavior information, where the current behavior information belongs to the monitoring video, and the duration of the monitoring video is equal to the target duration;

[0014] Based on the target duration, historical behavior information of the user to be verified in the target smart community is extracted, and the historical behavior information is a monitoring video formed by video monitoring of the historical behavior of the user to be verified in the target smart community for the target duration.

[0015] In some preferred embodiments, in the above-mentioned resident safety management method based on the smart community, the step of performing video monitoring on the current behavior of the user to be verified in the target smart community based on the target duration to collect the corresponding current behavior information includes:

[0016] Based on the target duration, the current behavior of the user to be verified in the target area in the target smart community is monitored by video to collect the corresponding current behavior information;

[0017] The step of extracting the historical behavior information of the user to be verified in the target smart community based on the target duration includes:

[0018] Based on the target duration, historical behavior information of the user to be verified belonging to the target area in the target smart community is extracted.

[0019] In some preferred embodiments, in the above-mentioned resident safety management method based on smart community, the step of determining the behavior matching between the current behavior information and the historical behavior information and outputting the behavior matching degree between the current behavior information and the historical behavior information includes:

[0020] Performing a feature mining operation on the current behavior information to output a current behavior description vector corresponding to the current behavior information, and performing a feature mining operation on the historical behavior information to output a historical behavior description vector corresponding to the historical behavior information;

[0021] Based on the current behavior description vector and the historical behavior description vector, a behavior matching degree between the current behavior information and the historical behavior information is analyzed.

[0022] In some preferred embodiments, in the above-mentioned resident safety management method based on smart community, the step of analyzing the behavior matching degree between the current behavior information and the historical behavior information based on the current behavior description vector and the historical behavior description vector includes:

[0023] Calculating cosine similarity between the current behavior description vector and the historical behavior description vector to output a corresponding first cosine similarity;

[0024] Performing a row-column swap operation on vector parameters of the current behavior description vector to output a swapped current behavior description vector corresponding to the current behavior description vector, multiplying the swapped current behavior description vector and the historical behavior description vector to output a corresponding first intermediate description vector, and, based on the first intermediate description vector and the current behavior description vector, analyzing an associated historical behavior description vector corresponding to the historical behavior description vector to implement association mining of the historical behavior description vector based on the current behavior description vector;

[0025] Performing a row-column swap operation on the vector parameters of the historical behavior description vector to output a swapped historical behavior description vector corresponding to the historical behavior description vector, multiplying the swapped historical behavior description vector and the current behavior description vector to output a corresponding second intermediate description vector, and, based on the second intermediate description vector and the historical behavior description vector, analyzing an associated current behavior description vector corresponding to the current behavior description vector to implement association mining of the current behavior description vector based on the historical behavior description vector;

[0026] Calculating cosine similarity of the historical behavior description vector and the associated historical behavior description vector to output a corresponding second cosine similarity;

[0027] Calculating cosine similarity between the current behavior description vector and the associated current behavior description vector to output a corresponding third cosine similarity;

[0028] Based on the first cosine similarity, the second cosine similarity, and the third cosine similarity, a behavior matching degree between the current behavior information and the historical behavior information is determined.

[0029] In some preferred embodiments, in the above-mentioned resident security management method based on the smart community, the step of performing security management operations on the user to be verified based on the behavior matching degree includes:

[0030] Extracting a pre-configured reference behavior matching degree, and performing a size comparison process on the behavior matching degree and the reference behavior matching degree to obtain a corresponding size comparison result;

[0031] If the size comparison result reflects that the behavior matching degree is greater than or equal to the reference behavior matching degree, determining not to perform a user monitoring operation on the user to be verified;

[0032] When the size comparison result reflects that the behavior matching degree is less than the reference behavior matching degree, it is determined to perform a user monitoring operation on the user to be verified, and the user monitoring operation at least includes continuous video monitoring of the user to be verified to achieve security management and control.

[0033] In some preferred embodiments, in the above-mentioned resident security management method based on the smart community, the step of performing a door access control verification operation on the user to be verified based on the target verification action determined by the verification action determination operation for the user to be verified includes:

[0034] Determine a user description vector to be verified corresponding to the user to be verified, wherein the user description vector to be verified is formed based on conversion data corresponding to the multidimensional data to be processed, wherein the multidimensional data to be processed is formed based on a fusion of a user description vector corresponding to each of at least one related user and a historical action description vector corresponding to each of at least one historical user action, wherein at least one of the related users belongs to a cell user related to the user to be verified, and at least one of the historical user actions belongs to an action that has occurred in history for each of the related users;

[0035] Determine a candidate user action description vector corresponding to a candidate user action, where the candidate user action belongs to a historical user action that has occurred in the history of the relevant user;

[0036] Performing a verification action determination operation on the user to be verified according to a combined description vector of the user description vector to be verified and the action description vector of the candidate user;

[0037] Based on the target verification action determined by the verification action determination operation, a door access control verification operation is performed on the user to be verified. The door access control verification operation includes giving an action prompt to the user to be verified based on the target verification action, and passing the door access control verification when the user to be verified has the target verification action.

[0038] The embodiment of the present invention further provides a resident safety management and control system based on a smart community, comprising:

[0039] An access control verification module, configured to perform an access control verification operation on the user to be verified based on a target verification action determined by performing a verification action determination operation on the user to be verified, wherein the access control verification operation includes prompting the user to be verified with an action based on the target verification action, and passing the access control verification when the user to be verified has the target verification action;

[0040] A behavior information collection module is used to collect the current behavior information of the user to be verified in the target smart community and extract the historical behavior information of the user to be verified in the target smart community when it is determined that the user to be verified has passed the access control verification based on the target verification action;

[0041] A behavior matching determination module, used to perform behavior matching determination on the current behavior information and the historical behavior information, and output a behavior matching degree between the current behavior information and the historical behavior information;

[0042] The user security management and control module is used to perform security management and control operations on the user to be verified based on the behavior matching degree.

[0043] In some preferred embodiments, in the above-mentioned resident safety management and control system based on smart community, the behavior information collection module is specifically used for:

[0044] In the case where it is determined based on the target verification action that the user to be verified has passed the access control verification, determining a pre-configured target duration;

[0045] Based on the target duration, the current behavior of the user to be verified in the target smart community is monitored by video to collect corresponding current behavior information, where the current behavior information belongs to the monitoring video, and the duration of the monitoring video is equal to the target duration;

[0046] Based on the target duration, historical behavior information of the user to be verified in the target smart community is extracted, and the historical behavior information is a monitoring video formed by video monitoring of the historical behavior of the user to be verified in the target smart community for the target duration.

[0047] In some preferred embodiments, in the above-mentioned resident safety management and control system based on smart community, the behavior matching determination module is specifically used for:

[0048] Performing a feature mining operation on the current behavior information to output a current behavior description vector corresponding to the current behavior information, and performing a feature mining operation on the historical behavior information to output a historical behavior description vector corresponding to the historical behavior information;

[0049] Based on the current behavior description vector and the historical behavior description vector, a behavior matching degree between the current behavior information and the historical behavior information is analyzed.

[0050] A resident security management and control method and system based on a smart community provided by an embodiment of the present invention can perform access control verification operations on the user to be verified based on the target verification action determined by the verification action determination operation for the user to be verified, and pass the access control verification when the user to be verified has the target verification action; when it is determined based on the target verification action that the user to be verified has passed the access control verification, the current behavior information of the user to be verified in the target smart community is collected, and the historical behavior information of the user to be verified in the target smart community is extracted; the current behavior information and the historical behavior information are determined to match the behavior, and the behavior matching degree between the current behavior information and the historical behavior information is output; and security management operations are performed on the user to be verified based on the behavior matching degree. Based on the foregoing, security management operations can be further performed after the access control verification, so that the reliability of resident security management can be improved, thereby improving the deficiencies in the prior art.

[0051] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A structural block diagram of a resident safety management and control platform based on a smart community provided in an embodiment of the present invention.

[0053] Figure 2 A flowchart of the steps included in the method for resident safety management and control based on a smart community provided in an embodiment of the present invention.

[0054] Figure 3 A schematic diagram of the modules included in the smart community-based resident safety management and control system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0056] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] like Figure 1 As shown, an embodiment of the present invention provides a resident safety management and control platform based on a smart community, wherein the resident safety management and control platform based on a smart community may include a memory and a processor, as well as other possible devices or components.

[0058] In detail, the memory and the processor are electrically connected directly or indirectly to realize data transmission or interaction. For example, they can be electrically connected to each other through one or more communication buses or signal lines. The memory may store at least one software function module (computer program) that can exist in the form of software or firmware. The processor can be used to execute the executable computer program stored in the memory, so as to realize the resident safety management method based on the smart community provided by the embodiment of the present invention (as described later).

[0059] Optionally, in some embodiments, the memory may be, but is not limited to, random access memory (RAM), read only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable read-only memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.

[0060] Optionally, in some embodiments, the processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a system on chip (SoC), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0061] Optionally, in some implementations, the smart community-based resident safety management and control platform may be a server with data processing capabilities.

[0062] Combination Figure 2 The embodiment of the present invention also provides a resident safety management method based on a smart community, which can be applied to the above-mentioned resident safety management platform based on a smart community. Among them, the method steps defined in the process related to the resident safety management method based on a smart community can be implemented by the resident safety management platform based on a smart community.

[0063] The following will Figure 2 The specific process shown is explained in detail.

[0064] Step S100: Based on a target verification action determined by performing a verification action determination operation on the user to be verified, a door access control verification operation is performed on the user to be verified.

[0065] In an embodiment of the present invention, the resident safety management and control platform based on the smart community can perform an access control verification operation on the user to be verified based on the target verification action determined by the verification action determination operation for the user to be verified. The access control verification operation includes prompting the user to be verified based on the target verification action, and passing the access control verification when the user to be verified has the target verification action.

[0066] Step S200, when it is determined based on the target verification action that the user to be verified has passed the access control verification, the current behavior information of the user to be verified in the target smart community is collected, and the historical behavior information of the user to be verified in the target smart community is extracted.

[0067] In an embodiment of the present invention, the resident security management and control platform based on the smart community can collect the current behavior information of the user to be verified in the target smart community and extract the historical behavior information of the user to be verified in the target smart community when it is determined that the user to be verified has passed the access control verification based on the target verification action.

[0068] Step S300 , performing behavior matching determination on the current behavior information and the historical behavior information, and outputting the behavior matching degree between the current behavior information and the historical behavior information.

[0069] In an embodiment of the present invention, the resident safety management and control platform based on the smart community can determine the behavior matching between the current behavior information and the historical behavior information, and output the behavior matching degree between the current behavior information and the historical behavior information.

[0070] Step S400: performing security control operations on the user to be verified based on the behavior matching degree.

[0071] In an embodiment of the present invention, the smart community-based resident security management and control platform can perform security management and control operations on the user to be verified based on the behavior matching degree.

[0072] Based on the foregoing, after the access control verification, further security control operations can be performed, so that the reliability of resident security control can be improved, thereby improving the deficiencies in the prior art.

[0073] Optionally, in some embodiments, the step of performing a access control verification operation on the user to be verified based on the target verification action determined by the verification action determination operation for the user to be verified may further include the following detailed contents, such as step S110, step S120, step S130 and step S140.

[0074] Step S110: determining a user description vector corresponding to the user to be verified.

[0075] In an embodiment of the present invention, the resident safety management and control platform based on the smart community can determine the description vector of the user to be verified corresponding to the user to be verified. The description vector of the user to be verified is formed based on the conversion data corresponding to the multidimensional data to be processed, and the multidimensional data to be processed is formed based on the fusion of the user description vector corresponding to each of the at least one related user and the historical action description vector corresponding to each of the at least one historical user action, at least one of the related users belongs to the community user related to the user to be verified, and at least one of the historical user actions belongs to each of the actions that have occurred in the history of the related users (which may be actions that occurred in the target smart community).

[0076] Step S120: determining a candidate user action description vector corresponding to the candidate user action.

[0077] In an embodiment of the present invention, the smart community-based resident safety management and control platform can determine a candidate user action description vector corresponding to a candidate user action. The candidate user action belongs to a historical user action that has occurred in the history of the relevant user.

[0078] Step S130 , performing a verification action determination operation on the user to be verified according to a combined description vector of the user description vector to be verified and the action description vector of the candidate user.

[0079] In an embodiment of the present invention, the smart community-based resident safety management and control platform can determine the verification action operation of the user to be verified based on the combined description vector of the user description vector to be verified and the candidate user action description vector (that is, the user description vector to be verified and the candidate user action description vector are combined or merged to form a combined description vector).

[0080] Step S140: Based on the target verification action determined by the verification action determination operation, a door access control verification operation is performed on the user to be verified.

[0081] In an embodiment of the present invention, the resident safety management and control platform based on the smart community can perform an access control verification operation on the user to be verified based on the target verification action determined by the verification action determination operation. The access control verification operation includes prompting the user to be verified based on the target verification action, and passing the access control verification when the user to be verified has the target verification action, such as allowing entry. In this way, when the user to be verified does not have the target verification action, the access control verification may not be passed, such as not being allowed to enter.

[0082] Based on the foregoing content, namely the above-mentioned steps S110, S120, S130 and S140, the target verification actions that can be formed are more diverse. Thus, compared with the conventional technical solution of performing the same action verification on all users, it can have higher verification reliability, that is, it can improve the reliability of access control verification, thereby improving the deficiencies in the prior art.

[0083] Optionally, in some implementations, the step of determining the to-be-verified user description vector corresponding to the to-be-verified user may further include the following details:

[0084] Determine the multidimensional data to be processed corresponding to the user to be verified (such as fusing the user description vector corresponding to each of the at least one related user and the historical action description vector corresponding to each of the at least one historical user action, wherein the user description vector is formed by performing feature mining based on the user information of the related user, and the historical action description vector is formed by performing feature mining based on the action information of the historical user action, which may be specifically realized by a corresponding neural network);

[0085] Determine a data difference between the multidimensional data to be processed and the reference multidimensional data (exemplarily, a difference operation may be performed on the multidimensional data to be processed and the reference multidimensional data), the reference multidimensional data is formed by performing data fusion processing based on a plurality of user multidimensional data (such as obtaining by performing mean calculation), the plurality of user multidimensional data including the multidimensional data to be processed;

[0086] According to a plurality of reference conversion rules, the data difference is subjected to data conversion processing to form a plurality of corresponding intermediate conversion description vectors (for the plurality of reference conversion rules, the data difference can be converted into or projected into a plurality of feature spaces, such as by performing nonlinear projection, so that a plurality of intermediate conversion description vectors corresponding to the plurality of feature spaces can be obtained);

[0087] Based on the first conversion data corresponding to the multiple intermediate conversion description vectors, the user description vector to be verified is determined, the first conversion data is formed based on vector integration processing (such as superposition or splicing, etc.) of the multiple intermediate conversion description vectors, and the conversion data corresponding to the multidimensional data to be processed includes at least the first conversion data (that is, the first conversion data can be directly used as the user description vector to be verified, or other data can be further integrated on the basis of the first conversion data to obtain the user description vector to be verified).

[0088] Optionally, in some implementations, the step of determining the multidimensional data to be processed corresponding to the user to be verified may further include the following details:

[0089] Determine a correlation characterization parameter between the user to be verified and the related user, wherein the correlation characterization parameter is used to reflect the degree of correlation between the user to be verified and the related user (the correlation characterization parameter may be predetermined, such as determined by the similarity or overlap between the actions corresponding to the user to be verified and the related user. For example, the user to be verified has actions 1, 2, 3, 4, 5, 6, 7, 8, 9 and 10, and the related user has actions 1, 5, 7, 10, 11, 12, 13, 14, 15 and 16. Thus, the same actions between the user to be verified and the related user include actions 1, 5, 7 and 10, and the number of the same actions may account for 40%).

[0090] Determining an action dependency characterization parameter between the relevant user and the historical user action, wherein the action dependency characterization parameter is used to reflect the degree of user action correlation between the relevant user and the historical user action (e.g., the action dependency characterization parameter is determined based on the occurrence frequency or occurrence proportion of the historical user action in each action of the relevant user);

[0091] Determine a first combined description vector corresponding to the correlation characterization parameter and the user description vector (for example, the correlation characterization parameter and the user description vector may be multiplied to obtain the first combined description vector), and determine a second combined description vector corresponding to the action dependency characterization parameter and the historical action description vector (for example, the action dependency characterization parameter and the historical action description vector may be multiplied to obtain the second combined description vector);

[0092] A fusion operation is performed (exemplarily, superposition processing can be performed) on at least one of the first combined description vectors corresponding to at least one of the relevant users and at least one of the second combined description vectors corresponding to at least one historical user action that has occurred in the history of each of the relevant users to form multi-dimensional data to be processed corresponding to the user to be verified.

[0093] Optionally, in some implementations, before the step of determining the to-be-verified user description vector corresponding to the to-be-verified user, the resident safety management and control method based on the smart community may further include the following details:

[0094] Determine the occurrence label data of the user to be verified relative to the candidate user action set, wherein the candidate user action set includes at least one historical user action that each of the relevant users has historically appeared; based on this, the step of determining the user description vector to be verified corresponding to the user to be verified may include the following details:

[0095] When the occurrence label data reflects that the candidate user action set includes at least one historical user action corresponding to the user to be verified, determining the single-dimensional data to be processed corresponding to the user to be verified, wherein the single-dimensional data to be processed is formed based on the fusion of the historical action description vector corresponding to the at least one historical user action;

[0096] A data fusion operation (such as superposition processing, etc.) is performed on the second conversion data corresponding to the single-dimensional data to be processed (the second conversion data may be the result of the nonlinear feature space projection of the single-dimensional data to be processed) and the first conversion data corresponding to the multidimensional data to be processed (the first conversion data may be the result of the nonlinear feature space projection of the multidimensional data to be processed) to form a user description vector corresponding to the user to be verified.

[0097] Optionally, in some implementations, the step of performing a data fusion operation on the second converted data corresponding to the single-dimensional data to be processed and the first converted data corresponding to the multi-dimensional data to be processed to form the user description vector to be verified corresponding to the user to be verified may further include the following details:

[0098] Performing data merging processing on the second converted data corresponding to the single-dimensional data to be processed and the first converted data corresponding to the multidimensional data to be processed to form corresponding candidate merged converted data, wherein the data merging processing at least includes performing a sum operation on the second converted data corresponding to the single-dimensional data to be processed and the first converted data corresponding to the multidimensional data to be processed;

[0099] Determine a first influence parameter that is negatively correlated with the candidate merged conversion data and positively correlated with the first conversion data, and determine a second influence parameter corresponding to the first influence parameter, wherein the second influence parameter is negatively correlated with the first influence parameter;

[0100] A vector fusion operation is performed on the combined description vector of the first influence parameter and the second conversion data, and the combined description vector of the second influence parameter and the first conversion data to form the description vector of the user to be verified corresponding to the user to be verified. The vector fusion operation at least includes summing the combined description vector of the first influence parameter and the second conversion data, and the combined description vector of the second influence parameter and the first conversion data, wherein the first influence parameter is multiplied by the second conversion data to form a corresponding combined description vector, and the second influence parameter is multiplied by the first conversion data to form a corresponding combined description vector.

[0101] Optionally, in some implementations, the step of determining the to-be-verified user description vector corresponding to the to-be-verified user may further include the following details:

[0102] When the appearance label data reflects that there is no inclusion relationship between the historical user set and the user to be verified, the second converted data corresponding to the multidimensional data to be processed is marked to be marked as the user description vector to be verified corresponding to the user to be verified, and the historical user set is a set of users who have performed the historical user actions in the candidate user action set.

[0103] Alternatively, in some implementations, the step of performing a verification action determination operation on the user to be verified based on a combined description vector of the user description vector to be verified and the action description vector of the candidate user may further include the following details:

[0104] According to the combined description vector of the to-be-verified user description vector and the candidate user action description vector, analyzing the matching possibility evaluation parameter of the to-be-verified user relative to the candidate user action (exemplarily, the combined description vector may be first fully connected to obtain a corresponding fully connected vector, and then the fully connected vector may be outputted by excitation mapping, such as by processing through a softmax function to obtain a matching possibility evaluation parameter, and the matching possibility evaluation parameter is used to reflect the matching degree between the candidate user action and the to-be-verified user);

[0105] In the case where the candidate user action set includes at least two candidate user actions, sorting the at least two candidate user actions (e.g., from large to small or from small to large, etc.) according to the at least two matching possibility evaluation parameters of the at least two candidate user actions by the to-be-verified user, so as to form a corresponding ordered set of candidate user actions;

[0106] In the ordered set of candidate user actions, at least one candidate user action is determined as the corresponding target verification action. For example, a candidate user action with the largest matching possibility evaluation parameter can be determined as the corresponding target verification action.

[0107] Among them, it can be selected that, in some implementations, the to-be-verified user description vector and the candidate user action description vector can be determined based on a target relationship graph, and the determination process of the target relationship graph can further include the following detailed contents:

[0108] Determine a corresponding user correlation graph based on user appearance record data between at least two candidate cell users (for example, the number of times two candidate cell users co-appear may be positively correlated with the correlation between the two candidate cell users in the user correlation graph), wherein the at least two candidate cell users include the user to be verified and at least one of the related users;

[0109] Based on the occurrence of at least one original historical user action by at least one user in the cell to be analyzed, a corresponding user action correlation graph is determined (so that, in the user action correlation graph, graph members may include the user in the cell to be analyzed and the original historical user actions), and at least one original historical user action includes at least one historical user action that has appeared in history for each of the related users;

[0110] According to the same cell users between at least two of the candidate cell users and at least one of the to-be-analyzed cell users, the user correlation relationship map and the user action correlation relationship map are merged to form an intermediate relationship map;

[0111] According to the conversion data corresponding to the multidimensional data of each user member in the intermediate relationship graph, the user members in the intermediate relationship graph are optimized. In the intermediate relationship graph, the member attribute data of the user members are corresponding user description vectors. The user members in the intermediate relationship graph are optimized by optimizing the user description vectors corresponding to the user members in the intermediate relationship graph (for the specific process, reference may be made to the step of determining the user description vector to be verified corresponding to the user to be verified);

[0112] The optimized intermediate relationship map is marked as the target relationship map.

[0113] Optionally, in some implementations, when it is determined based on the target verification action that the user to be verified has passed the access control verification, the step of collecting the current behavior information of the user to be verified in the target smart community and extracting the historical behavior information of the user to be verified in the target smart community may further include the following details:

[0114] When it is determined based on the target verification action that the user to be verified has passed the access control verification, a pre-configured target duration is determined, and the specific value of the target duration is not limited and can be selected according to actual needs, such as 2 minutes, 3 minutes, etc.;

[0115] Based on the target duration, the current behavior of the user to be verified in the target smart community is monitored by video to collect corresponding current behavior information, where the current behavior information belongs to the monitoring video, and the duration of the monitoring video is equal to the target duration;

[0116] Based on the target duration, historical behavior information of the user to be verified in the target smart community is extracted, and the historical behavior information is a monitoring video formed by video monitoring of the historical behavior of the user to be verified in the target smart community for the target duration.

[0117] Optionally, in some implementations, the step of performing video monitoring on the current behavior of the user to be verified in the target smart community based on the target duration to collect the corresponding current behavior information may further include the following details:

[0118] Based on the target duration, the current behavior of the user to be verified in the target area in the target smart community is monitored by video to collect the corresponding current behavior information.

[0119] Optionally, in some implementations, the step of extracting the historical behavior information of the user to be verified in the target smart community based on the target duration may further include the following details:

[0120] Based on the target duration, historical behavior information of the user to be verified belonging to the target area in the target smart community is extracted, that is, the historical behavior information and the current behavior information may be behaviors in the same area.

[0121] Optionally, in some implementations, the step of determining a behavior match between the current behavior information and the historical behavior information and outputting a behavior match degree between the current behavior information and the historical behavior information may further include the following details:

[0122] Performing a feature mining operation on the current behavior information to output a current behavior description vector corresponding to the current behavior information, and performing a feature mining operation on the historical behavior information to output a historical behavior description vector corresponding to the historical behavior information, wherein the feature mining operation may be implemented based on a corresponding neural network, such as some encoding neural networks;

[0123] Based on the current behavior description vector and the historical behavior description vector, a behavior matching degree between the current behavior information and the historical behavior information is analyzed.

[0124] Optionally, in some implementations, the step of analyzing the behavior matching degree between the current behavior information and the historical behavior information based on the current behavior description vector and the historical behavior description vector may further include the following details:

[0125] Calculating cosine similarity between the current behavior description vector and the historical behavior description vector to output a corresponding first cosine similarity;

[0126] Performing a row-column swap operation on the vector parameters of the current behavior description vector to output a swapped current behavior description vector corresponding to the current behavior description vector, multiplying the swapped current behavior description vector and the historical behavior description vector to output a corresponding first intermediate description vector, and, based on the first intermediate description vector and the current behavior description vector, analyzing the associated historical behavior description vector corresponding to the historical behavior description vector (for example, the first intermediate description vector may be divided by the vector dimension of the historical behavior description vector, and then the result may be activated, and then the activation result may be multiplied by the current behavior description vector) to achieve association mining of the historical behavior description vector based on the current behavior description vector;

[0127] Performing a row-column swap operation on the vector parameters of the historical behavior description vector to output a swapped historical behavior description vector corresponding to the historical behavior description vector, multiplying the swapped historical behavior description vector and the current behavior description vector to output a corresponding second intermediate description vector, and, based on the second intermediate description vector and the historical behavior description vector, analyzing an associated current behavior description vector corresponding to the current behavior description vector to implement association mining of the current behavior description vector based on the historical behavior description vector;

[0128] Calculating cosine similarity of the historical behavior description vector and the associated historical behavior description vector to output a corresponding second cosine similarity;

[0129] Calculating cosine similarity between the current behavior description vector and the associated current behavior description vector to output a corresponding third cosine similarity;

[0130] Based on the first cosine similarity, the second cosine similarity and the third cosine similarity, a behavior matching degree between the current behavior information and the historical behavior information is determined. Exemplarily, the first cosine similarity, the second cosine similarity and the third cosine similarity may be weightedly summed to obtain the behavior matching degree.

[0131] Optionally, in some implementations, the step of performing security control operations on the to-be-verified user based on the behavior matching degree further includes the following details:

[0132] Extracting a pre-configured reference behavior matching degree, and performing a size comparison process on the behavior matching degree and the reference behavior matching degree to obtain a corresponding size comparison result. The specific value of the reference behavior matching degree is not limited and can be configured according to actual needs;

[0133] If the size comparison result reflects that the behavior matching degree is greater than or equal to the reference behavior matching degree, determining not to perform a user monitoring operation on the user to be verified;

[0134] When the size comparison result reflects that the behavior matching degree is less than the reference behavior matching degree, it is determined to perform a user monitoring operation on the user to be verified, and the user monitoring operation at least includes continuous (constant) video monitoring of the user to be verified to achieve security management and control.

[0135] Combination Figure 3 The embodiment of the present invention further provides a resident safety management system based on a smart community, which can be applied to the above-mentioned resident safety management platform based on a smart community. The resident safety management system based on a smart community can include the following software function modules:

[0136] An access control verification module, configured to perform an access control verification operation on the user to be verified based on a target verification action determined by performing a verification action determination operation on the user to be verified, wherein the access control verification operation includes prompting the user to be verified with an action based on the target verification action, and passing the access control verification when the user to be verified has the target verification action;

[0137] A behavior information collection module is used to collect the current behavior information of the user to be verified in the target smart community and extract the historical behavior information of the user to be verified in the target smart community when it is determined that the user to be verified has passed the access control verification based on the target verification action;

[0138] A behavior matching determination module, used to perform behavior matching determination on the current behavior information and the historical behavior information, and output a behavior matching degree between the current behavior information and the historical behavior information;

[0139] The user security management and control module is used to perform security management and control operations on the user to be verified based on the behavior matching degree.

[0140] Optionally, in some implementations, the behavior information collection module is specifically used to:

[0141] In the case where it is determined based on the target verification action that the user to be verified has passed the access control verification, determining a pre-configured target duration;

[0142] Based on the target duration, the current behavior of the user to be verified in the target smart community is monitored by video to collect corresponding current behavior information, where the current behavior information belongs to the monitoring video, and the duration of the monitoring video is equal to the target duration;

[0143] Based on the target duration, historical behavior information of the user to be verified in the target smart community is extracted, and the historical behavior information is a monitoring video formed by video monitoring of the historical behavior of the user to be verified in the target smart community for the target duration.

[0144] Optionally, in some implementations, the behavior matching determination module is specifically used to:

[0145] Performing a feature mining operation on the current behavior information to output a current behavior description vector corresponding to the current behavior information, and performing a feature mining operation on the historical behavior information to output a historical behavior description vector corresponding to the historical behavior information;

[0146] Based on the current behavior description vector and the historical behavior description vector, a behavior matching degree between the current behavior information and the historical behavior information is analyzed.

[0147] In summary, the present invention provides a resident security management and control method and system based on a smart community, which can perform access control verification operations on the user to be verified based on the target verification action determined by the verification action determination operation for the user to be verified, and pass the access control verification when the user to be verified has the target verification action; when it is determined based on the target verification action that the user to be verified has passed the access control verification, the current behavior information of the user to be verified in the target smart community is collected, and the historical behavior information of the user to be verified in the target smart community is extracted; the current behavior information and the historical behavior information are determined to match the behavior, and the behavior matching degree between the current behavior information and the historical behavior information is output; and security management operations are performed on the user to be verified based on the behavior matching degree. Based on the foregoing, security management operations can be further performed after the access control verification, so that the reliability of resident security management can be improved, thereby improving the deficiencies in the prior art.

[0148] In several embodiments provided in the embodiments of the present invention, it should be understood that the disclosed devices and methods may also be implemented in other ways. The device and method embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the devices, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a portion of a code, and the module, program segment, or a portion of a code includes one or more executable instructions for implementing a specified logical function.

[0149] It should also be noted that in some alternative implementations, the functions marked in the blocks may also occur in a different order than that marked in the accompanying drawings. For example, two consecutive 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 diagram and / or flow chart, and the combination of blocks in the block diagram and / or flow chart, may be implemented with a dedicated hardware-based system that performs the specified functions or actions, or may be implemented with a combination of dedicated hardware and computer instructions.

[0150] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for resident safety management based on smart community. It is characterized in that include: Based on the target verification action determined by the verification action determination operation for the user to be verified, a door access control verification operation is performed on the user to be verified, wherein the door access control verification operation includes prompting the user to be verified based on the target verification action, and passing the door access control verification when the user to be verified has the target verification action; When it is determined based on the target verification action that the user to be verified has passed the access control verification, current behavior information of the user to be verified in the target smart community is collected, and historical behavior information of the user to be verified in the target smart community is extracted; Performing behavior matching determination on the current behavior information and the historical behavior information, and outputting a behavior matching degree between the current behavior information and the historical behavior information; Performing security control operations on the user to be verified based on the behavior matching degree; The step of determining a behavior match between the current behavior information and the historical behavior information and outputting a behavior match degree between the current behavior information and the historical behavior information includes: Performing a feature mining operation on the current behavior information to output a current behavior description vector corresponding to the current behavior information, and performing a feature mining operation on the historical behavior information to output a historical behavior description vector corresponding to the historical behavior information; Based on the current behavior description vector and the historical behavior description vector, a behavior matching degree between the current behavior information and the historical behavior information is analyzed.

2. The method for controlling household safety in a smart community according to claim 1, It is characterized in that The step of collecting the current behavior information of the user to be verified in the target smart community and extracting the historical behavior information of the user to be verified in the target smart community when it is determined based on the target verification action that the user to be verified has passed the access control verification comprises: In the case where it is determined based on the target verification action that the user to be verified has passed the access control verification, determining a pre-configured target duration; Based on the target duration, the current behavior of the user to be verified in the target smart community is monitored by video to collect corresponding current behavior information, where the current behavior information belongs to the monitoring video, and the duration of the monitoring video is equal to the target duration; Based on the target duration, historical behavior information of the user to be verified in the target smart community is extracted, and the historical behavior information is a monitoring video formed by video monitoring of the historical behavior of the user to be verified in the target smart community for the target duration.

3. The method for controlling household safety in a smart community according to claim 2, It is characterized in that The step of performing video monitoring on the current behavior of the user to be verified in the target smart community based on the target duration to collect corresponding current behavior information includes: Based on the target duration, the current behavior of the user to be verified in the target area in the target smart community is monitored by video to collect the corresponding current behavior information; The step of extracting the historical behavior information of the user to be verified in the target smart community based on the target duration includes: Based on the target duration, historical behavior information of the user to be verified belonging to the target area in the target smart community is extracted.

4. The method for controlling household safety in a smart community according to claim 1, It is characterized in that The step of analyzing the behavior matching degree between the current behavior information and the historical behavior information based on the current behavior description vector and the historical behavior description vector includes: Calculating cosine similarity between the current behavior description vector and the historical behavior description vector to output a corresponding first cosine similarity; Performing a row-column swap operation on vector parameters of the current behavior description vector to output a swapped current behavior description vector corresponding to the current behavior description vector, multiplying the swapped current behavior description vector and the historical behavior description vector to output a corresponding first intermediate description vector, and, based on the first intermediate description vector and the current behavior description vector, analyzing an associated historical behavior description vector corresponding to the historical behavior description vector to implement association mining of the historical behavior description vector based on the current behavior description vector; Performing a row-column swap operation on the vector parameters of the historical behavior description vector to output a swapped historical behavior description vector corresponding to the historical behavior description vector, multiplying the swapped historical behavior description vector and the current behavior description vector to output a corresponding second intermediate description vector, and, based on the second intermediate description vector and the historical behavior description vector, analyzing an associated current behavior description vector corresponding to the current behavior description vector to implement association mining of the current behavior description vector based on the historical behavior description vector; Calculating cosine similarity of the historical behavior description vector and the associated historical behavior description vector to output a corresponding second cosine similarity; Calculating cosine similarity between the current behavior description vector and the associated current behavior description vector to output a corresponding third cosine similarity; Based on the first cosine similarity, the second cosine similarity, and the third cosine similarity, a behavior matching degree between the current behavior information and the historical behavior information is determined.

5. The method for controlling household safety in a smart community according to claim 1, It is characterized in that The step of performing security control operations on the user to be verified based on the behavior matching degree includes: Extracting a pre-configured reference behavior matching degree, and performing a size comparison process on the behavior matching degree and the reference behavior matching degree to obtain a corresponding size comparison result; If the size comparison result reflects that the behavior matching degree is greater than or equal to the reference behavior matching degree, determining not to perform a user monitoring operation on the user to be verified; When the size comparison result reflects that the behavior matching degree is less than the reference behavior matching degree, it is determined to perform a user monitoring operation on the user to be verified, and the user monitoring operation at least includes continuous video monitoring of the user to be verified to achieve security management and control.

6. The method for resident safety management based on a smart community according to any one of claims 1 to 5, It is characterized in that The step of performing a door access control verification operation on the user to be verified based on the target verification action determined by the verification action determination operation for the user to be verified includes: Determine a user description vector to be verified corresponding to the user to be verified, wherein the user description vector to be verified is formed based on conversion data corresponding to the multidimensional data to be processed, wherein the multidimensional data to be processed is formed based on a fusion of a user description vector corresponding to each of at least one related user and a historical action description vector corresponding to each of at least one historical user action, wherein at least one of the related users belongs to a cell user related to the user to be verified, and at least one of the historical user actions belongs to an action that has occurred in history for each of the related users; Determine a candidate user action description vector corresponding to a candidate user action, where the candidate user action belongs to a historical user action that has occurred in the history of the relevant user; Performing a verification action determination operation on the user to be verified according to a combined description vector of the user description vector to be verified and the action description vector of the candidate user; Based on the target verification action determined by the verification action determination operation, a door access control verification operation is performed on the user to be verified. The door access control verification operation includes giving an action prompt to the user to be verified based on the target verification action, and passing the door access control verification when the user to be verified has the target verification action.

7. A resident safety management and control system based on smart community, It is characterized in that include: An access control verification module, configured to perform an access control verification operation on the user to be verified based on a target verification action determined by performing a verification action determination operation on the user to be verified, wherein the access control verification operation includes prompting the user to be verified with an action based on the target verification action, and passing the access control verification when the user to be verified has the target verification action; A behavior information collection module is used to collect the current behavior information of the user to be verified in the target smart community and extract the historical behavior information of the user to be verified in the target smart community when it is determined that the user to be verified has passed the access control verification based on the target verification action; A behavior matching determination module, used to perform behavior matching determination on the current behavior information and the historical behavior information, and output a behavior matching degree between the current behavior information and the historical behavior information; A user security control module, used to perform security control operations on the user to be verified based on the behavior matching degree; The behavior matching determination module is specifically used for: Performing a feature mining operation on the current behavior information to output a current behavior description vector corresponding to the current behavior information, and performing a feature mining operation on the historical behavior information to output a historical behavior description vector corresponding to the historical behavior information; Based on the current behavior description vector and the historical behavior description vector, a behavior matching degree between the current behavior information and the historical behavior information is analyzed.

8. The resident safety management and control system based on the smart community as claimed in claim 7, It is characterized in that The behavior information collection module is specifically used for: In the case where it is determined based on the target verification action that the user to be verified has passed the access control verification, determining a pre-configured target duration; Based on the target duration, the current behavior of the user to be verified in the target smart community is monitored by video to collect corresponding current behavior information, where the current behavior information belongs to the monitoring video, and the duration of the monitoring video is equal to the target duration; Based on the target duration, historical behavior information of the user to be verified in the target smart community is extracted, and the historical behavior information is a monitoring video formed by video monitoring of the historical behavior of the user to be verified in the target smart community for the target duration.

Citation Information

Cited By

  • Intelligent monitoring system based on FPGA technology

    CN119854453A

  • An intelligent monitoring system based on FPGA technology

    CN119854453B