Intelligent property management system

Abstract

The invention discloses an intelligent property management system, and the system comprises an input module which is used for obtaining owner information, and inputting reserved visitor information corresponding to the owner information; the acquisition module is used for acquiring a current visitor image, current visitor information and the like; the path navigation module is used for generating a navigation path from the park entrance to the owner address when the current visitor information is consistent with the reserved visitor information, and indicating the path direction through an indicating device; and the tracking navigation module is used for acquiring and tracking an image of the current visitor in the park, determining the position of the current visitor in the park based on the image, regenerating a navigation path if the position is not on the navigation path, and indicating the direction of the path through the indicating device. According to the invention, a visitor can be prevented from taking out a mobile phone to repeatedly view a map or repeatedly looking for a worker in a park to ask the way, so that the experience of the visitor in the last travel is improved, the time of the visitor is saved, and an owner does not need to dispatch a reception person for guidance.

Description

Technical Field

[0001] The present invention relates to the field of property management technology, and more specifically, to a smart property management system. Background Art

[0002] With the development of Internet of Things technology, property management is gradually turning to intelligence. In order to ensure the normal and orderly production and operation activities in the park and improve the accuracy and timeliness of visitor management in the park, the information of vehicles or personnel entering the park is generally collected, and the vehicles or personnel entering and leaving the park are restricted and confirmed based on the collected vehicles or personnel, and the location information of visitors is monitored through video. For larger office parks or industrial parks, since visitors may be visiting for the first time and are not familiar with the environment in the park, they are easy to get lost and delay the time to visit the owners in the park, resulting in a poor experience for both visitors and park owners. Summary of the invention

[0003] An object of the present invention is to solve at least the above problems and to provide at least the advantages which will be described hereinafter.

[0004] In order to achieve these purposes and other advantages according to the present invention, a smart property management system is provided, comprising:

[0005] An input module, which is used to obtain owner information, input reserved visitor information and reserved visit time corresponding to the owner information, the owner information including owner name and owner address;

[0006] An acquisition module is used to acquire the current visitor image, current visitor information, visit information and current visit time;

[0007] A path navigation module is used to check whether the current visitor information is consistent with the reserved visitor information and whether the current visit time is consistent with the reserved visit time. If they are consistent, a navigation path between the park entrance and the owner's address is generated, and the path direction is indicated by an indicator device preset on the roadside of the park;

[0008] A tracking navigation module is used to obtain images of the current visitor in the park, and determine the current visitor's position in the park based on the images of the current visitor in the park. If the current visitor's position in the park is not on the navigation path, the navigation path between the current visitor and the owner's address is regenerated based on the current visitor's position in the park, and the path direction is indicated by an indication device preset on the roadside of the park.

[0009] Preferably, a plurality of indicating devices are provided, each indicating device is correspondingly arranged at an intersection in the park, and the indicating device is an LED electronic road sign or a display or a loudspeaker; when the indicating device is an LED electronic road sign or a display, the way of indicating the path direction is to display the owner's address information and the path direction of the current intersection; when the indicating device is a loudspeaker, the way of indicating the path direction is to play the owner's address information and the path direction of the current intersection.

[0010] Preferably, the navigation path between the park entrance and the owner's address is generated by using one of the Dijkstra algorithm, the A* algorithm, and the Bellman-Ford algorithm.

[0011] Preferably, the method for determining the location of the current visitor in the park based on tracking the image of the current visitor in the park includes:

[0012] Extracting target features of the current visitor image obtained by the acquisition module;

[0013] Identify images of current visitors in the park with target features, associate each image of the current visitor in the park with the shooting time of the image, and obtain multiple images of the current visitor in the park arranged in time sequence;

[0014] Separating a current visitor from a background in a plurality of images of the current visitor in the park;

[0015] Based on the preset correspondence between the background scene in the image of the park and the positioning in the electronic map of the park, multiple images of the current visitor in the park arranged in time sequence are analyzed to obtain the corresponding movement trajectory and final position of the current visitor in the electronic map of the park.

[0016] Preferably, if the target feature in the image tracking the current visitor in the park disappears, an autoregressive algorithm is used to predict the position of the current visitor in the electronic map of the park at the next moment according to the movement trajectory of the current visitor in the electronic map of the park, as follows:

[0017]

[0018] Where, X t is the predicted position at the next moment, c is a constant term, and p is the order of the model, indicating that too few past moments are used. is the parameter of the model, representing the weight of the i-th past moment, X t-i is the position of the i-th past moment, ε t is the error term, which represents the random fluctuations of the model.

[0019] Preferably, p is determined by an information criterion or a cross-validation method, Determined using the least squares method or maximum likelihood method.

[0020] Preferably, it further comprises: a notification module, which is used to inform the owner of a visit event through a notification device preset at the owner's address when the current visitor information is consistent with the reserved visitor information.

[0021] Preferably, the notification device is a built-in speaker display, and the notification module is also used to transfer the image of the current visitor in the park obtained by the tracking navigation module to the notification device, and after the target feature in the image of the current visitor in the park disappears for a preset period of time, the notification device is used to inform the current visitor of the emergency situation.

[0022] The present invention includes at least the following beneficial effects: since the park entrance and the owner's address are fixed, the path navigation can be generated in real time according to the arrival time of the visitor. At the same time, the indicator device set at the intersection in the park can intuitively and conveniently guide the visitor to walk. In addition, with the help of the real-time image of the visitor in the park, the visitor's position in the park can be located in real time. When the visitor's walking path deviates from the initial navigation path, the visitor can be quickly re-navigated and guided to walk again with the help of the indicator device. It avoids the visitor taking out the mobile phone to check the map repeatedly, or repeatedly looking for the staff in the park to ask for directions, which not only improves the visitor's experience in the last leg of the trip, but also saves the visitor's time, and at the same time, there is no need for the owner to send reception staff to guide.

[0023] Other advantages, objectives and features of the present invention will be embodied in part through the following description, and in part will be understood by those skilled in the art through study and practice of the present invention. DETAILED DESCRIPTION

[0024] The present invention is further described in detail below in conjunction with embodiments so that those skilled in the art can implement the invention with reference to the description.

[0025] It should be noted that, in the description of the present invention, terms such as "lateral", "longitudinal", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside" and "outside" to indicate directions or positional relationships are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as a limitation on the present invention.

[0026] The present invention provides a smart property management system, which can be set in a backend server and includes:

[0027] An input module, which is used to obtain owner information, input reserved visitor information and reserved visit time corresponding to the owner information, the owner information including owner name and owner address;

[0028] Specifically, the owner name may be a company name or a corporate legal person name, and the owner address may be a company office address, such as a building, floor, or office number. The reserved visitor information may be the visitor's name, gender, telephone number, etc. After the visitor communicates with the owner in advance to make an appointment, the owner's personnel may enter the reserved visitor information and reserved visit time through the computer management terminal at the property office, and the computer management terminal then transmits this information to the system placed on the backend server. After the entry module obtains this information, it may record the reserved visitor information and reserved visit time under the owner information column. Here, multiple pieces of reserved visitor information and reserved visit time may be recorded under one owner information.

[0029] An acquisition module is used to acquire the current visitor image, current visitor information, visit information and current visit time;

[0030] Specifically, the current visitor information may be the name, phone number and other information of the current visitor, and the visit information may be the name of the owner that the current visitor needs to visit and other information. A camera may be used to obtain the current visitor's image, and the current visitor information and visit information may be inputted through a computer client. The current visit time may be obtained by obtaining the time online. When a visitor arrives at the entrance of the park, the visitor image, visitor information, visit information and visit time may be obtained in real time through the camera at the entrance of the park and the security personnel at the security office at the entrance of the park inputted into the computer client. The computer client then transmits this information to the system placed on the background server, and the acquisition module may temporarily save this information after acquiring it.

[0031] A path navigation module is used to check whether the current visitor information is consistent with the reserved visitor information and whether the current visit time is consistent with the reserved visit time. If they are consistent, a navigation path between the park entrance and the owner's address is generated, and the path direction is indicated by an indicator device preset on the roadside of the park;

[0032] Specifically, the path navigation module reads the current visitor image, current visitor information, visit information and current visit time obtained by the acquisition module, and then searches for the owner information corresponding to the owner name in the visit information among the numerous owner information pre-saved in the system based on the visit information, and then reads the reserved visitor information and the reserved visit time under the owner information column, and then checks whether the current visitor information is consistent with the reserved visitor information and whether the current visit time is consistent with the reserved visit time. If they are consistent, a navigation path between the park entrance and the owner's address is generated, and the path direction is indicated by an indication device preset on the roadside of the park. If they are inconsistent, the visit is informed of an error, and the incorrect visit information can be sent to a computer client set at the security office at the entrance of the park, and then the security personnel inform the visitor.

[0033] Through appointment-based visits, the management of park security can be strengthened, the activities of unrelated personnel in the park can be reduced, and the impact on the normal operation of owners in the park can be avoided.

[0034] More specifically, the navigation path between the park entrance and the owner's address is generated using one of the Dijkstra algorithm, the A* algorithm, and the Bellman-Ford algorithm. The Dijkstra algorithm is an algorithm used to find the shortest path from a single node to all other nodes in a graph. Since it always selects the one with the smallest distance among the unmarked nodes, it can ensure that the shortest path is found. The algorithm logic is simple and easy to implement. However, due to its algorithm logic, it may cause incorrect updates to the shortest path when processing graphs with negative weighted edges. The A* algorithm can introduce global information in the search process and estimate the distance from the current node to the target node through a heuristic function, thereby quickly finding the optimal path. However, the algorithm has a high computational complexity. When the number of nodes is large, the computation time is long and it is more dependent on the design of the heuristic function. Improper design affects the algorithm effect. The Bellman-Ford algorithm can process graphs containing negative weighted edges. The implementation is relatively simple, but the time complexity is high and it is not suitable for undirected graphs. When selecting an algorithm, any algorithm suitable for calculating the navigation path can be selected according to the park environment.

[0035] More specifically, there are several indicating devices, each of which is arranged at an intersection in the park, and the indicating device is an LED electronic road sign or a display or a loudspeaker; when the indicating device is an LED electronic road sign or a display, the way to indicate the path direction is to display the owner's address information and the path direction of the current intersection; when the indicating device is a loudspeaker, the way to indicate the path direction is to play the owner's address information and the path direction of the current intersection.

[0036] It is more recommended that the indicating device is an LED electronic road sign or display. In this way, when there are multiple visitors, the LED electronic road sign or display can display the visiting address and the path direction of the current intersection of each visitor one by one.

[0037] Since the existing electronic maps generally have a large grid scale, and when they are refined to a certain park, the accuracy is often insufficient, and it is difficult for users to confirm the detailed path through the electronic map. Therefore, the present invention sets an indication device at each intersection in the park. The indication device can more clearly guide visitors on the walking path in the park, so that visitors can find the address of the owner they need to visit more accurately and quickly.

[0038] More specifically, the path navigation module can decompose the navigation path into straight line segments that are connected in sequence. The connection between the previous path and the subsequent path occurs at the intersection of the park. If there are multiple next paths with different directions at the intersection, the multiple next paths with different directions can be coded respectively, and the path navigation module checks which coded next path the subsequent path is in. Based on the correspondence between the pre-set code and the path direction icon or voice, the path navigation module can control the indication device to indicate the path direction icon or voice corresponding to the code of the subsequent path. When the visitor walks to the intersection along the previous path, he can turn to the subsequent path according to the path direction icon or voice given by the indication device, so it is not easy to go wrong.

[0039] A tracking navigation module is used to obtain and track the image of the current visitor in the park, and determine the position of the current visitor's image in the park based on the image of the current visitor tracked in the park. If the current visitor's position in the park is not on the navigation path, the navigation path between the current visitor and the owner's address is regenerated based on the current visitor's position in the park, and the path direction is indicated by an indication device preset on the roadside of the park.

[0040] Specifically, a camera can be used to obtain images of the current visitor in the park. Multiple cameras can be set up, and their monitoring areas can cover different areas in the park. The images of the current visitor in the park obtained by the camera can be transmitted to the system placed in the background server, and the tracking navigation module analyzes these images.

[0041] Specifically, the method in which the tracking navigation module determines the position of the current visitor image in the park based on tracking the image of the current visitor in the park includes:

[0042] Extract the target features of the current visitor image obtained by the acquisition module. For example, if the acquisition module obtains the facial image of the current visitor, a convolutional neural network can be used to extract the target features of the facial image of the current visitor to obtain the facial features of the current visitor;

[0043] Identify the images of the current visitor with the target features in the park, associate each image of the current visitor in the park with the shooting time of the image, and obtain multiple images of the current visitor in the park arranged in time sequence. For example, a face recognition algorithm can be used to identify images taken by cameras from the park entrance to the deepest part of the park. Of course, it is not necessary to traverse all images completely. When it is recognized that there is no target feature of the current visitor in the image taken by the camera at a certain distance from the park entrance, it can be returned and then all images with the target feature of the current visitor can be arranged in time sequence.

[0044] Separate the current visitor from the background in multiple images of the current visitor in the park, using a fixed background extraction algorithm or an inter-frame difference method, etc.;

[0045] Based on the preset correspondence between the background scene in the image of the park and the location in the electronic map of the park, multiple images of the current visitor in the park arranged in time sequence are analyzed to obtain the corresponding movement trajectory and final location of the current visitor in the electronic map of the park.

[0046] Since the identity of visitors to the park is uncertain, if a UWB positioning system or Bluetooth positioning system is deployed in the park, it is necessary to issue UWB positioning badges or Bluetooth tags to visitors, and it is also necessary to install UWB positioning base stations or Bluetooth positioning beacons in the park, which increases costs. Existing office parks or industrial parks generally have cameras installed, so locating visitors in the park based on existing cameras can reduce hardware costs. In addition, there is no need for security personnel to issue temporary badges or tags to visitors, reducing entry procedures.

[0047] If the current visitor's location in the park is not on the initially generated navigation path, it means that there is an error in the current visitor's walking route, and he needs help to correct it. However, it is impossible for property management personnel to remember the visit information of each visitor, nor is it possible to pay attention to the location of each visitor through the monitoring screen in real time. Therefore, it is impossible to immediately discover and provide help when there is an error in the visitor's walking route. The system can regenerate the navigation path from the current visitor's location in the park to the owner's address, and indicate the path direction through the indicator device preset on the roadside of the park, so as to quickly provide the visitor with path guidance. The tracking navigation module here regenerates the navigation path, and the method of controlling the indicator device to indicate the path direction is basically the same as that of the path navigation module.

[0048] In the above embodiment, since the park entrance and the owner's address are fixed, the path navigation can be generated in real time according to the arrival time of the visitor. At the same time, the indicator device set at the intersection in the park can intuitively and conveniently guide the visitor to walk. In addition, with the help of the real-time image of the visitor in the park, the visitor's position in the park can be located in real time. When the visitor's walking path deviates from the initial navigation path, the visitor can be quickly re-navigated and guided again with the help of the indicator device. It avoids visitors taking out their mobile phones to check the map repeatedly, or repeatedly looking for staff in the park to ask for directions, which not only improves the visitor's experience in the last leg of the trip, but also saves the visitor's time, and at the same time, there is no need for the owner to send reception staff to guide.

[0049] In another embodiment, if the target feature in the image tracking the current visitor in the park disappears, the position of the current visitor in the electronic map of the park at the next moment is predicted using an autoregressive algorithm based on the movement trajectory of the current visitor in the electronic map of the park, as follows:

[0050]

[0051] Where, X t is the predicted position at the next moment, c is a constant term, and p is the order of the model, indicating that too few past moments are used. is the parameter of the model, representing the weight of the i-th past moment, X t-i is the position of the i-th past moment, ε t is the error term, which represents the random fluctuations of the model.

[0052] Specifically, p is determined by information criterion or cross-validation method, Determined using the least squares method or maximum likelihood method.

[0053] Here, the disappearance of the target features in the images of the current visitor in the park means that after a preset time from the last moment, the images obtained by all cameras in the park are traversed and the target features of the current visitor are not recognized.

[0054] In the above embodiment, the current visitor may be lost due to obstruction by cars or other temporary facilities in the park. Generally, if there is no emergency, the visitor will reappear in the monitoring screen of the park camera after a few seconds. If the visitor does not appear in the monitoring screen of any park camera for a long time, it means that the visitor may have an emergency and needs to be found and helped immediately. With the help of the autoregressive algorithm in the above embodiment, the position of the current visitor in the electronic map of the park at the next moment is predicted, which can help property staff or owners find the visitor's location more quickly and conveniently.

[0055] In another embodiment, the smart property management system further includes: a notification module, which is used to inform the owner of a visit event through a notification device preset at the owner's address when the current visitor information is consistent with the reserved visitor information.

[0056] Specifically, the notification device is a built-in speaker display, and the notification module is also used to transfer the image of the current visitor in the park obtained by the tracking navigation module to the notification device, and after the target features in the image of the current visitor in the park disappear for a preset period of time, the notification device is used to inform the current visitor of the emergency situation.

[0057] In the above embodiment, since the owner cannot pay attention to the visitor's visit information in real time, nor can he pay attention to the visitor's location in the park in real time, the notification module and notification device can be used to conveniently remind the owner of the visit event so that he can prepare in advance. When the visitor disappears from the image in the park for a preset period of time, it means that the visitor may have an emergency. The owner is informed of the visitor's emergency through the notification device, and the owner can find the visitor in the park more quickly and provide him with help.

[0058] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation modes. They can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the embodiments shown and described herein.

Claims

1. A smart property management system, characterized in that: include: An input module, which is used to obtain owner information, input reserved visitor information and reserved visit time corresponding to the owner information, the owner information including owner name and owner address; An acquisition module is used to acquire the current visitor image, current visitor information, visit information and current visit time; A path navigation module is used to check whether the current visitor information is consistent with the reserved visitor information and whether the current visit time is consistent with the reserved visit time. If they are consistent, a navigation path between the park entrance and the owner's address is generated, and the path direction is indicated by an indicator device preset on the roadside of the park; A tracking navigation module is used to obtain images of the current visitor in the park, and determine the current visitor's position in the park based on the images of the current visitor in the park. If the current visitor's position in the park is not on the navigation path, the navigation path between the current visitor and the owner's address is regenerated based on the current visitor's position in the park, and the path direction is indicated by an indication device preset on the roadside of the park.

2. The smart property management system according to claim 1, characterized in that: There are several indicating devices, each of which is correspondingly arranged at an intersection in the park. The indicating device is an LED electronic road sign or a display or a loudspeaker; when the indicating device is an LED electronic road sign or a display, the way to indicate the path direction is to display the owner's address information and the path direction of the current intersection; when the indicating device is a loudspeaker, the way to indicate the path direction is to play the owner's address information and the path direction of the current intersection.

3. The smart property management system according to claim 1, characterized in that: The navigation path between the park entrance and the owner's address is generated by using one of the Dijkstra algorithm, the A* algorithm, and the Bellman-Ford algorithm.

4. The smart property management system according to claim 1, characterized in that: The method for determining the location of the current visitor in the park based on tracking the image of the current visitor in the park includes: Extracting target features of the current visitor image obtained by the acquisition module; Identify images of current visitors in the park with target features, associate each image of the current visitor in the park with the shooting time of the image, and obtain multiple images of the current visitor in the park arranged in time sequence; Separating a current visitor from a background in a plurality of images of the current visitor in the park; Based on the preset correspondence between the background scene in the image of the park and the location in the electronic map of the park, multiple images of the current visitor in the park arranged in time sequence are analyzed to obtain the corresponding movement trajectory and final location of the current visitor in the electronic map of the park.

5. The smart property management system according to claim 4, characterized in that: If the target feature in the image tracking the current visitor in the park disappears, the autoregressive algorithm is used to predict the location of the current visitor in the electronic map of the park at the next moment according to the movement trajectory of the current visitor in the electronic map of the park, as follows: Where, X t is the predicted position at the next moment, c is a constant term, and p is the order of the model, indicating that too few past moments are used. is the parameter of the model, representing the weight of the i-th past moment, X t-i is the position of the i-th past moment, ε t is the error term, which represents the random fluctuations of the model.

6. The smart property management system according to claim 5, characterized in that: p is determined by information criteria or cross-validation methods, Determined using the least squares method or maximum likelihood method.

7. The smart property management system according to claim 1, characterized in that: Also includes: The notification module is used to notify the owner of a visit event through a notification device preset at the owner's address when the current visitor information is consistent with the reserved visitor information.

8. The smart property management system according to claim 7, characterized in that: The notification device is a built-in speaker display, and the notification module is also used to transfer the image of the current visitor in the park obtained by the tracking navigation module to the notification device, and after the target feature in the image of the current visitor in the park disappears for a preset period of time, the notification device is used to inform the current visitor of the emergency situation.

Images