CN112991585B

CN112991585B - Access personnel management method and computer readable storage medium

Info

Publication number: CN112991585B
Application number: CN202110172154.9A
Authority: CN
Inventors: 冯旭海; 赵大鹏; 黄志涌; 易小珍; 廖任
Original assignee: Assa Abloy Guangzhou Smart Technology Co Ltd
Current assignee: Assa Abloy Guangzhou Smart Technology Co Ltd
Priority date: 2021-02-08
Filing date: 2021-02-08
Publication date: 2023-02-28
Anticipated expiration: 2041-02-08
Also published as: CN112991585A

Abstract

The invention discloses an in-out personnel management method and a computer readable storage medium, which are used for an intelligent door system comprising an intelligent door, wherein the in-out personnel management method comprises the following steps: collecting first image information outside the intelligent door; identifying first face information to be detected in the first image information, judging whether a first person to be detected corresponding to the first face information to be detected enters a door or not, and if so, adding the information of the first person to be detected to an indoor person database; collecting second image information in the intelligent door; identifying second face information to be detected in the second image information, judging whether a second person to be detected corresponding to the second face information to be detected is out of the door or not, and if so, deleting the information of the second person to be detected from the indoor person database; and receiving a personnel number confirmation instruction, and determining the personnel number in the indoor personnel database. The method can effectively identify the number of indoor personnel.

Description

Personnel entering and exiting management method and computer readable storage medium

Technical Field

The invention relates to the technical field of intelligent doors, in particular to an in-and-out personnel management method and a computer readable storage medium.

Background

The intelligent door, also known as intelligent security door or intelligent burglary-resisting door, is on traditional burglary-resisting security door's basis, with the intelligent system host computer as the carrier, realize through internet of things, it not only possesses the function of traditional burglary-resisting security door, can also realize automatic unblanking according to discernment face information or fingerprint information, broken through the simple "with the lock control door" theftproof thinking of traditional burglary-resisting door, improved the theftproof effect of intelligent door, consequently intelligent door is used by more and more users, becomes the important component part of intelligent home life.

However, the current smart door generally only can identify the identity of an unlocking person and cannot identify the number of indoor people, so that the away-from-home safety mode cannot be automatically started after a user leaves home, and the user must manually start the away-from-home button to start the away-from-home safety mode at present, but the user sometimes forgets, so that a large potential safety hazard exists.

Disclosure of Invention

The invention aims to solve the problem that the number of indoor personnel cannot be identified due to the fact that an intelligent door in the prior art is used. The invention provides a method for managing people entering and exiting, which can automatically identify the number of indoor people.

Accordingly, an embodiment of the present invention discloses an entrance and exit person management method for an intelligent door system including an intelligent door, including:

acquiring first image information outside the intelligent door;

identifying first face information to be detected in the first image information, judging whether a first person to be detected corresponding to the first face information to be detected enters a door or not, and if so, adding the information of the first person to be detected to an indoor person database;

collecting second image information in the intelligent door;

identifying second face information to be detected in the second image information, judging whether a second person to be detected corresponding to the second face information to be detected is out of the door or not, and if so, deleting the information of the second person to be detected from the indoor person database;

and receiving a personnel number confirmation command, and determining the personnel number in the indoor personnel database.

According to another embodiment of the invention, the number of people confirmation instruction comprises a door closing confirmation instruction, and the door closing confirmation instruction is generated when the second person to be detected is judged to be out of the door and the smart door is closed.

According to another specific embodiment of the invention, the intelligent door system further comprises a cloud server, wherein the cloud server is in communication connection with the intelligent home user side; after receiving the personnel number confirmation instruction and determining the personnel number in the indoor personnel database, the personnel entering and exiting management method further comprises the following steps:

judging whether the number of personnel in the indoor personnel database is zero, if so, sending an away mode starting instruction to the cloud server;

the cloud server receives the leaving mode starting instruction and transmits the leaving mode starting instruction to the intelligent home user side, so that the intelligent home user side can start the leaving mode.

According to another embodiment of the present invention, the determining whether the first person to be detected corresponding to the first face information to be detected enters the door comprises:

identifying first door frame information in the first image information and position information of a first person to be detected, and comparing the first door frame information with the position information of the first person to be detected to judge whether the first person to be detected enters the door;

judging whether a second person to be detected corresponding to the second face information to be detected goes out comprises:

and identifying second doorframe information in the second image information and the position information of a second person to be detected, and comparing the second doorframe information with the position information of the second person to be detected so as to judge whether the second person to be detected leaves.

According to another specific embodiment of the present invention, the information in the indoor personnel database includes identity information of each family and identity information of strangers;

adding the information of the first person to be detected to the indoor person database comprises:

respectively comparing the first face information to be detected with the face information of each family person in the preset face information to judge the identity information of the first person to be detected;

if the preset face information contains the face information of the family members, the similarity of which with the first face information to be detected is within the threshold range, judging the identity of the family members of the first person to be detected according to the face information of the family members, the similarity of which is within the threshold range; otherwise, the first person to be detected is the identity of a stranger;

adding identity information of a first person to be detected to an indoor person database;

deleting the information of the second person to be detected from the indoor person database comprises the following steps:

respectively comparing the second face information to be detected with the face information of each family person in the preset face information to judge the identity information of the second person to be detected;

if the preset face information contains the family personnel face information with the similarity to the second face information to be detected within the threshold range, judging the family personnel identity of the second person to be detected according to the family member face information with the similarity within the threshold range; otherwise, the second person to be detected is the identity of a stranger;

and deleting the identity information of the second person to be detected from the indoor person database.

According to another embodiment of the present invention, after determining that the first person to be detected is a stranger, before adding the identity information of the stranger to the indoor person database, the method further includes:

comparing the first face information to be detected with face information in a stranger database to determine the corresponding stranger number of the first face information, and storing the first face information to be detected in the stranger database;

and the identity information of the strangers added to the indoor personnel database is the stranger number.

According to another specific embodiment of the invention, the intelligent door system further comprises a cloud server and a user terminal which are in communication connection;

after the second person to be detected is judged to be a stranger, before the identity information of the second person to be detected is deleted from the indoor person database, the method for managing the person coming in and going out further comprises the following steps:

judging whether face information with similarity within a threshold value range with second face information to be detected of a stranger exists in a stranger database;

if the similarity exists in the threshold range, judging the stranger number corresponding to the stranger according to the face information of which the similarity is in the threshold range, and deleting the stranger number corresponding to the stranger from the indoor personnel database;

if the alarm information does not exist, the alarm information is sent to a cloud server, and the cloud server sends the alarm information to the user terminal.

According to another specific embodiment of the invention, the intelligent door system further comprises a cloud server and a user terminal which are in communication connection; the entrance and exit person management method further includes:

after the first person to be detected is judged to be a stranger, the intelligent door stores the first face information to be detected of the stranger while the identity information of the stranger is added to the indoor person database;

the cloud server receives a first calling request instruction sent by the user terminal, calls first face information to be detected of a stranger stored in the intelligent door, and transmits the first face information to be detected to the user terminal.

According to another embodiment of the present invention, the method for managing entrance and exit persons further comprises:

after the second face information to be detected is judged to be a stranger, the intelligent door stores the second face information to be detected of the stranger while identity information of the stranger is deleted from the indoor personnel database;

the cloud server receives a second calling request instruction sent by the user terminal, calls second face information to be detected of a stranger stored in the intelligent door, and transmits the second face information to be detected to the user terminal.

According to another specific embodiment of the invention, the family personnel identity comprises children, when the first person to be detected and/or the second person to be detected are judged to be children and strangers, the alarm information is sent to the cloud server, and the cloud server sends the alarm information to the user terminal for alarming.

According to another embodiment of the present invention, before the acquiring the first image information outside the smart door and/or acquiring the second image information inside the smart door, the method further comprises:

detecting the distance between the intelligent door and the surrounding objects; and if the distance is smaller than the preset distance, awakening the intelligent door to control the acquisition of the first image information and/or the second image information.

after the information of the first person to be detected is added to the indoor person database, the door entering information of the first person to be detected is recorded;

after the information of the second person to be detected is deleted from the indoor person database, the exit information of the second person to be detected is recorded;

the entrance information comprises entrance time, and the exit information comprises exit time.

Correspondingly, the embodiment of the invention also discloses a computer-readable storage medium, and the computer-readable storage medium stores instructions which can be executed on a computer to enable the computer to execute the access person management method.

Correspondingly, the embodiment of the invention also discloses an access personnel management system, which is used for an intelligent door system comprising an intelligent door and comprises:

the first acquisition module is used for acquiring first image information outside the intelligent door;

the identification module is used for identifying first face information to be detected in the first image information and judging whether a first person to be detected corresponding to the first face information to be detected enters a door or not; identifying second face information to be detected in the second image information, and judging whether a second person to be detected corresponding to the second face information to be detected is out;

the adding module is used for adding the information of the first person to be detected to the indoor person database when the identifying module judges that the first person to be detected enters the door;

the second acquisition module is used for acquiring second image information in the intelligent door;

the deleting module is used for deleting the information of the second person to be detected from the indoor person database when the identifying module judges that the second person to be detected goes out;

and the quantity confirmation module is used for receiving the personnel quantity confirmation instruction and determining the personnel quantity in the indoor personnel database.

Correspondingly, the embodiment of the invention also discloses an entrance and exit personnel management system, which comprises: the device comprises a first acquisition module, an identification module, an adding module, a second acquisition module, a deleting module and a quantity confirmation module. The first acquisition module includes a processor, and a memory including instructions that when executed by the processor enable the following functions: first image information outside the intelligent door is collected. The identification module includes a processor, and a memory including instructions that when executed by the processor enable the following functions: identifying first face information to be detected in the first image information, and judging whether a first person to be detected corresponding to the first face information to be detected enters a door or not; and identifying second face information to be detected in the second image information, and judging whether a second person to be detected corresponding to the second face information to be detected goes out. The adding module comprises a processor and a memory, wherein the memory comprises instructions which can realize the following functions when being implemented by the processor: when the recognition module judges that the first person to be detected enters the door, the information of the first person to be detected is added to the indoor person database. The second acquisition module comprises a processor and a memory, wherein the memory comprises instructions that when executed by the processor are capable of performing the following functions: and collecting second image information in the intelligent door. The deletion module includes a processor, and a memory including instructions that when executed by the processor are capable of performing the following functions: and when the identification module judges that the second person to be detected goes out, deleting the information of the second person to be detected from the indoor person database. The quantity validation module includes a processor, and a memory including instructions that when executed by the processor enable the following functions: and receiving a personnel number confirmation command, and determining the personnel number in the indoor personnel database.

Compared with the prior art, the invention has the following technical effects:

through discerning the indoor outer image information who gathers to judge whether someone is business turn over, when personnel are gone into, can add into indoor personnel database with personnel's relevant information, when personnel are gone out, can delete out personnel's relevant information from indoor personnel database, thereby can judge indoor personnel's quantity through the information in the discernment indoor personnel database at last. The method is simple and effective.

Drawings

FIG. 1 is a flow chart illustrating a method of managing access personnel in accordance with the present invention;

fig. 2 is a flowchart illustrating a person management method for a central entrance in the person management method for entrance and exit provided by the present invention;

FIG. 3 is a flowchart of a person management method for a person who enters or exits the door according to the present invention;

FIG. 4 shows a schematic view of an electronic device of an embodiment of the invention;

FIG. 5 illustrates a schematic diagram of a system on a chip of an embodiment of the invention.

Detailed Description

The following description is given by way of example of the present invention and other advantages and features of the present invention will become apparent to those skilled in the art from the following detailed description. While the invention will be described in conjunction with the preferred embodiments, it is not intended that features of the invention be limited to these embodiments. On the contrary, the invention has been described in connection with the embodiments for the purpose of covering alternatives or modifications as may be extended based on the claims of the invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. The invention may be practiced without these particulars. Moreover, some of the specific details have been omitted from the description in order not to obscure or obscure the focus of the present invention. It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.

It should be noted that in this specification, like reference numerals and letters refer to like items in the following drawings, and thus, once an item is defined in one drawing, it need not be further defined and explained in subsequent drawings.

In the description of the present embodiment, it should be noted that the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.

In the description of the present embodiment, it should be further noted that, unless explicitly stated or limited otherwise, the terms "disposed" and "connected" should be interpreted broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. Specific meanings of the above terms in the present embodiment can be understood as specific cases by those of ordinary skill in the art.

To make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

As shown in fig. 1, the present invention provides an entrance and exit person management method that can be used in an intelligent door system, including:

and S101, acquiring first image information outside the intelligent door.

Specifically, the camera can be arranged on one side of the intelligent door located outdoors, and the camera is used for collecting first image information outside the intelligent door. Optionally, the camera can also be arranged on the door frame or the wall side wall on one side outside the intelligent door, as long as the image information near the outside of the intelligent door can be clearly collected.

However, in the image acquisition process, the situation that the front information of the person entering the door cannot be clearly acquired by the camera on the door after the intelligent door is opened sometimes occurs, because the camera arranged on the intelligent door or the door frame and the like is based on the person track tracking for recognizing the face information from the front of the door; however, if someone else enters the system, the face information is not captured, which may result in inaccurate identification. In order to more clearly acquire required image information, a camera can be additionally arranged on an outdoor wall to assist in acquiring images, so that the identity accuracy of the personnel is improved. Because the camera that increases on door frame or wall is fixed, can catch the positive information of people's face that is close to personnel, the personnel that rethread image processing module caught on with two cameras on the door and the door frame or wall carry out the feature matching, obtain the accurate identity of business turn over door personnel to accomplish reliable identification. Specifically, a plurality of cameras can be used for covering the whole monitoring area, the plurality of cameras are connected with each other and are all connected to a switch in a unified manner to form a monitoring network, so that video data among the cameras can be transmitted mutually; when people enter a monitoring area, real-time detection of video streams is carried out by using an HOG algorithm, targets detected by the HOG are numbered, and unique identity identification and positioning are established for each moving target. Preferably, all cameras installed in the monitored area are interconnected and operate simultaneously. When a certain target is searched, each camera can be controlled by operating the control command through monitoring personnel, any monitoring picture is called, and the video data of the cameras can be mutually transmitted. The target matching of the multiple cameras can adopt a speedy-up robust features (SURF) algorithm as a feature extraction algorithm for image matching, the Speed of feature extraction is improved, and matching operation is simplified and the matching Speed is improved by combining an improved random Sample Consensus (PROSAC) algorithm. The main process of SURF feature point detection can be divided into feature point extraction and generation of feature SURF description vectors. The method specifically includes the steps of sequencing all feature-matched point pairs according to the similarity of the feature-matched point pairs, wherein the higher the similarity of the matched point pairs is, the more likely the matched point pairs are the interior points of the correct model, and then determining the parameters of the model by using the data of the interior points. And performing multiple comparison verification to take the corresponding model parameter with the maximum number of the interior points as the optimal matching point pair.

Further, in order to more clearly acquire image information required inside and outside the smart door on the basis of the lowest cost, the camera arranged outside the smart door for acquiring the image information outside the smart door may be a wide-angle lens, and the camera arranged inside the smart door for acquiring the image information inside the smart door may be a conventional lens. Specifically, the wide-angle lens may have a viewing angle of 150 ° or more, whereas the conventional lens is smaller than 90 °, and thus the wide angle may capture wider visual field information.

Step S102, identifying the first face information to be detected in the first image information,

step S103, judging whether a first person to be detected corresponding to the first face information to be detected enters the door or not, if so, executing step S104;

and step S104, adding the information of the first person to be detected to an indoor person database.

The image processing module integrated in the camera or the intelligent door main control module is used for identifying the face information in the image information, identifying the clothing and shape information of each person in the image, and judging whether the person in the image information enters the door or not according to the position information of the person and the door frame.

In addition, the main control module of the intelligent door stores an indoor personnel database, and particularly, the indoor personnel database can be a storage file in the intelligent door system. When the image processing module identifies that a person enters the door, the related information of the person entering the door is transmitted to the main control module, and the main control module stores the related information of the person entering the door into the indoor person database. The related information of the first person to be detected may be face information, identity information or other information that can be distinguished by different persons.

Further, if it is determined in step S103 that the first person to be detected does not enter, the first image information continues to be acquired, the first face information to be detected in the image information is identified, and then the same operation as in step S103 is performed.

And step S105, collecting second image information in the intelligent door.

Specifically, a camera can be arranged on one side of the intelligent door located indoors, and second image information in the intelligent door is collected through the camera. Optionally, the camera can also be arranged on the door frame or the wall side wall on one side of the indoor part of the intelligent door, as long as the image information in the vicinity of the intelligent door can be clearly collected. Furthermore, in order to more clearly acquire the required image information, a camera can be additionally arranged on the indoor wall so as to achieve the purpose of assisting in acquiring the indoor image. Specifically, the matching processing may be performed on the second image information collected by the two cameras by using the image processing method for feature matching mentioned in step S101.

Step S106, identifying the second face information to be detected in the second image information,

step S107, judging whether a second person to be detected corresponding to the second face information to be detected is out, if so, performing carton step S108;

and step S108, deleting the information of the second person to be detected from the indoor person database.

Specifically, the image recognition method in step S106 is similar to the method in step S102, and the image processing module is used to recognize face information in the image, recognize clothing and shape information of each person in the image, and then determine whether the person is out of the door according to the position information of the person and the doorframe.

The face recognition technology is a relatively mature technology, and for example, an AVS03A image processor may be used to determine whether a face image exists in a dynamic scene or a complex background, and separate the face image. In general, the face recognition method may include a reference template method, a face rule method, a sample learning method, a skin color model method, a feature sub-face method, or the like. Taking a reference template method as an example, firstly, one or a plurality of templates of standard human faces are designed, then, collected image information is divided and the like, the matching degree between each divided part of image and the standard template is calculated, and whether the human faces exist is judged by comparing whether the calculated matching degree reaches a threshold value. And whether the personnel pass in and out the door is judged according to the position information of the personnel and the door frame, namely, a door frame channel is firstly identified in the graphic information, and whether the personnel in the utilized image is positioned on the left side or the right side of the door frame is judged so as to judge whether the personnel pass in and out the door. The specific process will be explained in detail below.

In addition, unlike steps S103 and S104, in steps S107 and S108, when the image processing module recognizes that a person is out of the door, a deletion signal is sent to the main control module of the smart door, and after receiving the deletion signal, the main control module deletes information related to the person out of the door from the information stored in the indoor person database. For example, when the indoor personnel database stores personnel identity information (which may include family member identities and stranger identities), after the image processing module determines that a person enters the door according to the first image information, the image processing module further determines the identity information of the person entering the door according to the face information of the person entering the door, and if the identity information of the person entering the door is determined to be dad in the family member at the moment, the text information of 'dad' is stored in the indoor personnel database; similarly, after the image processing module judges that the person is out of the house according to the second image information, the identity information of the person is further judged according to the face information of the person, and if the judged identity information of the person is a mom in the family members, the text information of the mom is deleted from the indoor personnel database.

It should be noted that, in the method for managing persons entering and exiting from a home, steps S101 to S104 are sequentially executed, and steps S105 to S108 are also sequentially executed, but there is no requirement for the execution sequence of steps S101 to S104 and steps S105 to S108, that is, first image information outside a smart door may be collected first, and the first image information is identified and determined (i.e., step S101 to step S104 are executed first), or second image information inside the smart door may be collected first, and the second image information is identified (i.e., step S105 to step S108 are executed first), and the execution sequence of these steps is actually determined depending on the direction of the person entering and exiting from the door, and when the person enters the door, steps S101 to S104 are executed; and when the person goes out, steps S105 to S108 are performed.

And step S109, receiving a personnel number confirmation command, and determining the personnel number in the indoor personnel database.

Specifically, the step may be performed in the main control module of the intelligent door according to all information in the indoor personnel database. Taking the information stored in the indoor personnel database as the identity information of the personnel as an example, step S109 can be understood as follows: after the intelligent door main control module receives the personnel number confirmation instruction, all identity information in the indoor personnel database can be traversed, so that the number of the identity information contained in the indoor personnel database is determined, and the number is the total number of the indoor personnel at the moment. For example, as mentioned above, when the image processing module determines that the person enters the door according to the first image information and further determines that the identity information of the person entering the door is dad of the family member, the text information of "dad" is stored in the indoor person database, if the information stored in the indoor person database is "mom" or "breast", at this time, the "dad" is added to the indoor person database, the information in the indoor person database becomes "dad", "mom" and "breast", and if at this time, the smart door receives a person number confirmation instruction, then the number of the indoor persons can be known to be 3 according to the information stored in the indoor person database; after the person who is out of the house is judged to be 'milk', the text information of 'milk' is deleted from the indoor personnel database by the image processing module after the person who is out of the house is judged to be 'milk', at the moment, the text information of 'dad' and 'mom' are stored in the indoor personnel database, and if the intelligent door receives a personnel quantity confirmation instruction at the moment, the quantity of the indoor personnel at the moment can be known to be 2 according to the information stored in the indoor personnel database.

The method for managing the person entering and exiting the house judges whether the person enters or exits the house by identifying the collected indoor and outdoor image information, adds the related information of the person into the indoor person database when the person enters the house, deletes the related information of the person leaving the house from the indoor person database when the person leaves the house, and finally achieves the purpose of judging the number of the indoor persons by identifying the information in the indoor person database. The method is simple and effective.

Further, in step S103 and step S107, the action of identifying whether the person to be detected in the image information enters the door is triggered by the identification command issued by the main control module. Specifically, after a user unlocks the intelligent door from the outside or the inside, the bolt sensor of the intelligent door can generate an unlocking signal and transmits the unlocking signal to the intelligent door main control module, the intelligent door main control module receives the unlocking signal and then sends a starting command to the door opener to enable the door opener to start opening the door, and meanwhile, the main control module also sends a recognition command to the image processing module to start the door entering and exiting behavior recognition program to detect whether a person to be detected in image information enters or exits the door.

Further, before acquiring the first image information outside the smart door and/or acquiring the second image information inside the smart door, the method may further include: detecting the distance between the intelligent door and the surrounding objects; and if the distance is smaller than the preset distance, awakening the intelligent door to control the acquisition of the first image information and/or the second image information. Therefore, the energy waste caused by long-time startup of the camera for collecting the image information can be avoided.

Specifically, the preset distance may be 0.5m. For example, if a person is 0.6m away from the intelligent door, then the distance between the person and the intelligent door, which is detected by the distance sensor on the intelligent door, is 0.6m, which is greater than the preset distance of 0.5m, then each module of the intelligent door is still in the sleep mode, when the person is 0.4m away from the intelligent door, the distance between the person and the intelligent door, which is detected by the distance sensor, is 0.4m, which is less than the preset distance of 0.5m, then the distance sensor sends a wake-up signal to the main control module of the intelligent door to wake-up the main control module, and then the main control module starts the camera to collect the image information around the intelligent door.

Further, the method may further include: after the information of the first person to be detected is added to the indoor person database, the door entering information of the first person to be detected is recorded; after the information of the second person to be detected is deleted from the indoor person database, the exit information of the second person to be detected is recorded; the entrance information comprises entrance time, and the exit information comprises exit time. Therefore, the user can conveniently and accurately master the door entering and exiting time of the personnel.

Furthermore, the current intelligent home scene linkage has limitation because the quantity of indoor personnel cannot be judged. That is, in the existing away-from-home defense deployment, when a user closes a door, the user manually presses a defense deployment key (a mobile phone, an electronic lock, and a function key on an intelligent door) to start, so that the robot for sweeping the floor, closing doors and windows, starting security monitoring and the like can be linked. To solve the problem, optionally, in the method for managing the person entering and exiting, the person number confirmation instruction may include a door closing confirmation instruction, and the door closing confirmation instruction is generated when it is determined that the second person to be detected is going out and the smart door is closed. The intelligent door system can further comprise a cloud server, and the cloud server is in communication connection with the intelligent home user side; after receiving the person number confirmation command and determining the number of the persons in the indoor person database, the method for managing the entrance and exit of the persons may further include: judging whether the number of indoor personnel is zero, if so, sending an away mode starting instruction to a cloud server; the cloud server receives the leaving mode starting instruction and transmits the leaving mode starting instruction to the intelligent home user side, so that the intelligent home user side can start the leaving mode.

On the basis of judging the number of indoor personnel, the intelligent door can know whether people exist in home when people go out; when no person is present, the intelligent door automatically starts the defense deployment linkage set by the user, and the defense deployment button does not need to be pressed, so that the potential safety hazard caused by forgetting to press the defense deployment button by the user is reduced; and when someone, intelligent door system also can not the automatic start cloth and defend the linkage, has guaranteed the reliability.

In addition, the current smart home system cannot judge whether other people exist indoors, when a user goes home, the user also needs to confirm that no other people exist in the home, and then the smart home linkage set according to the favorite of the user can be started manually, so that rest, study and thinking of other people in the home can be disturbed.

After the information of the family personnel is provided, the intelligent door can know whether the family has the family members when people enter the door; when someone is available, the personalized home furnishing linkage of the user is not automatically started; when no other person exists, the personalized linkage of the user can be intelligently started, such as: turn on your favorite music or turn on the television, set the air conditioner to your favorite temperature, adjust your favorite lights, etc. And manual scene selection starting is not needed. Therefore, the personnel management method for the intelligent door can change the habit of the existing intelligent home scene linkage, so that the intelligent home scene linkage is more intelligent and personalized. Optionally, the number of people confirmation instruction may further include a door opening confirmation instruction, and the door opening confirmation instruction is generated when it is determined that the first person to be detected enters the door and the smart door is closed. When the first detection person enters the door, a door entering confirmation instruction is generated after the intelligent door is closed, whether a person is in the room or not is judged according to the door entering confirmation instruction, and if the person is not in the room, the intelligent door main control module can send a home scene linkage opening instruction to the cloud server; the cloud server receives the home scene linkage starting instruction and transmits the home scene linkage starting instruction to the intelligent home user side, so that the intelligent home user side starts a scene linkage mode.

Alternatively, the step S103 of determining whether the person corresponding to the first face information to be detected enters the door may include:

and identifying first door frame information in the first image information and position information of a first person to be detected, and comparing the first door frame information with the position information of the first person to be detected so as to judge whether the first person to be detected enters the door or not.

The step S107 of determining whether the person corresponding to the second face information to be detected is going out may include:

Whether the principle of discerning personnel to pass in and out can be understood as, when intelligent door was opened, the door frame passageway can be shot to the camera on the intelligent door, and image processing module can discern the door frame in the picture to use the door frame mark as the boundary line, and when personnel passed in and out, must can cross this boundary line, both can use the door frame position as the boundary line, judge whether personnel in the image information are on the left side of boundary line or right side, thereby judge whether personnel passed in and out. Specifically, after the intelligent door main control module receives the unlocking signal, the intelligent door main control module sends a command to the door opening machine to start opening the door, and simultaneously sends a command to the image processing module to start the door access behavior recognition program, the door access behavior recognition program can recognize the door frame position in the picture acquired by the camera in real time, and then recognizes the positions of indoor and outdoor personnel, so that whether the personnel are on the left side or the right side is judged by taking the door frame position as a boundary line, and whether the personnel access the door is judged.

When the intelligent door is specifically implemented, whether the intelligent door is indoors or outdoors can be judged according to the installation mode of the door and the position of a person, so that whether the person enters or exits the door can be judged. Can be in order to set up the door frame differently with the position relation between waiting to detect the personnel according to the mounting means of intelligent door to reach the purpose of accurate judgement whether have personnel's business turn over. Specifically, for doors which are opened to the indoor right and the outdoor left, the left side of the door frame is indoor; for doors which are opened indoors from left and opened outdoors from right, the right side of the doorframe is indoor. In a door opening and closing cycle process, the position is changed from indoor to outdoor and is identified as an exit, and the position is changed from outdoor to indoor and is identified as an entrance; and after the door is closed, the door entrance and exit behavior identification program is ended. For example, for a smart door that opens to the right of the room, if the image processing module recognizes that the position of the person to be detected changes from being on the left side of the boundary to being on the right side of the boundary, the image processing module may consider the person to be detected as being out.

In specific implementation, whether people enter or exit the door is judged by carrying out recognition processing after carrying out feature matching and synthesis on images collected by the cameras arranged indoors and outdoors. This is because the camera of collection monitoring door frame passageway is installed outdoors, if the intelligent door is to the form of opening to the indoor, before opening the door, the indoor people face information can not be gathered to the camera outside the door, can only gather people's side face information, clothing, physique information etc. after the door is opened. Therefore, inaccurate face recognition may occur in the recognition process, and thus, the camera mounted on the inner panel of the door can recognize face front information of a person in the door before the door is opened. And for doors that open outdoors: the monitoring camera installed on the door outer panel cannot collect the picture of the door channel after the door is opened, so that the camera is required to be installed on the door inner panel to collect the picture of the door channel so as to identify the in-and-out behavior, and meanwhile, the monitoring camera is used for identifying the face front information of the person at the door.

In other words, for doors that open indoors: the camera of the door outer panel is used for identifying the front face information of a person before the door is opened outdoors and collecting the door channel picture; the function of the inner panel camera of the door is to identify the front face information of the person before the door is opened indoors; for the door which is opened outdoors, the camera of the outer panel of the door is used for identifying the front face information of the person before the door is opened outdoors; the inner panel camera of the door is used for identifying the front face information of a person before the door is opened indoors and collecting the door channel picture.

Specifically, the fusion judgment process of the personnel information collected by the two cameras inside and outside the door can be as follows:

for doors that open indoors:

when going out: before people go out of the door, a camera of the inner door panel collects face information to identify the identity and collects clothing and shape information; after the door is opened, when a person passes through the door channel, the camera of the outer door panel collects the side face, the clothes and the body of the person; the intelligent door can accurately acquire the identity of the person who goes out by comparing the information of the side face, clothes and body of the person who has the behavior of going out with the information acquired by the camera in the front door of going out.

When entering the door: before people enter a door, a camera on an outer door panel collects face information to identify the identity and clothing and shape information; after the door is opened, when a person passes through the door channel, the camera of the outer door panel collects the side face, the clothes and the body of the person; the intelligent door can accurately acquire the identity of the person entering the door by identifying the side face, clothing and shape information of the person who enters the door and comparing the information with the information acquired by the camera outside the front door of the door.

For doors that open out:

when entering the door: before people enter a door, a camera on an outer door panel collects face information to identify the identity and clothing and shape information; after the door is opened, when a person passes through the door channel, the camera of the inner door panel collects the side face, clothes and body of the person; the intelligent door can accurately acquire the identity of the person entering the door by identifying the side face, clothes and body information of the person with the door exit behavior and comparing the information with the information acquired by the camera outside the front door of the entering door.

When going out: before people go out of the door, a camera of the inner door panel collects face information to identify the identity and collects clothing and shape information; after the door is opened, when a person passes through the door channel, the camera of the inner panel of the door collects the side face, clothes and body of the person; the intelligent door can accurately acquire the identity of the person going out by identifying the side face, clothes and body information of the person having the action of going out and comparing the information with the information acquired by the camera in the front door of the person going out.

Optionally, the information in the indoor people database may include the identity of each family person and the identity of a stranger;

adding the information of the first person to be detected to the indoor person database in the step S104 may include the steps of:

and adding the identity information of the first person to be detected to an indoor person database.

Optionally, the threshold range of the similarity may be not less than 90%, that is, when the similarity between the face information to be detected and the preset face information reaches or exceeds 90%, it may be determined that the person to be detected and the person corresponding to the preset face information are the same person. For example, when the similarity between the face information to be detected and the preset face information is 80%, the two persons are considered to be different because 80% is less than 90%, and when the similarity between the face information to be detected and the preset face information is 95%, the two persons are considered to be the same because 95% is greater than 90%.

Further, the identity of the family can include title information of dad, mom, breast, child, etc., for example, when the person entering the house is identified as dad, the word information of "dad" is added to the indoor people database.

The deleting of the information of the second person to be detected from the indoor person database in step S108 may include:

if the preset face information contains the family person face information with the similarity of the second face information to be detected within the threshold value range, judging the family person identity of the second person to be detected according to the family member face information with the similarity within the threshold value range; otherwise, the second person to be detected is a stranger;

Similarly, the threshold range in this step may also be not less than 90%, that is, when the similarity between the face information to be detected and the preset face information reaches or exceeds 90%, the same person may be considered.

As mentioned above, the identity of the family can include the title information of dad, mom, breast, child, etc., for example, when the person who is going to go is identified as dad, the main control module deletes the text information of "dad" in the indoor people database.

Further, the intelligent door system can further comprise a cloud server and a user terminal which are in communication connection. And when the first person to be detected and/or the second person to be detected are/is judged to be children and strangers, alarm information is sent to the cloud server, and the cloud server sends the alarm information to the user terminal to give an alarm.

When the image processing module judges that the person entering the door or the person leaving the door only comprises children and strangers, alarm information is sent to the cloud server, at the moment, the intelligent door can send a message that the stranger enters the room and a face snapshot of the stranger to the cloud server through the wireless network, and the cloud server sends the information of the stranger entering the door and the face snapshot to the user mobile phone app; after receiving the information, the mobile phone app sends an alarm prompt, wherein the alarm prompt can be set to be vibration, prompt tone or mute prompt-free.

Further, in the door entry identification process, after the first person to be detected is judged to be a stranger, before the identity information of the stranger is added to the indoor person database, the first face information to be detected of the person entering the door can be compared with the face information in the stranger database to determine the corresponding stranger number, and the first face information to be detected is stored in the stranger database; at this time, the identity information of the strangers added to the indoor personnel database is the stranger number. The intelligent door also comprises a stranger database, the stranger database can also be a storage file stored in the intelligent door system, the stranger database comprises stranger face information and stranger numbers corresponding to the face information, and the stranger face information corresponds to the stranger numbers one by one. That is, stranger numbers such as "stranger 001", "stranger 002", and the like are stored in the storage file, when the image processing module identifies that the person entering the door is stranger 001, the text information of "stranger 001" is stored in the indoor person database, if the image processing module does not find a stranger number corresponding to the face information of the person entering the door in the stranger database, the intelligent door main control module numbers the stranger entering the door according to the stranger coding sequence in the stranger database, for example, the numbers in the stranger database are from "stranger 001" to "stranger 005", and if the number corresponding to the face information of the person entering the door is not found in the stranger database at this time, the main control module recodes the stranger face information into "stranger 006", and stores the stranger face information and the stranger "006" in the stranger database together.

Furthermore, strangers who go in and out for multiple times can be clustered, and therefore multiple-time-of-going-in and-out information of the strangers is related. Before manual identity labeling is not carried out, only the faces classified into one group are known to belong to the same identity, but the exact identity is not known, so that the user information is inconvenient to summarize. For example, a stranger is present today, and the stranger who has come the past week can be found to be a person through the face clustering. Face clustering may be specifically understood as dividing people with the same identity into a group by comparing every two faces in a set and then analyzing according to the similarity values.

Further, in the process of the identification and judgment of the person going out, after the second person to be detected is judged to be a stranger, before the identity information of the second person to be detected is deleted from the indoor person database, the person entering and exiting management method may further include:

judging whether face information with the similarity between the second face information to be detected of the stranger and the face information in the threshold range exists in the stranger database;

if the similarity exists, judging a stranger number corresponding to a stranger according to the face information with the similarity within the threshold range, and deleting the stranger number corresponding to the stranger from the indoor personnel database;

Namely, the image processing module can compare the detected face information of the person who goes out with the face information in the stranger database to judge the number of the stranger, and meanwhile, the stranger number is deleted in the indoor person database. For example, the image processing module identifies face information of a person going out to judge the number of the stranger, when the stranger number exists in the indoor person database, the main control module deletes the number in the indoor person database, if the stranger number does not exist in the indoor person database, it is indicated that the stranger may enter the room through illegal ways such as window climbing, at the moment, the cloud server gives an alarm to a user terminal (which may be an APP terminal downloaded on a mobile phone), and optionally, the face information of the stranger which may enter the room illegally can be sent to the user terminal, so that the user terminal can grasp indoor conditions in real time, and the house safety is improved.

Further, in the door entering identification process, after the first person to be detected is judged to be a stranger, the intelligent door can store the first face information to be detected of the stranger while the identity information of the stranger is added to the indoor person database; the cloud server receives a first calling request instruction sent by the user terminal, calls first face information to be detected of a stranger stored in the intelligent door, and transmits the first face information to be detected to the user terminal.

When a stranger enters a room, the intelligent door stores face information of the stranger and uploads the face information to the cloud server, when a user wants to check the information of the stranger entering the door through the user terminal, a first calling icon on the user terminal can be clicked, the user terminal responds to user operation at the moment and sends a first calling request instruction to the cloud server, and the cloud server calls the stored face information of the stranger entering the door according to the first calling request instruction and transmits the face information to the user terminal so that the user can check the face information.

Further, in the process of identification when the user goes out, after the second face information to be detected is judged to be a stranger, the intelligent door can store the second face information to be detected of the stranger while identity information of the stranger is deleted from the indoor personnel database; the cloud server receives a second calling request instruction sent by the user terminal, calls second face information to be detected of the stranger stored in the intelligent door, and transmits the second face information to be detected to the user terminal.

When a stranger goes out of a room, the intelligent door can also store face information of the stranger, the face information is uploaded to the cloud server, when a user wants to check the information of the stranger, the user can click a second calling icon on the user terminal, the user terminal can respond to user operation and send a second calling request instruction to the cloud server, and similarly, the cloud server can call the stored face information of the stranger according to the second calling request instruction and transmit the face information to the user terminal so that the user can check the face information. Therefore, the user can conveniently master the related information of strangers entering and exiting the door, and the safety is improved.

The following describes the steps of the method for managing an entering/exiting person according to the present invention with reference to fig. 2 and 3 as an example.

Fig. 2 is a flow chart of entrance detection in the entrance and exit management method, when a sensor on an intelligent door detects the presence of a person nearby, an intelligent door main control module and a camera are waken (i.e., the intelligent door is waken), the camera collects image information outside the intelligent door, an image processing module performs face recognition on the image information collected by the camera, the number of faces is determined (i.e., the number of people in front of the door is recognized), the face information is compared with preset face information stored in the intelligent door in advance to recognize the identity information of people in front of the door (i.e., all the people in front of the door is recognized), when the verification is passed, the intelligent door is unlocked (i.e., the verification is passed), the main control module sends an entrance recognition instruction to the image processing module, the image processing module recognizes the image information collected by the camera in real time, whether the person enters the house is determined according to the movement trajectory of the person (i.e., all the movement trajectory of the person is captured, whether the person enters the house is determined), if the house, the person enters the house is further determined, if the person enters the house, the person is a stranger, the person is marked, and then the information of the stranger is added to an indoor person database; if the person entering the door is not a stranger, the information of the person entering the door is directly added to an indoor person database, meanwhile, the intelligent door records the door entering time of the person entering the door (namely, the information of the person entering the door is recorded), and the detection of the person entering the door is finished; if the person is judged not to enter the house according to the movement track of the person, the image information acquired by the camera in real time is continuously identified by the image processing module to judge whether the person enters the house subsequently until the intelligent door is closed, and the entrance detection process is finished.

Fig. 3 is a flowchart of the exit detection in the entering and exiting personnel management method, similar to the entering detection method. When a sensor on the intelligent door detects that people exist nearby, an intelligent door main control module and a camera are waken up (i.e. the intelligent door is waken up), the camera collects image information in the intelligent door, an image processing module carries out face recognition on the image information collected by the camera, the number of faces is judged (i.e. the number of people in front of the door is recognized), each face information is compared with preset face information stored in the intelligent door in advance to recognize identity information of people in front of the door (i.e. the identities of all people in front of the door is recognized), when the person is verified, the intelligent door is unlocked, the main control module sends an exit recognition instruction to the image processing module, the image processing module recognizes the image information collected by the camera in real time, whether the person leaves the door or not is judged according to the movement track of the people (i.e. all people moving tracks are captured, whether the person leaves the door or not is judged), if the person leaves the door, whether the person entering person is a stranger or not is a stranger is judged, if the person leaves the stranger, the door information in an indoor person database is marked, and if the stranger leaves the door information is deleted, the stranger information in the indoor person database is pushed to the indoor person leaving the door, and the indoor person clustering alarm information is pushed to the stranger, if the stranger is obtained, and the stranger is obtained in the indoor person is obtained; if the person who leaves the door is not a stranger, the information of the person who enters the door is directly deleted from the indoor personnel database, meanwhile, the intelligent door records the time of the person who leaves the door (namely, the information of the person who enters the door), and at the moment, one detection on the person who leaves the door is finished; if the person is judged not to go out according to the movement track of the person, the image information acquired by the camera in real time is continuously identified by the image processing module to judge whether the person goes out subsequently until the intelligent door is closed, and the going-out detection process is finished.

According to the method for managing the person entering and exiting the intelligent door, the identity and the quantity change of the person at home can be deduced according to the person identity information stored in the indoor person database, and when the number of the persons in the indoor person database is zero, the main control module of the intelligent door can automatically start the defense deployment setting of the leaving mode; moreover, the intelligent door can identify the identities of all people who come in and go out at each time, so that the accurate time of each person who comes in and go out can be known, and the accurate information of the coming in and going out of children and old people and the coming in and going out of strangers along with family members can be accurately obtained; when a family enters or exits a stranger, the related image information of the stranger can be recorded in time. And when a stranger leaves through the door after entering illegally through other ways, the intelligent door can give an alarm like a user terminal so that the user can know the situation in time.

Accordingly, the embodiment of the invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, and the instructions are suitable for being added by a processor and executing the access personnel management method.

Referring to FIG. 4, shown is a block diagram of an electronic device 400 in accordance with one embodiment of the present application. The electronic device 400 may include one or more processors 401 coupled to a controller hub 403. For at least one embodiment, the controller hub 403 communicates with the processor 401 via a multi-drop Bus such as a Front Side Bus (FSB), a point-to-point interface such as a QuickPath Interconnect (QPI), or similar connection port. The processor 401 executes instructions that control data processing operations of a general type. In one embodiment, the Controller Hub 403 includes, but is not limited to, a Graphics Memory Controller Hub (GMCH) (not shown) and an Input/Output Hub (IOH) (which may be on separate chips) (not shown), where the GMCH includes a Memory and a Graphics Controller and is coupled to the IOH.

The electronic device 400 may also include a coprocessor 402 and memory 404 coupled to the controller hub 403. Alternatively, one or both of the memory and GMCH may be integrated within the processor (as described herein), with the memory 404 and coprocessor 402 coupled directly to the processor 401 and controller hub 403, with the controller hub 403 and IOH in a single chip.

The Memory 404 may be, for example, a Dynamic Random Access Memory (DRAM), a Phase Change Memory (PCM), or a combination of the two. Memory 404 may include one or more tangible, non-transitory computer-readable media therein for storing data and/or instructions. The computer readable storage medium has stored therein instructions, in particular, temporary and permanent copies of the instructions. The instructions may include: instructions that, when executed by at least one of the processors, cause the electronic device 400 to implement the method shown in fig. 1. The instructions, when executed on a computer, cause the computer to perform the methods disclosed in any one or combination of the embodiments above.

In one embodiment, the coprocessor 402 is a special-purpose processor, such as, for example, a high-throughput MIC (man Integrated Core) processor, a network or communication processor, compression engine, graphics processor, GPGPU (General-purpose computing on graphics processing unit), embedded processor, or the like. The optional nature of coprocessor 402 is represented in FIG. 4 by dashed lines.

In one embodiment, the electronic device 400 may further include a Network Interface Controller (NIC) 406. Network interface 406 may include a transceiver to provide a radio interface for electronic device 400 to communicate with any other suitable device (e.g., front end module, antenna, etc.). In various embodiments, the network interface 406 may be integrated with other components of the electronic device 400. The network interface 406 may implement the functions of the communication unit in the above-described embodiments.

The electronic device 400 may further include an Input/Output (I/O) device 405.I/O405 may include: a user interface designed to enable a user to interact with the electronic device 400; the design of the peripheral component interface enables peripheral components to also interact with the electronic device 400; and/or sensors may be configured to determine environmental conditions and/or location information associated with electronic device 400.

It is noted that fig. 4 is merely exemplary. That is, although fig. 4 shows that the electronic device 400 includes a plurality of devices, such as a processor 401, a controller hub 403, a memory 404, etc., in practical applications, the device using the methods of the present application may include only a part of the devices of the electronic device 400, for example, may include only the processor 401 and the network interface 406. The nature of the optional device in fig. 4 is shown in dashed lines.

Referring now to fig. 5, shown is a block diagram of a SoC (System on Chip) 500 in accordance with an embodiment of the present application. In fig. 5, like parts have the same reference numerals. In addition, the dashed box is an optional feature of more advanced socs. In fig. 5, soC500 includes: an interconnect unit 550 coupled to the processor 510; a system agent unit 580; a bus controller unit 590; an integrated memory controller unit 540; a set or one or more coprocessors 520 which may include integrated graphics logic, an image processor, an audio processor, and a video processor; an Static Random-Access Memory (SRAM) unit 530; a Direct Memory Access (DMA) unit 560. In one embodiment, coprocessor 520 comprises a special-purpose processor, such as, for example, a network or communication processor, compression engine, GPGPU (General-purpose computing on graphics processing units, general-purpose computing on a graphics processing unit), high-throughput MIC processor or embedded processor, or the like.

Static Random Access Memory (SRAM) unit 530 may include one or more tangible, non-transitory computer-readable media for storing data and/or instructions. The computer readable storage medium has stored therein instructions, in particular, temporary and permanent copies of the instructions. The instructions may include: instructions that when executed by at least one of the processors cause the SoC to implement the method as shown in fig. 1. The instructions, when executed on a computer, cause the computer to perform the methods disclosed in the embodiments described above.

The method embodiments of the present application may be implemented in software, magnetic, firmware, etc.

Program code may be applied to input instructions to perform the functions described herein and generate output information. The output information may be applied to one or more output devices in a known manner. For purposes of this application, a processing system includes any system having a Processor such as, for example, a Digital Signal Processor (DSP), a microcontroller, an Application Specific Integrated Circuit (ASIC), or a microprocessor.

The program code may be implemented in a high level procedural or object oriented programming language to communicate with a processing system. The program code can also be implemented in assembly or machine language, if desired. Indeed, the mechanisms described herein are not limited in scope to any particular programming language. In any case, the language may be a compiled or interpreted language.

One or more aspects of at least one embodiment may be implemented by representative instructions stored on a computer-readable storage medium, which represent various logic in a processor, which when read by a machine causes the machine to fabricate logic to perform the techniques herein. These representations, known as "IP (Intellectual Property) cores," may be stored on a tangible computer-readable storage medium and provided to a number of customers or production facilities to load into the manufacturing machines that actually manufacture the logic or processors.

In some cases, an instruction converter may be used to convert instructions from a source instruction set to a target instruction set. For example, the instruction converter may transform (e.g., using static binary transformations, dynamic binary transformations including dynamic compilation), morph, emulate, or otherwise convert an instruction into one or more other instructions to be processed by the core. The instruction converter may be implemented in software, hardware, firmware, or a combination thereof. The instruction converter may be on the processor, external to the processor, or partially on and partially off the processor.

While the invention has been shown and described with reference to certain preferred embodiments thereof, it will be understood by those skilled in the art that the foregoing is a more particular description of the invention than is possible with reference to the specific embodiments, and the specific embodiments of the invention are not to be considered as limited to those descriptions. Various changes in form and detail, including simple deductions or substitutions, may be made by those skilled in the art without departing from the spirit and scope of the invention.

Claims

1. An access personnel management method for a smart door system including a smart door, comprising:

collecting first image information outside the intelligent door;

the information in the indoor personnel database comprises identity information of each family and identity information of strangers; the adding the information of the first person to be detected to an indoor person database comprises:

respectively comparing the first to-be-detected face information with each family person face information in preset face information to judge the identity information of the first to-be-detected person;

if the preset face information contains the family member face information with the similarity with the first face information to be detected within a threshold value range, judging the family member identity of the first person to be detected according to the family member face information with the similarity within the threshold value range; otherwise, the first person to be detected is a stranger identity;

adding the identity information of the first person to be detected to the indoor person database;

after the first person to be detected is judged to be a stranger, before identity information of the stranger is added to the indoor person database, the method further comprises the following steps:

comparing the first face information to be detected with face information in a stranger database to determine the corresponding stranger number of the first face information to be detected, and storing the first face information to be detected in the stranger database;

wherein the stranger identity information added to the indoor personnel database is the stranger number;

clustering strangers who come in and go out for many times; the clustering is to compare every two faces in the set, analyze according to these similarity values, divide the people belonging to the same identity into a group, thus associate the multiple entrance and exit information of this stranger;

collecting second image information in the intelligent door;

identifying second face information to be detected in the second image information, judging whether a second person to be detected corresponding to the second face information to be detected goes out, and if so, deleting the information of the second person to be detected from the indoor person database;

deleting the information of the second person to be detected from the indoor person database comprises:

if the preset face information contains the family personnel face information with the similarity to the second face information to be detected within a threshold range, judging the family personnel identity of the second person to be detected according to the family member face information with the similarity within the threshold range; otherwise, the second person to be detected is the identity of a stranger;

deleting the identity information of the second person to be detected from the indoor person database;

if the similarity exists, judging a stranger number corresponding to the stranger according to the face information with the similarity within a threshold range, and deleting the stranger number corresponding to the stranger from the indoor personnel database;

if the alarm information does not exist, sending alarm information to a cloud server, and sending the alarm information to a user terminal by the cloud server;

the cloud server receives a second calling request instruction sent by the user terminal, calls second face information to be detected of the stranger stored in the intelligent door and transmits the second face information to be detected to the user terminal;

receiving a personnel number confirmation instruction, traversing all identity information in the indoor personnel database, and determining the personnel number in the indoor personnel database, wherein the personnel number is the total number of the indoor personnel at the moment.

2. The person management method according to claim 1, wherein the person number confirmation instruction includes a door closing confirmation instruction, and the door closing confirmation instruction is generated when it is determined that the second person to be checked is out and the smart door is closed.

3. The method of managing access to personnel of claim 2, wherein said smart door system further comprises a cloud server, said cloud server being communicatively coupled to a smart home client; after the receiving the person number confirmation instruction and determining the number of the persons in the indoor person database, the method for managing the entrance and exit persons further comprises the following steps:

judging whether the number of the personnel in the indoor personnel database is zero, if so, sending an away mode starting instruction to the cloud server;

and the cloud server receives the off-home mode starting instruction and transmits the off-home mode starting instruction to the intelligent home user side, so that the intelligent home user side starts the off-home mode.

4. The method for managing an entering or exiting person of claim 1,

judging with whether the first personnel that wait to detect who waits to detect the face information corresponding enter includes:

identifying first door frame information in the first image information and position information of the first person to be detected, and comparing the first door frame information with the position information of the first person to be detected to judge whether the first person to be detected enters a door or not;

the judging whether a second person to be detected corresponding to the second face information to be detected goes out comprises the following steps:

and identifying second doorframe information in the second image information and the position information of the second person to be detected, and comparing the second doorframe information with the position information of the second person to be detected so as to judge whether the second person to be detected leaves.

5. The method of access personnel management of claim 1, wherein said intelligent door system further comprises a cloud server and a user terminal communicatively connected; the method for managing the person who enters or exits further includes:

the cloud server receives a first calling request instruction sent by the user terminal, calls first face information to be detected of the stranger stored in the intelligent door, and transmits the first face information to be detected to the user terminal.

6. The person management method according to claim 1, wherein the family person identity includes a child, and when it is determined that the first person to be detected and/or the second person to be detected are a child and a stranger, alarm information is sent to the cloud server, and the cloud server sends the alarm information to the user terminal to alarm.

7. The method for managing access personnel of claim 1, wherein prior to said capturing first image information outside the intelligent door and/or capturing second image information inside the intelligent door, further comprising:

8. The method for managing an entering or exiting person of claim 1, further comprising:

after the information of the first person to be detected is added to an indoor person database, recording the entrance information of the first person to be detected;

9. A computer-readable storage medium having instructions stored thereon, which when executed on a computer, cause the computer to perform the access person management method of any one of claims 1-8.