Dormitory management system for smart campus
By integrating monitoring, identification and management modules in the dormitory management system, the number of people in the dormitory is updated and judged in real time, the serious problem of students skipping classes and bedtime under traditional management methods is solved, and management efficiency and accuracy are improved.
Patent Information
- Application Number
- CN202411531158.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-30
- Publication Date
- 2025-02-14
AI Technical Summary
The traditional dormitory management method cannot effectively cover students' life and learning situations, resulting in serious phenomenon of students skipping classes and sleeping, and the workload of managers is large and easy to miss, making it difficult to count the sleeping situation.
Design a dormitory management system for smart campuses, including corridor monitoring module, number of people identification module, number of people management module, feature management module, exception judgment module and exception sending module, to identify the entry and exit of the dormitory through the monitoring screen, and update the actual number of people in real time. And adjust the number of people to be assigned based on the course schedule and leave data, and judge and mark abnormal situations.
It improves the efficiency and accuracy of dormitory management, reduces the workload of managers, and can promptly detect and deal with abnormal situations such as skipping classes and bedtime, ensuring the safety of students and the normal operation of dormitory.
Smart Images
Figure CN119444515A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of smart campus, and in particular to a dormitory management system of a smart campus. Background Art
[0002] The campus is an educational place where students study and live. Many students complete their study, accommodation, meals and other affairs in the school. It is particularly important to manage the campus effectively. The student apartment on campus is an important place for students to live and study. It is the main place for students' belongings and a place with a high population density. The safety of the student apartment is related to everyone's personal and property safety. It must be paid close attention to at all times. A good campus environment is what every student expects and yearns for.
[0003] The traditional way of dormitory inspection is manual inspection by dormitory management personnel. This method has many loopholes in student management and cannot fully cover all aspects of students' life and study. Common problems in student apartment management include: students skipping classes and dormitories are serious, manual dormitory inspections are labor-intensive, easy to miss and disturb students' rest, and it is difficult to count the number of dormitories. Therefore, improving the management ability of student dormitories is an issue that apartment managers need to focus on. Summary of the invention
[0004] The technical problem solved by the present invention is to provide a management system for a smart campus, which can help dormitory managers improve their management capabilities of student dormitories.
[0005] The basic solution provided by the present invention: a dormitory management system for a smart campus, comprising a server, wherein the server comprises a corridor monitoring module, a number recognition module, a number management module, a number judgment module, a feature management module, an abnormality judgment module and an abnormality sending module; Corridor monitoring module, used to obtain monitoring images of dormitory corridors; The number recognition module is used to identify the entry and exit of people in each dormitory based on the corridor monitoring screen, and update the actual number of people in each dormitory in real time based on the entry and exit of people; The number management module is used to obtain the personnel information of each dormitory, determine the time nodes when the number of people in each dormitory will change according to the personnel information, mark them as change nodes, and determine the number of people who should be in the dormitory between each change node; The feature management module is used to identify and extract unique feature information when someone goes out of the dormitory based on the monitoring screen, and bind the feature information to the dormitory. When someone enters the dormitory, it identifies whether the person has unique feature information bound to the dormitory. If not, the dormitory is marked as an outsider. If yes, the unique feature information is cleared. The number determination module is used to determine whether the actual number of people in the current dormitory matches the number of people expected to arrive between the current change node and the next change node at the change node. If not, a number discrepancy mark is added to the dormitory; The abnormality judgment module is used to judge whether there is an abnormality in the dormitory according to whether the dormitory has an outsider mark or a number discrepancy mark, and the time period when the outsider mark or the number discrepancy mark is present; The abnormality sending module is used to send the dormitory number of the corresponding dormitory to the dormitory administrator when an abnormal situation occurs in the dormitory.
[0006] The principle and advantage of the present invention are: in the present application, by shooting the corridor monitoring screen, the entry and exit of the personnel in each dormitory is identified according to the corridor monitoring screen, and the actual number of people in the dormitory is updated in real time according to the entry and exit of the personnel. For example, when there are four people in the dormitory, when it is obtained that one person goes out, the actual number will be updated to three people. According to the personnel information in each dormitory, the time node at which the number of people in each dormitory will change is marked as a change node. For colleges and universities, people from different classes live in different dormitories, and the course schedules of people from different classes are different. In addition, there are also people in the same dormitory, even if the draft courses of the same people are different, so according to the personnel information of the dormitory, the personnel change node is determined. For example, all the staff in a dormitory have classes at 10 o'clock in the morning, classes end at 12 o'clock, lunch breaks at 1 o'clock in the afternoon, and one person has classes at 2 o'clock in the afternoon. For this dormitory, the change nodes are 10 o'clock, 12 o'clock, 1 o'clock and 2 o'clock. The number of people who should be there between 10 o'clock and 12 o'clock is 0, the number of people who should be there from 12 o'clock to 1 o'clock is 0-4, the number of people who should be there from 1 o'clock to 2 o'clock is 4, and the number of people who should be there after 2 o'clock is 0-3. At the same time, the feature management module extracts the unique feature information of the person when someone goes out of the dormitory, and binds the feature information to the dormitory. When someone enters the dormitory, it identifies whether the person has the feature information bound to the dormitory. If so, it means that the person has been out of the dormitory before, if not, it means that the person is not out of the dormitory, and the dormitory is marked with an outsider. Finally, according to whether the dormitory has an outsider mark or a mark that does not match the number of people, and the time period with the outsider mark or the mark that does not match the number of people, it is judged whether the dormitory has an abnormal situation. For example, if someone skips class or escapes from sleep, the actual number of people will not match the number of people who should be there, and when outsiders appear during a period when there is no one in the dormitory, it means that an outsider has broken in and there is an abnormal situation. When there is an abnormal situation, the dormitory administrator will be informed.
[0007] Compared with the existing technology, this solution uses surveillance images to identify the in and out situations of the dormitories to determine whether there are any abnormal situations in each dormitory. Compared with the existing dormitory access control system, there is no need for people to enter and exit by swiping the access control card, and they only need to enter and exit normally, which improves the efficiency of dormitory access. At the same time, compared with the identity authentication method of face recognition, this solution does not need to recognize faces. It only needs to determine the number of people in the dormitory based on the in and out situation, and determine whether the actual number of people matches the number of people who should be present. For personal identification, it is only necessary to identify the unique feature information of the people leaving the dormitory, which reduces the amount of calculation compared with the face recognition method.
[0008] Further, the headcount management module includes a course schedule management module; The course schedule management module is used to obtain the course schedule data of each person in the dormitory, identify the class time of each person in the dormitory, and determine the relevant change nodes according to the class time of each person; The abnormality judgment module is used to judge that an abnormality exists in the dormitory if the actual number of people in the dormitory is higher than the expected number of people when the time period with the number discrepancy mark is a class period.
[0009] According to the class schedule of each person, determine each change node and the number of people who should be present between each change node. At the change node, identify whether the actual number of people and the number of people who should be present are consistent. If the time period when the number of people does not match is during the class period, it means that someone has skipped class, for example, the number of people who should be present is 0, and the actual number is 2, or the number of people who should be present is 0-1, and the actual number is 2. Therefore, it is judged that there is an abnormality and the dormitory administrator is informed.
[0010] Furthermore, the headcount management module also includes a leave management module; The leave management module is used to obtain the leave data of each person in the dormitory, the leave data includes course leave and dormitory leave, and is used to update the number of people who should be present between each change node according to the leave data.
[0011] Update the number of people who should be present according to the leave information. Leave includes dormitory leave and course leave. For example, if someone takes leave for a class, the number of people who should be present in the dormitory during the period of the leave course will increase by one. If it is a dormitory leave, the number of people who should be present between the related change nodes will decrease by one.
[0012] Furthermore, the feature management module includes a feature library module, a feature recognition module and a feature judgment module; The feature library module is used to store the feature information of people going out and the dormitories bound to the feature information; The feature recognition module is used to extract feature information of the person in the monitoring screen that is not in the feature library module when a person goes out of the dormitory, and store the feature information in the feature library module after binding it with the dormitory; The feature judgment module is used to retrieve the feature information bound to the dormitory from the feature library module when a person enters the dormitory, and identify whether the person has the retrieved feature information. If so, the feature information is deleted from the feature library module. If not, an outsider mark is added to the dormitory. The abnormality judgment module is used to judge the actual number of people in the dormitory when there is a mark of an outsider in the dormitory. When the actual number of people is equal to the number of outsiders, it is judged that the dormitory has an abnormal situation; The feature recognition module is also used to identify whether the person has feature information already in the feature library when extracting feature information of the person. If so, multiple feature information is extracted from the person, including first feature information and second feature information, wherein the second feature information is feature information already in the feature library corresponding to the person, and the first feature information is feature information not in the feature library, and the first feature information is associated with the second feature information and bound to the dormitory, and stored in the feature library module; The feature judgment module is used to identify whether the person has the first feature information bound to other dormitories when the feature information bound to a dormitory becomes the second feature information bound to other dormitories. If the feature information is verified, it is judged that there is an abnormal situation when a person enters for verification.
[0013] When a person goes out, feature information that does not exist in the feature library module is extracted from the person. The feature information is specifically identified based on the person's clothing appearance information. For example, person 1 goes out in dormitory A. Person 1 wears a red shirt when going out. There is no feature of a red shirt in the feature library module. The feature information of person 1 is the shirt. After extracting the feature of "red shirt", "red shirt" is bound to dormitory A and added to the feature library. Assume that the features bound to dormitory A include "red shirt" and "black shorts", and the features bound to dormitory B include "red T-shirt" and "white hat". At this time, if person 1 enters dormitory A, it will be verified whether the person has the features of "red shirt" or "black shorts". Since person 1 wears a red shirt and has the features of "red shirt", it means that person 1 came out of dormitory A and there is no abnormality. If person 1 enters dormitory B, it will be verified whether person 1 has the features of "red T-shirt" or "white hat". Since person 1 does not have the corresponding features, it means that the person did not come out of dormitory B. At this time, entering dormitory B is abnormal. When person 1 enters dormitory A, the feature of "red shirt" can be deleted from the feature library so that this feature can be used when other people wear red shirts later.
[0014] At the same time, in order to avoid the problem of repeated features when too many people go out at the same time, for example, there is feature information of black shorts in the feature library, and when person 2 goes out of the dormitory, he also wears black shorts. At this time, if person 2 enters the dormitory bound with the feature information of "black shorts", no exception will be triggered. To avoid this situation, when extracting the feature information of a person, it is identified whether the person has feature information already in the feature library. If so, multiple feature information is extracted for the person, including the first feature information and the second feature information. The second feature information is the feature information already in the feature library corresponding to the person, and the first feature information is the feature information not in the feature library. When person 2 has "black shorts" and the feature library already has the feature of "black shorts", black shorts are extracted from person 2 as the second feature information, and a feature information not in the feature library is extracted from person 2, assuming it is "black frame glasses", and "black frame glasses" is used as the first feature information. At this time, the feature information bound to the dormitory is "black frame glasses + black shorts".
[0015] At this time, the dormitory that was originally bound to the characteristic information of "black shorts" has this characteristic information used as the "second characteristic information" of other dormitories. Therefore, when other people enter the dormitory, if they are verified to have "black shorts", it is also necessary to verify whether the person is wearing "black-framed glasses". If not, there is no abnormality. If so, there is an abnormality.
[0016] Further, the server also includes a dormitory marking module; The dormitory marking module is used to mark the dormitories where the number of people who should attend the class period obtained according to the course schedule data is not 0 or the total number of people in the dormitory is not zero as repeated verification dormitories between the change nodes corresponding to the class period, and to identify the time point when the people in the pending dormitories go out before the change node of the repeated verification dormitory; The abnormality judgment module is used to judge that there is an abnormality in the dormitory when the time point at which the dormitory has people going out is repeatedly verified to be not within the preset range of the change node.
[0017] For example, there are 4 people in a dormitory. Person 1 and Person 2 have classes in a certain period, while Person 3 and Person 4 do not. Therefore, the number of people who should be present in this period is 0-2. However, Person 1 and Person 3 are in the dormitory, while Person 2 and Person 4 are not. As a result, the actual number of people in the dormitory is the same as the number of people who should be present. In this case, the time when the person goes out is identified. For people who have classes, since the teaching building is a certain distance away from the dormitory, they need to go out some time in advance. People who go out usually go out in a fixed time period. For people who do not have classes, the time of going out is more random. Therefore, when it is identified that some people do not go out in a specific period, but the actual number of people in the dormitory meets the number of people who should be present, it is judged that there is an abnormality. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 This is a logical block diagram of an embodiment of a dormitory management system for a smart campus according to the present invention. DETAILED DESCRIPTION
[0019] The following is further described in detail through specific implementation methods: The embodiment is basically as shown in the attached Figure 1 As shown: A dormitory management system for a smart campus includes a server, wherein the server includes a corridor monitoring module, a number recognition module, a number management module, a number judgment module, a feature management module, an abnormality judgment module, and an abnormality sending module; Corridor monitoring module, used to obtain monitoring images of dormitory corridors; The number recognition module is used to identify the entry and exit of people in each dormitory based on the corridor monitoring screen, and update the actual number of people in each dormitory in real time based on the entry and exit of people; The number management module is used to obtain the personnel information of each dormitory, determine the time nodes when the number of people in each dormitory will change according to the personnel information, mark them as change nodes, and determine the number of people who should be in the dormitory between each change node; The feature management module is used to identify and extract unique feature information when someone goes out of the dormitory based on the monitoring screen, and bind the feature information to the dormitory. When someone enters the dormitory, it identifies whether the person has unique feature information bound to the dormitory. If not, the dormitory is marked as an outsider. If yes, the unique feature information is cleared. The number determination module is used to determine whether the actual number of people in the current dormitory matches the number of people expected to arrive between the current change node and the next change node at the change node. If not, a number discrepancy mark is added to the dormitory; The abnormality judgment module is used to judge whether there is an abnormality in the dormitory according to whether the dormitory has an outsider mark or a number discrepancy mark, and the time period when the outsider mark or the number discrepancy mark is present; The abnormality sending module is used to send the dormitory number of the corresponding dormitory to the dormitory administrator when an abnormal situation occurs in the dormitory.
[0020] In this application, by shooting the corridor monitoring screen, the entry and exit of each dormitory is identified according to the corridor monitoring screen, and the actual number of people in the dormitory is updated in real time according to the entry and exit of the personnel. For example, when there are four people in the dormitory, when one person goes out, the actual number will be updated to three. According to the personnel information in each dormitory, the time node at which the number of people in each dormitory will change is marked as a change node. For colleges and universities, people from different classes live in different dormitories, and the course schedules of people from different classes are different. There are also people in the same dormitory, even if the draft courses of the same people are different, so according to the personnel information of the dormitory, the personnel change node is determined. For example, all the staff in a dormitory have classes at 10 o'clock in the morning, and classes end at 12 o'clock. There is a lunch break at 1 o'clock in the afternoon. One person has a class at 2 o'clock in the afternoon. For this dormitory, the change nodes are 10 o'clock, 12 o'clock, 1 o'clock and 2 o'clock. The number of people who should be there between 10 o'clock and 12 o'clock is 0, the number of people who should be there from 12 o'clock to 1 o'clock is 0-4, the number of people who should be there from 1 o'clock to 2 o'clock is 4, and the number of people who should be there after 2 o'clock is 0-3. At the same time, the feature management module extracts the unique feature information of the person when someone goes out of the dormitory, and binds the feature information to the dormitory. When someone enters the dormitory, it identifies whether the person has the feature information bound to the dormitory. If so, it means that the person has been out of the dormitory before, if not, it means that the person is not out of the dormitory, and the dormitory is marked with an outsider. Finally, according to whether the dormitory has an outsider mark or a mark that does not match the number of people, and the time period with the outsider mark or the mark that does not match the number of people, it is judged whether the dormitory has an abnormal situation. For example, if someone skips class or escapes from sleep, the actual number of people will not match the number of people who should be there, and when outsiders appear during a period when there is no one in the dormitory, it means that an outsider has broken in and there is an abnormal situation. When there is an abnormal situation, the dormitory administrator will be informed.
[0021] In this solution, the dormitory entry and exit conditions are identified through monitoring images to determine whether there are any abnormal conditions in each dormitory. Compared with the existing dormitory access control system, there is no need for people to enter and exit by swiping the access control system. They only need to enter and exit normally, which improves the efficiency of dormitory access. At the same time, compared with the identity authentication method of face recognition, this solution does not require face recognition. It only needs to determine the number of people in the dormitory based on the entry and exit conditions and whether the actual number of people matches the number of people who should be present. For personal identification, it is only necessary to identify the unique feature information of the people leaving the dormitory. Compared with the face recognition method, it reduces the amount of calculation.
[0022] The number management module includes a course schedule management module; The course schedule management module is used to obtain the course schedule data of each person in the dormitory, identify the class time of each person in the dormitory, and determine the relevant change nodes according to the class time of each person; The abnormality judgment module is used to judge that an abnormality exists in the dormitory if the actual number of people in the dormitory is higher than the expected number of people when the time period with the number discrepancy mark is a class period.
[0023] According to the class schedule of each person, determine each change node and the number of people who should be present between each change node. At the change node, identify whether the actual number of people and the number of people who should be present are consistent. If the time period when the number of people does not match is during the class period, it means that someone has skipped class, for example, the number of people who should be present is 0, and the actual number is 2, or the number of people who should be present is 0-1, and the actual number is 2. Therefore, it is judged that there is an abnormality and the dormitory administrator is informed.
[0024] The headcount management module also includes a leave management module; The leave management module is used to obtain the leave data of each person in the dormitory, the leave data includes course leave and dormitory leave, and is used to update the number of people who should be present between each change node according to the leave data.
[0025] Update the number of people who should be present according to the leave information. Leave includes dormitory leave and course leave. For example, if someone takes leave for a class, the number of people who should be present in the dormitory during the period of the leave course will increase by one. If it is a dormitory leave, the number of people who should be present between the related change nodes will decrease by one.
[0026] The feature management module includes a feature library module, a feature recognition module and a feature judgment module; The feature library module is used to store the feature information of people going out and the dormitories bound to the feature information; The feature recognition module is used to extract feature information of the person in the monitoring screen that is not in the feature library module when a person goes out of the dormitory, and store the feature information in the feature library module after binding it with the dormitory; The feature judgment module is used to retrieve the feature information bound to the dormitory from the feature library module when a person enters the dormitory, and identify whether the person has the retrieved feature information. If so, the feature information is deleted from the feature library module. If not, an outsider mark is added to the dormitory. The abnormality judgment module is used to judge the actual number of people in the dormitory when there is a mark of an outsider in the dormitory. When the actual number of people is equal to the number of outsiders, it is judged that the dormitory has an abnormal situation; The feature recognition module is also used to identify whether the person has feature information already in the feature library when extracting feature information of the person. If so, multiple feature information is extracted from the person, including first feature information and second feature information, wherein the second feature information is feature information already in the feature library corresponding to the person, and the first feature information is feature information not in the feature library, and the first feature information is associated with the second feature information and bound to the dormitory, and stored in the feature library module; The feature judgment module is used to identify whether the person has the first feature information bound to other dormitories when the feature information bound to a dormitory becomes the second feature information bound to other dormitories. If the feature information is verified, it is judged that there is an abnormal situation when a person enters for verification.
[0027] When a person goes out, feature information that does not exist in the feature library module is extracted from the person. The feature information is specifically identified based on the person's clothing appearance information. For example, person 1 goes out in dormitory A. Person 1 wears a red shirt when going out. There is no feature of a red shirt in the feature library module. The feature information of person 1 is the shirt. After extracting the feature of "red shirt", "red shirt" is bound to dormitory A and added to the feature library. Assume that the features bound to dormitory A include "red shirt" and "black shorts", and the features bound to dormitory B include "red T-shirt" and "white hat". At this time, if person 1 enters dormitory A, it will be verified whether the person has the features of "red shirt" or "black shorts". Since person 1 wears a red shirt and has the features of "red shirt", it means that person 1 came out of dormitory A and there is no abnormality. If person 1 enters dormitory B, it will be verified whether person 1 has the features of "red T-shirt" or "white hat". Since person 1 does not have the corresponding features, it means that the person did not come out of dormitory B. At this time, entering dormitory B is abnormal. When person 1 enters dormitory A, the feature of "red shirt" can be deleted from the feature library so that this feature can be used when other people wear red shirts later.
[0028] At the same time, in order to avoid the problem of repeated features when too many people go out at the same time, for example, there is feature information of black shorts in the feature library, and when person 2 goes out of the dormitory, he also wears black shorts. At this time, if person 2 enters the dormitory bound with the feature information of "black shorts", no exception will be triggered. To avoid this situation, when extracting the feature information of a person, it is identified whether the person has feature information already in the feature library. If so, multiple feature information is extracted for the person, including the first feature information and the second feature information. The second feature information is the feature information already in the feature library corresponding to the person, and the first feature information is the feature information not in the feature library. When person 2 has "black shorts" and the feature library already has the feature of "black shorts", black shorts are extracted from person 2 as the second feature information, and a feature information not in the feature library is extracted from person 2, assuming it is "black frame glasses", and "black frame glasses" is used as the first feature information. At this time, the feature information bound to the dormitory is "black frame glasses + black shorts".
[0029] At this time, the dormitory that was originally bound to the characteristic information of "black shorts" has this characteristic information used as the "second characteristic information" of other dormitories. Therefore, when other people enter the dormitory, if they are verified to have "black shorts", it is also necessary to verify whether the person is wearing "black-framed glasses". If not, there is no abnormality. If so, there is an abnormality.
[0030] The server also includes a dormitory marking module; The dormitory marking module is used to mark the dormitories where the number of people who should attend the class period obtained according to the course schedule data is not 0 or the total number of people in the dormitory is not zero as repeated verification dormitories between the change nodes corresponding to the class period, and to identify the time point when the people in the pending dormitories go out before the change node of the repeated verification dormitory; The abnormality judgment module is used to judge that there is an abnormality in the dormitory when the time point at which the dormitory has people going out is repeatedly verified to be not within the preset range of the change node.
[0031] For example, there are 4 people in a dormitory. Person 1 and Person 2 have classes in a certain period, while Person 3 and Person 4 do not. Therefore, the number of people who should be present in this period is 0-2. However, Person 1 and Person 3 are in the dormitory, while Person 2 and Person 4 are not. As a result, the actual number of people in the dormitory is the same as the number of people who should be present. In this case, the time when the person goes out is identified. For people who have classes, since the teaching building is a certain distance away from the dormitory, they need to go out some time in advance. People who go out usually go out in a fixed time period. For people who do not have classes, the time of going out is more random. Therefore, when it is identified that some people do not go out in a specific period, but the actual number of people in the dormitory meets the number of people who should be present, it is judged that there is an abnormality.
[0032] The above are only embodiments of the present invention. Common knowledge such as the known specific structures and features in the scheme is not described in detail here. Ordinary technicians in the relevant field are aware of all the common technical knowledge in the technical field to which the invention belongs before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply conventional experimental means before that date. Ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the scope of protection of the present invention, and these will not affect the effect of the implementation of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.
Claims
1. A dormitory management system for a smart campus, characterized by: The server includes a corridor monitoring module, a number recognition module, a number management module, a number judgment module, a feature management module, an abnormality judgment module and an abnormality sending module; Corridor monitoring module, used to obtain monitoring images of dormitory corridors; The number recognition module is used to identify the entry and exit of people in each dormitory based on the corridor monitoring screen, and update the actual number of people in each dormitory in real time based on the entry and exit of people; The number management module is used to obtain the personnel information of each dormitory, determine the time nodes when the number of people in each dormitory will change according to the personnel information, mark them as change nodes, and determine the number of people who should be in the dormitory between each change node; The feature management module is used to identify and extract unique feature information when someone goes out of the dormitory based on the monitoring screen, and bind the feature information to the dormitory. When someone enters the dormitory, it identifies whether the person has unique feature information bound to the dormitory. If not, the dormitory is marked as an outsider. If yes, the unique feature information is cleared. The number determination module is used to determine whether the actual number of people in the current dormitory matches the number of people expected to arrive between the current change node and the next change node at the change node. If not, a number discrepancy mark is added to the dormitory; The abnormality judgment module is used to judge whether there is an abnormality in the dormitory according to whether the dormitory has an outsider mark or a number discrepancy mark, and the time period when the outsider mark or the number discrepancy mark is present; The abnormality sending module is used to send the dormitory number of the corresponding dormitory to the dormitory administrator when there is an abnormal situation in the dormitory; The feature management module includes a feature library module, a feature recognition module and a feature judgment module; The feature library module is used to store the feature information of people going out and the dormitories bound to the feature information; The feature recognition module is used to extract feature information of the person in the monitoring screen that is not in the feature library module when a person goes out of the dormitory, and store the feature information in the feature library module after binding it with the dormitory; The feature judgment module is used to retrieve the feature information bound to the dormitory from the feature library module when a person enters the dormitory, and identify whether the person has the retrieved feature information. If so, the feature information is deleted from the feature library module. If not, an outsider mark is added to the dormitory. The abnormality judgment module is used to judge the actual number of people in the dormitory when there is a mark of an outsider in the dormitory. When the actual number of people is equal to the number of outsiders, it is judged that the dormitory has an abnormal situation; The feature recognition module is also used to identify whether the person has feature information already in the feature library when extracting feature information of the person. If so, multiple feature information is extracted from the person, including first feature information and second feature information, wherein the second feature information is feature information already in the feature library corresponding to the person, and the first feature information is feature information not in the feature library, and the first feature information is associated with the second feature information and bound to the dormitory, and stored in the feature library module; The feature judgment module is used to identify whether the person has the first feature information bound to other dormitories when the feature information bound to a dormitory becomes the second feature information bound to other dormitories. If the feature information is verified, it is judged that there is an abnormal situation when a person enters for verification.
2. According to claim 1, a dormitory management system for a smart campus is characterized in that: The number management module includes a course schedule management module; The course schedule management module is used to obtain the course schedule data of each person in the dormitory, identify the class time of each person in the dormitory, and determine the relevant change nodes and the number of people who should attend between each change node according to the class time of each person; The abnormality judgment module is used to judge that an abnormality exists in the dormitory if the actual number of people in the dormitory is higher than the expected number of people when the time period with the number discrepancy mark is a class period.
3. The dormitory management system for a smart campus according to claim 2 is characterized in that: The headcount management module also includes a leave management module; The leave management module is used to obtain the leave data of each person in the dormitory, the leave data includes course leave and dormitory leave, and is used to update the number of people who should be present between each change node according to the leave data.
4. The dormitory management system for a smart campus according to claim 1, characterized in that: The server also includes a dormitory marking module; The dormitory marking module is used to mark the dormitories where the number of people who should attend the class period obtained according to the course schedule data is not 0 or the total number of people in the dormitory is not zero as repeated verification dormitories between the change nodes corresponding to the class period, and to identify the time point when the people in the pending dormitories go out before the change node of the repeated verification dormitory; The abnormality judgment module is used to judge that there is an abnormality in the dormitory when the time point at which the dormitory has people going out is repeatedly verified to be not within the preset range of the change node.