Management Method, Device and Computer Readable Storage Medium of Apartment

Abstract

The present invention discloses a management method, device and computer-readable storage medium for an apartment. The method includes: acquiring videos of a preset area; acquiring gait features, clothing features and body type features of a target person in the videos, and acquiring registered person features associated with the preset area; comparing the gait features, clothing features and body type features with the registered person features to determine whether the target person is associated with the preset area; and if the target person is not associated with the preset area, outputting a prompt message indicating that an abnormal person appears in the preset area. The present invention improves the security of apartment management.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a management method, device, and computer-readable storage medium for an apartment. Background Art

[0002] Currently, with the continuous development of the Internet, people's lives are closely integrated with the Internet. Traditional apartment management systems have also installed visual acquisition devices to monitor various areas of the apartment. Existing technical means perform face recognition on the image information collected from different areas of the apartment to identify whether there are abnormal personnel in each area of the apartment. However, since it is difficult to collect facial features, there are still security risks in this recognition method. Summary of the Invention

[0003] Embodiments of the present invention provide a management method, device, and computer-readable storage medium for an apartment, aiming to solve the technical problem of how to improve the security of apartment management.

[0004] Embodiments of the present invention provide a management method for an apartment, and the management method for the apartment includes the following steps:

[0005] The management method for the apartment includes the following steps:

[0006] Obtain videos of a preset area;

[0007] Obtain the gait features, clothing features, and body type features of a target person in the video, and obtain the features of registered persons associated with the preset area;

[0008] Compare the gait features, clothing features, and body type features with the features of registered persons to determine whether the target person is associated with the preset area;

[0009] If the target person is not associated with the preset area, output a prompt message indicating that there is an abnormal person in the preset area.

[0010] In an embodiment, after the step of outputting a prompt message indicating that there is an abnormal person in the preset area if the target person is not associated with the preset area, the method further includes;

[0011] Obtain the features of abnormal persons associated with the preset area;

[0012] Compare the gait features, clothing features, and body type features with the features of registered persons to determine whether the target person is an abnormal person in the preset area;

[0013] If the target person is the abnormal person, increase the number of times the target person appears in the preset area at different time periods;

[0014] If the number of times reaches a preset value, mark the gait feature, the clothing feature, and the body shape feature as the registered person features associated with the preset area.

[0015] In one embodiment, the step of obtaining the video of the preset area includes:

[0016] Perform a live detection on the video collected from the preset area;

[0017] When it is detected that a live body appears in the preset area, execute the step of obtaining the video of the preset area.

[0018] In one embodiment, after the step of obtaining the video of the preset area, the method further includes:

[0019] Detect whether there is a face feature in the video;

[0020] If the face feature is detected, obtain the registered face features associated with the preset area;

[0021] Compare the face feature with the registered face features to determine whether the similarity between the face feature and the registered face features is greater than a preset similarity;

[0022] If the similarity between the face feature and the registered face features is less than the preset similarity, output a prompt message indicating that an abnormal person appears in the preset area;

[0023] If the face feature is not detected, execute the steps of obtaining the gait feature, the clothing feature, and the body shape feature of the target person in the video, and obtaining the registered person features associated with the preset area.

[0024] In one embodiment, the step of comparing the gait feature, the clothing feature, and the body shape feature with the registered person features to determine whether the target person is associated with the preset area includes:

[0025] Input the video into a pre-trained feature extraction neural network model for gait feature recognition, clothing feature recognition, and body shape feature recognition to obtain the feature vector corresponding to the video;

[0026] After normalizing the feature vector, calculate the Euclidean distance, compare the Euclidean distance corresponding to the video with the Euclidean distance corresponding to the registered person features, and determine whether the Euclidean distance difference is less than a preset threshold;

[0027] If the Euclidean distance difference is less than the preset threshold, determine that the target person is associated with the preset area;

[0028] If the Euclidean distance difference is greater than or equal to the preset threshold, it is determined that the target person is not associated with the preset area.

[0029] In one embodiment, the step of outputting a prompt message indicating that there is an abnormal person in the preset area when the target person is not associated with the preset area includes:

[0030] If the target person is not associated with the preset area, obtain the contact information associated with the registered person's characteristics;

[0031] Output the prompt message according to the contact information.

[0032] In one embodiment, after the step of comparing the gait characteristics, the clothing characteristics, and the body shape characteristics with the registered person's characteristics to determine whether the target person is associated with the preset area, the method further includes:

[0033] If the target person is associated with the preset area, use the target person as the registered face associated with the preset area;

[0034] Update the travel pattern of the registered person;

[0035] Output a prompt message according to the travel pattern.

[0036] In one embodiment, the step of outputting a prompt message according to the travel pattern includes:

[0037] Determine a target time period according to the travel pattern, where the target time period is the time period when the target person appears in the preset area a preset number of times;

[0038] If it is detected that the registered person does not appear in the preset area within the target time period and the number of times reaches the preset number of times, output the prompt message.

[0039] An embodiment of the present invention further provides a management device for an apartment. The management device for the apartment includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, each step of the above-mentioned management method for the apartment is implemented.

[0040] An embodiment of the present invention further provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, each step of the above-mentioned management method for the apartment is implemented.

[0041] In the technical solution of this embodiment, the management device of the apartment acquires the video of the preset area; acquires the gait characteristics, clothing characteristics, and body type characteristics of the target person in the video, and acquires the characteristics of the registered persons associated with the preset area; compares the gait characteristics, the clothing characteristics, and the body type characteristics with the characteristics of the registered persons to determine whether the target person is associated with the preset area; if the target person is not associated with the preset area, outputs a prompt message indicating that there is an abnormal person in the preset area. Due to the reasons of the apartment scene itself, there are often only fixed persons entering and leaving many areas in the apartment. If there are abnormal persons in these areas, it is very likely to affect the safety of the apartment. The conventional technical means often carry out early warning based on face recognition. Considering the difficulty of obtaining face images, when the face cannot be detected, it is easy to miss the target person. The present invention provides a method for verifying the identity of the target person in the preset area, which specifically includes identifying the gait characteristics, clothing characteristics, and body type characteristics of the video collected in the preset area, and then verifying the identity of the target person based on the above characteristics. Compared with the face recognition method, the detection ability for abnormal persons in the apartment is stronger, and the safety of apartment management can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0043] Figure 1 It is a schematic hardware structure diagram of the management device of the apartment related to the embodiment of the present invention;

[0044] Figure 2 It is a schematic flowchart of the first embodiment of the management method of the apartment of the present invention;

[0045] Figure 3 It is a schematic flowchart of the second embodiment of the management method of the apartment of the present invention;

[0046] Figure 4 It is a schematic detailed flowchart of step S10 of the third embodiment of the management method of the apartment of the present invention;

[0047] Figure 5 It is a schematic flowchart of the fourth embodiment of the management method of the apartment of the present invention;

[0048] Figure 6 It is a schematic flowchart of the fifth embodiment of the management method of the apartment of the present invention;

[0049] Figure 7Schematic flowchart of the sixth embodiment of the management method of the apartment of the present invention. Detailed implementation manners

[0050] To better understand the above technical solutions, exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0051] The main solution of the present invention is that: the management device of the apartment acquires videos of a preset area; acquires the gait characteristics, clothing characteristics, and body shape characteristics of the target person in the videos, and acquires the characteristics of the registered persons associated with the preset area; compares the gait characteristics, the clothing characteristics, and the body shape characteristics with the characteristics of the registered persons to determine whether the target person is associated with the preset area; if the target person is not associated with the preset area, outputs a prompt message indicating that an abnormal person appears in the preset area.

[0052] Due to the reasons of the apartment scenario itself, only fixed persons often enter and exit many areas in the apartment. If abnormal persons appear in these areas, it is very likely to affect the safety of the apartment. Conventional technical means often perform early warning based on face recognition. Considering the difficulty of obtaining face images, when a face cannot be detected, it is easy to miss the target person. The present invention provides a method for verifying the identity of a target person in a preset area, specifically including identifying gait characteristics, clothing characteristics, and body shape characteristics from the videos collected in the preset area, and then verifying the identity of the target person based on the above characteristics. Compared with the face recognition method, the detection ability for abnormal persons in the apartment is stronger, and the safety of apartment management can be improved.

[0053] As an implementation manner, the management device of the apartment can be as Figure 1 .

[0054] The solution of the embodiment of the present invention relates to a management device of an apartment. The management device of the apartment includes: a processor 101, such as a CPU, a memory 102, and a communication bus 103. Among them, the communication bus 103 is used to realize the connection and communication between these components.

[0055] The memory 102 can be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. As Figure 1, the memory 103, as a computer-readable storage medium, may include a detection program; and the processor 101 may be configured to call the detection program stored in the memory 102 and perform the following operations:

[0056] Obtain a video of a preset area;

[0057] Obtain the gait features, clothing features, and body shape features of a target person in the video, and obtain the registered person features associated with the preset area;

[0058] Compare the gait features, clothing features, and body shape features with the registered person features to determine whether the target person is associated with the preset area;

[0059] If the target person is not associated with the preset area, output a prompt message indicating that an abnormal person has appeared in the preset area.

[0060] In one embodiment, the processor 101 may be configured to call the detection program stored in the memory 102 and perform the following operations:

[0061] Obtain the abnormal person features associated with the preset area;

[0062] Compare the gait features, clothing features, and body shape features with the registered person features to determine whether the target person is an abnormal person in the preset area;

[0063] If the target person is the abnormal person, increase the number of times the target person appears in the preset area at different time periods;

[0064] If the number reaches a preset value, mark the gait features, clothing features, and body shape features as the registered person features associated with the preset area.

[0065] In one embodiment, the processor 101 may be configured to call the detection program stored in the memory 102 and perform the following operations:

[0066] Perform a live detection on the video collected from the preset area;

[0067] When it is detected that a live body appears in the preset area, execute the step of obtaining the video of the preset area.

[0068] In one embodiment, the processor 101 may be configured to call the detection program stored in the memory 102 and perform the following operations:

[0069] Detect whether there are face features in the video;

[0070] If the face features are detected, obtain the registered face features associated with the preset area;

[0071] Compare the face features with the registered face features to determine whether the similarity between the face features and the registered face features is greater than a preset similarity;

[0072] If the similarity between the face features and the registered face features is less than the preset similarity, output a prompt message indicating that there is an abnormal person in the preset area;

[0073] If the face features are not detected, perform the steps of obtaining the gait features, clothing features, and body shape features of the target person in the video, and obtaining the features of the registered persons associated with the preset area.

[0074] In one embodiment, the processor 101 can be used to call the detection program stored in the memory 102 and perform the following operations:

[0075] Input the video into a pre-trained feature extraction neural network model for gait feature recognition, clothing feature recognition, and body shape feature recognition to obtain the feature vector corresponding to the video;

[0076] After normalizing the feature vector, calculate the Euclidean distance, compare the Euclidean distance corresponding to the video with the Euclidean distance corresponding to the registered person's features, and determine whether the Euclidean distance difference is less than a preset threshold value;

[0077] If the Euclidean distance difference is less than the preset threshold, determine that the target person is associated with the preset area;

[0078] If the Euclidean distance difference is greater than or equal to the preset threshold, determine that the target person is not associated with the preset area.

[0079] In one embodiment, the processor 101 can be used to call the detection program stored in the memory 102 and perform the following operations:

[0080] If the target person is not associated with the preset area, obtain the contact information associated with the registered person's features;

[0081] Output the prompt message according to the contact information.

[0082] In one embodiment, the processor 101 can be used to call the detection program stored in the memory 102 and perform the following operations:

[0083] If the target person is associated with the preset area, regard the target person as the registered face associated with the preset area;

[0084] Update the travel pattern of the registered person;

[0085] Output a prompt message according to the travel pattern.

[0086] In one embodiment, the processor 101 may be used to call the detection program stored in the memory 102 and perform the following operations:

[0087] Determine a target time period according to the travel pattern, where the target time period is the time period when the target person appears in the preset area a preset number of times;

[0088] If it is detected that the registered person does not appear in the preset area during the target time period and the number of times reaches the preset number, output the prompt message.

[0089] In the technical solution of this embodiment, the management device of the apartment acquires the video of the preset area; acquires the gait characteristics, clothing characteristics, and body type characteristics of the target person in the video, and acquires the characteristics of the registered person associated with the preset area; compares the gait characteristics, the clothing characteristics, and the body type characteristics with the characteristics of the registered person to determine whether the target person is associated with the preset area; if the target person is not associated with the preset area, output a prompt message indicating that there is an abnormal person in the preset area. Due to the reasons of the apartment scene itself, many areas in the apartment often only have fixed personnel entering and leaving. If abnormal personnel appear in these areas, it is very likely to affect the safety of the apartment. Conventional technical means often perform early warning based on face recognition. Considering the difficulty of obtaining face images, it is easy to miss the target person when the face cannot be detected. The present invention provides a method for verifying the identity of the target person in the preset area, which specifically includes identifying the gait characteristics, clothing characteristics, and body type characteristics of the video collected in the preset area, and then verifying the identity of the target person based on the above characteristics. Compared with the face recognition method, the detection ability for abnormal personnel in the apartment is stronger, and the safety of apartment management can be improved.

[0090] To better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0091] Refer to Figure 2 , Figure 2 This is the first embodiment of the management method of the apartment of the present invention. The method includes the following steps:

[0092] Step S10, acquire the video of the preset area.

[0093] In this embodiment, the above preset area may be the area corresponding to the entrance of each room in the apartment, or the public entrance of the whole building, and no more limitations are made here. It is easy to understand that the preset area is often an area where a certain group of people or individuals frequently enter and leave.

[0094] Step S20: Obtain the gait features, clothing features, and body type features of the target person in the video, and obtain the features of the registered persons associated with the preset area.

[0095] In this embodiment, the target person is determined based on the acquired video and is the object corresponding to the above-mentioned gait features, clothing features, and body type features. It is easy to understand that the gait features, clothing features, and body type features acquired based on the video are used to represent the target person. Optionally, the gait features, clothing features, and body type features exist in the form of image feature values. Since a video is composed of image frames, and a computer does not recognize images but only numbers. In order for the computer to "understand" images and thus have a true sense of "vision", the image feature value is a "non-image" representation or description of the image, such as numerical values, vectors, and symbols, etc. This process is feature extraction, and these "non-image" representations or descriptions extracted are features. A feature is the corresponding (essential) characteristic or property that distinguishes a certain type of object from other types of objects, or a set of these characteristics and properties. Features are data that can be extracted through measurement or processing. For an image, each image has its own features that can distinguish it from other types of images.

[0096] Step S30: Compare the gait features, clothing features, and body type features with the features of the registered persons to determine whether the target person is associated with the preset area.

[0097] In this embodiment, the features of the registered persons are the graphical features of the registered persons associated with the preset area. Among them, the features of the registered persons at least include gait features, clothing features, and body type features, and may also include face features. They are persons with clear identities. If the features detected in the video belong to the registered persons, the target person will not be defined as an abnormal person.

[0098] Optionally, input the video into a pre-trained feature extraction neural network model for gait feature recognition, clothing feature recognition, and body type feature recognition to obtain the feature vector corresponding to the video; perform normalization processing on the feature vector and then calculate the Euclidean distance, compare the Euclidean distance corresponding to the video with the Euclidean distance corresponding to the features of the registered persons, and determine whether the Euclidean distance difference is less than a preset threshold value; if the Euclidean distance difference is less than the preset threshold value, determine that the target person is associated with the preset area; if the Euclidean distance difference is greater than or equal to the preset threshold value, determine that the target person is not associated with the preset area.

[0099] Step S40: If the target person is not associated with the preset area, output a prompt message indicating that there is an abnormal person in the preset area.

[0100] In the technical solution of this embodiment, due to the reasons of the apartment scenario itself, there are often only fixed personnel entering and leaving many areas in the apartment. If there are abnormal personnel in these areas, it is very likely to affect the safety of the apartment. Conventional technical means often carry out early warning based on face recognition. Considering the difficulty of obtaining face images, when faces cannot be detected, it is easy to miss the target personnel. The present invention provides a method for verifying the identity of target personnel in a preset area, which specifically includes recognizing gait features, clothing features, and body shape features of the video collected in the preset area, and then verifying the identity of the target personnel based on the above features. Compared with the face recognition method, the detection ability for abnormal personnel in the apartment is stronger, and the safety of apartment management can be improved.

[0101] Referring to Figure 3 , Figure 3 This is the second embodiment of the management method of the apartment of the present invention. Based on the first embodiment, after step S40, it includes:

[0102] Step S50, obtaining the features of abnormal personnel associated with the preset area.

[0103] Step S60, comparing the gait features, the clothing features, and the body shape features with the features of the registered personnel to determine whether the target personnel is an abnormal personnel in the preset area.

[0104] Step S70, if the target personnel is the abnormal personnel, increase the number of times the target personnel appears in the preset area at different time periods.

[0105] Step S80, if the number reaches the preset value, mark the gait features, the clothing features, and the body shape features as the features of the registered personnel associated with the preset area.

[0106] In this embodiment, the features of abnormal personnel refer to the features of personnel who rarely appear in the preset area. The number of times different abnormal personnel appear in the preset area can be counted. If the number of appearances is greater than the preset value, it is considered that the abnormal personnel will not affect the safety of apartment management, and the features of the abnormal personnel can be incorporated into the features of the registered personnel.

[0107] In the technical solution of this embodiment, considering that some householders do not have time to register or there are accompanying householders who do not need to register, therefore, it is possible to define whether they can be determined as registered personnel based on the number of times they appear in the preset area, which improves the intelligence level of apartment management. Further, if some householders do not have time to register, after their registration, the features collected before and the features to be collected later will exist in both the abnormal personnel feature library and the registered personnel feature library at the same time. And the above method of the present application does not require an active operation to merge the feature libraries, and can automatically merge according to the number of times they appear in the preset area, reducing the difficulty of file management.

[0108] Referring to Figure 4 , Figure 4 This is the third embodiment of the management method of the apartment of the present invention. Based on any one of the first to second embodiments, step S10 includes:

[0109] Step S11, perform a live detection on the video collected in the preset area.

[0110] Step S12, when a live body is detected in the preset area, execute the step of obtaining the video of the preset area.

[0111] In the technical solution of this embodiment, considering that the computing power required for feature extraction is relatively large, if feature extraction is performed on all the collected videos, it will bring huge pressure to the apartment management device. Therefore, live detection is introduced, and feature extraction is only performed on the videos determined to have a live body, which can reduce the pressure on the apartment management device.

[0112] Referring to Figure 5 , Figure 5 This is the fourth embodiment of the management method of the apartment of the present invention. Based on any one of the first to third embodiments, after step S10, it further includes:

[0113] Step S90, detect whether there is a face feature in the video.

[0114] Step S100, if the face feature is detected, obtain the registered face features associated with the preset area.

[0115] Step S110, compare the face feature with the registered face features to determine whether the similarity between the face feature and the registered face features is greater than a preset similarity.

[0116] Step S120, if the similarity between the face feature and the registered face features is less than the preset similarity, output a prompt message indicating that an abnormal person appears in the preset area.

[0117] Step S130, if the face feature is not detected, perform the steps of obtaining the gait feature, clothing feature, and body type feature of the target person in the video, and obtaining the registered person feature associated with the preset area.

[0118] In the technical solution of this embodiment, considering that it is difficult to obtain a face image, the reason is not the extraction of face features from video images, but the intentional occlusion of the face by the target person. Therefore, before extracting the gait feature, clothing feature, and body type feature of the video in this embodiment, it can first be determined whether the face feature of the target person can be extracted. If it exists, it can be used to replace the gait feature, clothing feature, and body type feature to identify whether the target person is associated with the preset area, improving the flexibility of abnormal person recognition.

[0119] Refer to Figure 6 , Figure 6 This is the fifth embodiment of the management method of the apartment of the present invention. Based on any one of the first to fourth embodiments, step S40 includes:

[0120] Step S41, if the target person is not associated with the preset area, obtain the contact information associated with the registered person feature.

[0121] In the technical solution of this embodiment, considering that the target person may be a visitor of a registered person, therefore, this embodiment can send the information of abnormal person intrusion to the registered person so that the registered person can be informed in time, improving the user experience.

[0122] Refer to Figure 5 , Figure 5 This is the fourth embodiment of the management method of the apartment of the present invention. Based on any one of the first to third embodiments, after step S40, it further includes:

[0123] Step S140, if the target person is associated with the preset area, use the target person as the registered face associated with the preset area.

[0124] Step S150, update the travel pattern of the registered person.

[0125] Step S160, output a prompt message according to the travel pattern.

[0126] Optionally, determine a target time period according to the travel pattern. The target time period is the time period when the target person appears in the preset area up to a preset number of times; if it is detected that the registered person does not appear in the preset area within the target time period and the number of times reaches the preset number, output the prompt message.

[0127] In the technical solution of this embodiment, while identifying abnormal personnel, if the target person is not an abnormal person, the target person can be regarded as a registered person and the travel pattern of the target person can be recorded. For some single-resident households, a prompt message can be sent based on their travel pattern, enabling apartment managers to judge whether there is a possibility of an accident for the corresponding household based on their travel pattern, indirectly improving the safety of apartment management.

[0128] To achieve the above object, an embodiment of the present invention further provides a management device for an apartment. The management device for the apartment includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, each step of the above-described management method for the apartment is implemented.

[0129] To achieve the above object, an embodiment of the present invention further provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, each step of the above-described management method for the apartment is implemented.

[0130] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a network configuration product program implemented on one or more computer-usable computer-readable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0131] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more flows and / or Figure 1 blocks or multiple blocks.

[0132] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one or more flows and / orFigure 1 The functions specified in one or more boxes.

[0133] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 process or multiple processes and / or boxes Figure 1 or more boxes.

[0134] It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim listing several devices, several of these devices can be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names.

[0135] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0136] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. A management method for an apartment, characterized in that, The management method of the apartment includes the following steps: Obtain videos of a preset area; Obtain the gait characteristics, clothing characteristics, and body shape characteristics of the target person in the video, and obtain the characteristics of the registered persons associated with the preset area. The gait characteristics, clothing characteristics, and body shape characteristics exist in the form of image feature values; Compare the gait characteristics, clothing characteristics, and body shape characteristics with the characteristics of the registered persons to determine whether the target person is associated with the preset area; If the target person is not associated with the preset area, output a prompt message indicating that an abnormal person appears in the preset area; After the step of obtaining videos of the preset area, the method further includes: Detect whether there are face features in the video; If face features are detected, obtain the registered face features associated with the preset area; Compare the face features with the registered face features to determine whether the similarity between the face features and the registered face features is greater than a preset similarity; If the similarity between the face features and the registered face features is less than the preset similarity, output a prompt message indicating that an abnormal person appears in the preset area; If no face features are detected, execute the steps of obtaining the gait characteristics, clothing characteristics, and body shape characteristics of the target person in the video, and obtaining the characteristics of the registered persons associated with the preset area; The step of comparing the gait characteristics, clothing characteristics, and body shape characteristics with the characteristics of the registered persons to determine whether the target person is associated with the preset area includes: Input the video into a pre-trained feature extraction neural network model for gait feature recognition, clothing feature recognition, and body shape feature recognition to obtain the feature vector corresponding to the video; Perform normalization processing on the feature vector and then calculate the Euclidean distance. Compare the Euclidean distance corresponding to the video with the Euclidean distance corresponding to the characteristics of the registered persons to determine whether the Euclidean distance difference is less than a preset threshold; If the Euclidean distance difference is less than the preset threshold, determine that the target person is associated with the preset area; If the Euclidean distance difference is greater than or equal to the preset threshold, determine that the target person is not associated with the preset area; After the step of outputting a prompt message indicating that an abnormal person appears in the preset area if the target person is not associated with the preset area, the method further includes; Obtain the characteristics of the abnormal person associated with the preset area; Compare the gait characteristics, clothing characteristics, and body shape characteristics with the characteristics of the registered persons to determine whether the target person is an abnormal person in the preset area; If the target person is the abnormal person, increase the number of times the target person appears in the preset area at different time periods; If the number reaches a preset value, mark the gait characteristics, clothing characteristics, and body shape characteristics as the characteristics of the registered persons associated with the preset area; The step of obtaining videos of the preset area includes: Perform liveness detection on the videos collected from the preset area; When the living body traveling in the preset area is detected, execute the step of obtaining the video of the preset area; After the step of comparing the gait feature, the clothing feature and the body shape feature with the registered personnel feature to determine whether the target person is associated with the preset area, the method further includes: If the target person is associated with the preset area, use the target person as the registered face associated with the preset area; Update the travel pattern of the registered personnel; Output a prompt message according to the travel pattern; The step of outputting a prompt message according to the travel pattern includes: Determine a target time period according to the travel pattern, where the target time period is the time period when the target person appears in the preset area reaching a preset number of times; If it is detected that the registered person does not appear in the preset area within the target time period and the number of times reaches the preset number of times, output the prompt message.

2. The management method of the apartment according to claim 1, characterized in that, The step of outputting a prompt message indicating that an abnormal person appears in the preset area if the target person is not associated with the preset area includes: If the target person is not associated with the preset area, obtain the contact information associated with the registered person feature; Output the prompt message according to the contact information.

3. A management device for an apartment, characterized in that, The management device of the apartment includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the apartment management method according to claim 1 or 2 are implemented.

4. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, the steps of the apartment management method according to claim 1 or 2 are implemented.

Images