Campus hotspot event monitoring method and device, electronic equipment and storage medium

Abstract

The embodiment of the present application provides a kind of campus hotspot event monitoring method, obtains the campus monitoring video to be handled;According to the pre-determined hotspot event component and the campus monitoring video, determine whether there is campus hotspot event in the campus monitoring video;When it is determined that there is the campus hotspot event in the campus monitoring video, then the target video corresponding to the campus hotspot event is extracted and sent to the campus management department.The campus monitoring video and the hotspot event component are used to determine whether there is a campus hotspot event in the campus monitoring video.If there is a campus hotspot event in the campus monitoring video, the campus management department can be prompted, so that the campus management department can know the information of the campus hotspot event in advance, so as to respond reasonably in advance, thereby improving the efficiency of campus event management.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and in particular to a method, device, electronic equipment and storage medium for monitoring campus hot events. Background Art

[0002] Campuses are somewhat closed and collective. With education increasingly valued, incidents occurring on campus can easily become hot topics. Since students are in their developmental stages, rashly associating them with hot topics can negatively impact their physical and mental development. Because incidents occur on campus, relevant personnel are unable to identify hot topics in a timely manner. Due to the rapid development of internet platforms, incidents can become hot topics by the time they are discovered. Consequently, the efficiency of campus incident management is low. Summary of the Invention

[0003] The present invention provides a method for monitoring campus hot events, aiming to address the low efficiency of campus event management in the prior art. Using campus surveillance video and hot event components, the method determines whether a campus hot event exists in the video. If a campus hot event exists in the video, a notification can be sent to the campus processing department, allowing the campus management department to be informed of the campus hot event in advance and to take appropriate measures in advance, thereby improving the efficiency of campus event management.

[0004] In a first aspect, an embodiment of the present invention provides a method for monitoring campus hot events, the method comprising:

[0005] Obtain campus surveillance videos to be processed;

[0006] Determining whether there is a campus hot event in the campus surveillance video based on a predetermined hot event component and the campus surveillance video;

[0007] When it is determined that the campus hot event exists in the campus surveillance video, the target video corresponding to the campus hot event is extracted and sent to the campus management department.

[0008] Optionally, before determining whether a campus hot event exists in the campus surveillance video based on the predetermined hot event component and the campus surveillance video, the method further includes:

[0009] Obtain online hot event data and local hot event data;

[0010] The hot event component is determined according to the online hot event data and the local hot event data.

[0011] Optionally, determining the hot event component according to the online hot event data and the local hot event data includes:

[0012] Performing clustering processing on the online hot event data and the local hot event data to obtain a clustering result;

[0013] Determining candidate hot event components based on the clustering results;

[0014] A principal component analysis is performed on the candidate hot event components to determine a final hot event component.

[0015] Optionally, determining whether a campus hot event exists in the campus surveillance video based on a predetermined hot event component and the campus surveillance video includes:

[0016] Performing event detection on the campus surveillance video to obtain candidate campus events;

[0017] According to the predetermined hot event component and the candidate campus events, it is determined whether there is a campus hot event in the campus surveillance video.

[0018] Optionally, the hot event component is a component at a semantic level, and determining whether a campus hot event exists in the campus surveillance video based on the predetermined hot event component and the candidate campus event includes:

[0019] Performing semantic extraction on the candidate campus event to obtain semantic information of the candidate campus event;

[0020] Matching the hot event component with the semantic information at a semantic level to obtain a semantic matching result;

[0021] According to the semantic matching result, it is determined whether there is a campus hot event in the campus surveillance video.

[0022] Optionally, when determining that the campus hot event exists in the campus surveillance video, extracting a target video corresponding to the campus hot event and sending it to a campus management department includes:

[0023] When it is determined that the campus hot event exists in the campus surveillance video, extracting the original video corresponding to the campus hot event from the campus surveillance video;

[0024] Post-processing the original video to obtain a target video corresponding to the campus hot event;

[0025] The target video is sent to the campus administration.

[0026] Optionally, after sending the target video to the campus management department, the method further includes:

[0027] Determine the attributes of the campus hot event;

[0028] Determining a solution for handling the campus hotspot event based on the attributes of the campus hotspot event;

[0029] The treatment plan is sent to the campus administration.

[0030] In a second aspect, an embodiment of the present invention provides a campus hotspot event monitoring device, the device comprising:

[0031] A first acquisition module is used to acquire the campus surveillance video to be processed;

[0032] A first determining module is used to determine whether there is a campus hot event in the campus surveillance video based on a predetermined hot event component and the campus surveillance video;

[0033] The first sending module is used to extract the target video corresponding to the campus hot event and send it to the campus management department when determining that the campus hot event exists in the campus surveillance video.

[0034] In a third aspect, an embodiment of the present invention provides an electronic device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the campus hotspot event monitoring method provided in an embodiment of the present invention are implemented.

[0035] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the campus hotspot event monitoring method provided in the embodiment of the invention are implemented.

[0036] In an embodiment of the present invention, a campus surveillance video to be processed is obtained; based on a predetermined hot event component and the campus surveillance video, it is determined whether there is a campus hot event in the campus surveillance video; when it is determined that the campus hot event exists in the campus surveillance video, a target video corresponding to the campus hot event is extracted and sent to the campus management department. The campus surveillance video and the hot event component are used to determine whether there is a campus hot event in the campus surveillance video. If there is a campus hot event in the campus surveillance video, a prompt can be given to the campus processing department, so that the campus management department can know the information of the campus hot event in advance, so that it can take reasonable measures in advance, thereby improving the efficiency of campus event management. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1 This is a flow chart of a campus hotspot event monitoring method provided by an embodiment of the present invention;

[0039] Figure 2 This is a schematic structural diagram of a campus hotspot event monitoring device provided by an embodiment of the present invention;

[0040] Figure 3 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0042] See Figure 1 , Figure 1 This is a flow chart of a campus hotspot event monitoring method provided by an embodiment of the present invention. Figure 1 As shown, the campus hot event monitoring method includes the following steps:

[0043] 101. Obtain the campus surveillance video to be processed.

[0044] In an embodiment of the present invention, campus surveillance video can be collected by campus surveillance equipment installed on campus. Specifically, campus surveillance equipment can be installed in specific areas on campus, and surveillance video of the specific areas can be collected by the campus surveillance equipment. The surveillance video of all specific areas can be aggregated to obtain the campus surveillance video. The specific areas mentioned above can be campus playgrounds, teaching building corridors, classrooms, etc.

[0045] The above-mentioned campus monitoring equipment can be an intelligent monitoring equipment. After collecting the monitoring video corresponding to a specific area, the intelligent monitoring equipment can perform target detection on each frame image in the monitoring video. If the corresponding target is not detected in the frame image, the corresponding frame image will be stored locally. If the corresponding target is detected in the frame image, the corresponding frame image will be uploaded to the server for storage. In this way, the server storage capacity and data processing capacity can be reduced.

[0046] The above campus hot event monitoring method is applied to a server. After receiving surveillance videos from campus monitoring equipment, the server can aggregate all surveillance videos within a preset time period to obtain a campus surveillance video. For example, all surveillance videos for a given day can be aggregated to obtain the campus surveillance video for that day. The campus surveillance video can include multiple surveillance videos, and specifically, the campus surveillance video can include surveillance videos of specific areas.

[0047] 102. Based on the pre-determined hot event components and the campus surveillance video, determine whether there is a campus hot event in the campus surveillance video.

[0048] In the embodiment of the present invention, the hot event component may be a necessary component constituting a hot event. A hot event may be composed of multiple hot event components. The component of the hot event may be abstract semantic information.

[0049] Specifically, feature extraction can be performed on campus surveillance videos to obtain semantic information of the campus surveillance videos, and the semantic information of the campus surveillance videos can be compared with hot event components to determine whether there are campus hot events in the campus surveillance videos.

[0050] It should be noted that the aforementioned campus hot events only include one or more hot event components, and the campus hot events have not yet become hot events. Specifically, if the aforementioned campus hot events are spread through the Internet platform, they have a high probability of becoming hot events. In this embodiment of the present invention, the aforementioned campus hot events have not yet spread through the Internet platform and have not yet become true hot events.

[0051] 103. When it is determined that there is a campus hot event in the campus surveillance video, the target video corresponding to the campus hot event is extracted and sent to the campus management department.

[0052] In an embodiment of the present invention, if it is determined that there is a campus hot event in the campus surveillance video, a target video corresponding to the campus hot event can be sent to the campus management department so that the campus management department can take corresponding management measures based on the target video, such as eliminating the adverse effects that may be caused by the campus hot event.

[0053] In a possible embodiment, when it is determined that there is a campus hot event in the campus surveillance video, a target video corresponding to the campus hot event can be extracted from the campus surveillance video, and target detection can be performed on the target video to determine whether there is a shooter in the campus hot event. If there is a shooter, the identity information of the shooter is identified through personnel recognition technology, and the target video and the identity information of the shooter are sent to the campus management department. If there is no shooter, the target video is sent to the campus management department.

[0054] In an embodiment of the present invention, a campus surveillance video to be processed is obtained; based on a predetermined hot event component and the campus surveillance video, it is determined whether there is a campus hot event in the campus surveillance video; when it is determined that the campus hot event exists in the campus surveillance video, a target video corresponding to the campus hot event is extracted and sent to the campus management department. The campus surveillance video and the hot event component are used to determine whether there is a campus hot event in the campus surveillance video. If there is a campus hot event in the campus surveillance video, a prompt can be given to the campus processing department, so that the campus management department can know the information of the campus hot event in advance, so that it can take reasonable measures in advance, thereby improving the efficiency of campus event management.

[0055] Optionally, before determining whether there is a campus hot event in the campus surveillance video based on the predetermined hot event component and the campus surveillance video, online hot event data and local hot event data can also be obtained; and the hot event component can be determined based on the online hot event data and the local hot event data.

[0056] In an embodiment of the present invention, the above-mentioned online hot event data and local hot event data can be hot event data in any data form, such as video form, text form, audio form, graphic form, etc.

[0057] Specifically, crawler technology can be used to obtain hot event data on online internet platforms, such as content platforms with a large user base. Local hot event data can also be collected through local traditional media, such as local newspapers, local broadcasts, and local news channels.

[0058] After obtaining the online hot event data and the local hot event data, a big data analysis method can be used to analyze the online hot event data and the local hot event data to obtain the hot event components. The big data analysis method can be cluster analysis, factor analysis, correlation analysis, correspondence analysis, etc.

[0059] Cluster analysis is the process of grouping sets of physical or abstract objects into clusters of similar objects. Clustering is the process of categorizing data into classes or clusters, so that objects within the same cluster have significant similarities, while objects in different clusters have significant differences. Specifically, cluster analysis categorizes online and local hot event data into classes or clusters, and then identifies the corresponding hot event components based on these classes or clusters.

[0060] Factor analysis is a method for extracting common factors from a group of variables. Specifically, factor analysis is used to extract common factors from online and local hot event data, and then the corresponding hot event components are determined based on these common factors.

[0061] Correlation analysis studies whether dependencies exist between phenomena and explores the direction and degree of correlation for specific dependent phenomena. Specifically, correlation analysis analyzes the dependencies between online and local hot event data, and identifies corresponding hot event components based on these dependencies.

[0062] Correspondence analysis can be understood as revealing the relationships between variables by analyzing interaction summaries composed of qualitative variables. Specifically, multiple candidate components of hot events can be pre-set as qualitative variables to obtain the variable relationships between hot events and candidate components. Based on these variable relationships, the corresponding hot event components can be determined.

[0063] In the server, the above-mentioned big data analysis method can be used to analyze online hot event data and local hot event data to obtain the components of hot events. Generally speaking, if an event contains the components of these hot events, it is more likely to become a hot event.

[0064] Optionally, in the step of determining hot event components based on online hot event data and local hot event data, the online hot event data and local hot event data can be clustered to obtain clustering results; based on the clustering results, candidate hot event components are determined; and principal component analysis is performed on the candidate hot event components to determine the final hot event components.

[0065] In an embodiment of the present invention, after obtaining the online hot event data and the local hot event data, the server may cluster the online hot event data and the local hot event data, dividing the online hot event data and the local hot event data into different classes or clusters, and determining corresponding hot event components based on the different classes or clusters. The above-mentioned classes or clusters are the clustering results.

[0066] Specifically, semantic extraction can be performed on all hot event data in each class or cluster to obtain the corresponding semantic information in each class or cluster as candidate hot event components. The principal component analysis mentioned above can reduce the large number of candidate hot event components to an acceptable number. Specifically, the candidate hot event components corresponding to each class or cluster are used as variables, and a smaller number of important variables are selected through linear transformation as hot event components of the corresponding class or cluster. The hot event components of all classes or clusters are deduplicated to obtain the final hot event components.

[0067] Optionally, in the step of determining whether there is a campus hot event in the campus surveillance video based on predetermined hot event components and campus surveillance videos, event detection can be performed on the campus surveillance video to obtain candidate campus events; based on the predetermined hot event components and candidate campus events, determine whether there is a campus hot event in the campus surveillance video.

[0068] In an embodiment of the present invention, the event detection can be performed based on an existing event detection algorithm. The event detection algorithm configured in the server is used to detect events in campus surveillance videos to obtain candidate campus events. The candidate campus events can be events corresponding to teacher or student activities on campus, such as basketball, running, and calisthenics.

[0069] After obtaining a candidate campus event, the server can analyze the candidate campus event to determine whether the candidate campus event has a predetermined hot event component. If the candidate campus event has a predetermined hot event component, then the candidate campus event has a probability of becoming a hot event. For example, if the candidate campus event is a basketball event corresponding to a basketball activity, and the hot event component is a slam dunk, if the slam dunk hot event component appears in the basketball event, then the basketball event can be determined to be a campus hot event, thereby confirming the presence of a campus hot event in the campus surveillance video. Otherwise, it is determined that no campus hot event exists in the campus surveillance video. For another example, if the candidate campus event is a running event corresponding to a running activity, and the hot event component is a record-breaking running speed, if the running event contains a record-breaking running speed hot event component, then the running event can be determined to be a campus hot event, thereby confirming the presence of a campus hot event in the campus surveillance video. Otherwise, it is determined that no campus hot event exists in the campus surveillance video.

[0070] Optionally, the hot event component is a component at the semantic level. In the step of determining whether there is a campus hot event in the campus surveillance video based on the predetermined hot event component and the candidate campus events, semantic extraction can be performed on the candidate campus events to obtain semantic information of the candidate campus events; the hot event component and the semantic information can be matched at the semantic level to obtain a semantic matching result; based on the semantic matching result, it is determined whether there is a campus hot event in the campus surveillance video.

[0071] In an embodiment of the present invention, a server is provided with a semantic extraction algorithm. After obtaining candidate campus events, the server performs semantic extraction on the candidate campus events using the semantic extraction algorithm to obtain semantic information for each candidate campus event. Semantic information can be understood as a high-level, abstract type of information. Through semantic extraction, hot event components can be compared with candidate campus events.

[0072] It should be noted that online hot event data and local hot event data can be clustered, and semantic extraction can be performed on all hot event data in each class or cluster to obtain the corresponding semantic information in each class or cluster as a candidate hot event component. The hot event component is determined based on the semantic level. Therefore, the candidate campus event can be semantically extracted so that the hot event component and the candidate campus event can be compared and matched at the semantic level to obtain the semantic matching result of the candidate campus event. If the semantic matching result includes the semantic information corresponding to one or more hot event components, the matching result is a successful match. If the semantic matching result does not include the semantic information corresponding to any hot event component, the matching result is a failed match.

[0073] Furthermore, if the semantic matching result of a candidate campus event is a successful match, it means that the candidate campus event includes semantic information corresponding to one or more hot event components, and the candidate campus event can be determined as a campus hot event, thereby confirming the presence of a campus hot event in the campus surveillance video. If the semantic matching result of a candidate campus event is a failed match, it means that the candidate campus event does not include semantic information corresponding to any hot event component, and the candidate campus event can be determined as a non-campus hot event. When all candidate campus events are non-campus hot events, it can be determined that there is no campus hot event in the campus surveillance video.

[0074] Optionally, when it is determined that the campus hot event exists in the campus surveillance video, in the step of extracting the target video corresponding to the campus hot event and sending it to the campus management department, it can be determined that the campus hot event exists in the campus surveillance video, extracting the original video corresponding to the campus hot event from the campus surveillance video; post-processing the original video to obtain the target video corresponding to the campus hot event; and sending the target video to the campus management department.

[0075] In an embodiment of the present invention, when the server determines that there is a campus hot event in the campus video, it uses the campus surveillance video of the candidate campus event corresponding to the campus hot event and extracts the video clip of the candidate campus event from the campus surveillance video as the original video corresponding to the campus hot event.

[0076] The above-mentioned post-processing can be to clarify the original video to obtain a target video with clearer pictures, and send the target video to the campus management department so that the campus management department can make corresponding management measures based on the target video, such as eliminating the adverse effects that may be caused by the campus hot event, or making advance preparations for the impact of the campus hot event.

[0077] Optionally, after the step of sending the target video to the campus management department, the attribute of the campus hot event can be determined; according to the attribute of the campus hot event, a processing scheme of the campus hot event is determined; and the processing scheme is sent to the campus management department.

[0078] In the embodiment of the present application, the attribute can be a positive attribute and a negative attribute, the positive attribute indicating that the campus hot event spreads and does not cause negative influence on teachers and students of the school, and the negative attribute indicating that the campus hot event spreads and causes negative influence on teachers and students of the school.

[0079] The server is provided with an emotion recognition algorithm, and the emotion recognition algorithm is used to perform emotion prediction on the campus hot event to obtain the attribute of the campus hot event, the positive emotion corresponding to the positive attribute and the negative emotion corresponding to the negative attribute.

[0080] The server is further provided with a processing scheme of the campus hot event with the negative attribute, and when the attribute of the campus hot event is the negative attribute, the corresponding processing scheme is matched and sent to the campus management department, so that the campus management department can reduce the negative influence of the campus hot event on teachers and students of the school through the processing scheme.

[0081] It should be noted that the campus hot event monitoring method provided by the embodiment of the present application can be applied to intelligent cameras, smart phones, computers, servers and other devices that can perform the campus hot event monitoring method.

[0082] Optionally, please refer to Figure 2 , Figure 2 is a structural schematic diagram of a campus hot event monitoring device provided by the embodiment of the present application, as Figure 2 shown, the device comprises:

[0083] The first acquisition module 201 is configured to acquire a campus monitoring video to be processed.

[0084] The first determination module 202 is configured to determine whether a campus hot event exists in the campus monitoring video according to a pre-determined hot event component and the campus monitoring video.

[0085] The first sending module 203 is configured to extract a target video corresponding to the campus hot event and send the target video to the campus management department when it is determined that the campus hot event exists in the campus monitoring video.

[0086] Optionally, the device further comprises:

[0087] The second acquisition module is configured to acquire online hot event data and local hot event data.

[0088] The second determining module is used to determine the hot event component according to the online hot event data and the local hot event data.

[0089] Optionally, the second determining module includes:

[0090] A clustering submodule, configured to perform clustering processing on the online hot event data and the local hot event data to obtain clustering results;

[0091] A first determining submodule is configured to determine candidate hot event components based on the clustering result;

[0092] The second determining submodule is configured to perform principal component analysis on the candidate hot event components to determine a final hot event component.

[0093] Optionally, the first determining module 202 includes:

[0094] A detection submodule, configured to perform event detection on the campus surveillance video to obtain candidate campus events;

[0095] The third determining submodule is configured to determine whether there is a campus hot event in the campus surveillance video according to a predetermined hot event component and the candidate campus event.

[0096] Optionally, the third determining submodule includes:

[0097] An extraction unit, configured to perform semantic extraction on the candidate campus event to obtain semantic information of the candidate campus event;

[0098] A matching unit, configured to match the hot event component with the semantic information at a semantic level to obtain a semantic matching result;

[0099] The determining unit is used to determine whether there is a campus hot event in the campus surveillance video according to the semantic matching result.

[0100] Optionally, the first sending module 203 includes:

[0101] A fourth determining submodule is configured to extract an original video corresponding to the campus hot event from the campus surveillance video when determining that the campus hot event exists in the campus surveillance video;

[0102] A processing submodule, configured to post-process the original video to obtain a target video corresponding to the campus hot event;

[0103] The sending submodule is used to send the target video to the campus management department.

[0104] Optionally, the device further includes:

[0105] A third determining module is used to determine the attributes of the campus hot event;

[0106] A fourth determining module, configured to determine a solution for handling the campus hot event based on the attributes of the campus hot event;

[0107] The second sending module is used to send the processing solution to the campus management department.

[0108] It should be noted that the campus hot event monitoring device provided by the embodiment of the present invention can be applied to smart cameras, smart phones, computers, servers and other devices that can perform campus hot event monitoring methods.

[0109] The campus hot event monitoring device provided by the embodiment of the present invention can implement each process implemented by the campus hot event monitoring method in the above method embodiment and can achieve the same beneficial effects. To avoid repetition, it will not be described here.

[0110] See also Figure 3 , Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, it includes: a memory 302, a processor 301, and a computer program of a campus hotspot event monitoring method stored in the memory 302 and executable on the processor 301, wherein:

[0111] The processor 301 is configured to call the computer program stored in the memory 302 and execute the following steps:

[0112] Obtain campus surveillance videos to be processed;

[0113] Determining whether there is a campus hot event in the campus surveillance video based on a predetermined hot event component and the campus surveillance video;

[0114] When it is determined that the campus hot event exists in the campus surveillance video, the target video corresponding to the campus hot event is extracted and sent to the campus management department.

[0115] Optionally, before determining whether a campus hot event exists in the campus surveillance video based on the predetermined hot event component and the campus surveillance video, the method executed by the processor 301 further includes:

[0116] Obtain online hot event data and local hot event data;

[0117] The hot event component is determined according to the online hot event data and the local hot event data.

[0118] Optionally, the determining of the hot event component according to the online hot event data and the local hot event data performed by the processor 301 includes:

[0119] Performing clustering processing on the online hot event data and the local hot event data to obtain a clustering result;

[0120] Determining candidate hot event components based on the clustering results;

[0121] A principal component analysis is performed on the candidate hot event components to determine a final hot event component.

[0122] Optionally, the processor 301 determines whether a campus hot event exists in the campus surveillance video based on the predetermined hot event component and the campus surveillance video, including:

[0123] Performing event detection on the campus surveillance video to obtain candidate campus events;

[0124] According to the predetermined hot event component and the candidate campus events, it is determined whether there is a campus hot event in the campus surveillance video.

[0125] Optionally, the hot event component executed by the processor 301 is a component at a semantic level, and determining whether a campus hot event exists in the campus surveillance video based on the predetermined hot event component and the candidate campus event includes:

[0126] Performing semantic extraction on the candidate campus event to obtain semantic information of the candidate campus event;

[0127] Matching the hot event component with the semantic information at a semantic level to obtain a semantic matching result;

[0128] According to the semantic matching result, it is determined whether there is a campus hot event in the campus surveillance video.

[0129] Optionally, when the processor 301 determines that the campus hot event exists in the campus surveillance video, extracting a target video corresponding to the campus hot event and sending it to a campus management department includes:

[0130] When it is determined that the campus hot event exists in the campus surveillance video, extracting the original video corresponding to the campus hot event from the campus surveillance video;

[0131] Post-processing the original video to obtain a target video corresponding to the campus hot event;

[0132] The target video is sent to the campus administration.

[0133] Optionally, after sending the target video to the campus management department, the method executed by the processor 301 further includes:

[0134] Determine the attributes of the campus hot event;

[0135] Determining a solution for handling the campus hotspot event based on the attributes of the campus hotspot event;

[0136] The treatment plan is sent to the campus administration.

[0137] The electronic device provided in the embodiment of the present invention can implement each process implemented by the campus hot event monitoring method in the above method embodiment and can achieve the same beneficial effects. To avoid repetition, it will not be described here.

[0138] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the campus hot event monitoring method provided by the embodiment of the present invention are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0139] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware through a computer program. The program can be stored in a computer-readable storage medium, and when executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (RON), or a random access memory (RAN).

[0140] The above disclosure is merely a preferred embodiment of the present invention and certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for monitoring campus hot events, characterized in that: The following steps are involved: Obtain campus surveillance videos to be processed; Determining whether there is a campus hot event in the campus surveillance video based on a predetermined hot event component and the campus surveillance video; When it is determined that the campus hot event exists in the campus surveillance video, a target video corresponding to the campus hot event is extracted and sent to a campus management department; Before determining whether a campus hot event exists in the campus surveillance video based on the predetermined hot event component and the campus surveillance video, the method further includes: Obtain online hot event data and local hot event data; Determining the hot event component according to the online hot event data and the local hot event data; The determining the hot event component according to the online hot event data and the local hot event data includes: Clustering online hot event data and local hot event data to divide online hot event data and local hot event data into different classes or clusters; Perform semantic extraction on all hot event data in each class or cluster, and obtain the corresponding semantic information in each class or cluster as a candidate hot event component; Through principal component analysis, the candidate hot event components corresponding to each class or cluster are used as variables, and a smaller number of important variables are selected as the hot event components of the corresponding class or cluster through linear transformation; the hot event components of all classes or clusters are deduplicated to obtain the final hot event components.

2. The campus hot event monitoring method according to claim 1, wherein: The determining, based on the predetermined hot event component and the campus surveillance video, whether there is a campus hot event in the campus surveillance video includes: Performing event detection on the campus surveillance video to obtain candidate campus events; According to the predetermined hot event component and the candidate campus events, it is determined whether there is a campus hot event in the campus surveillance video.

3. The campus hot event monitoring method according to claim 2, wherein: The hot event component is a component at a semantic level. The determining whether there is a campus hot event in the campus surveillance video based on the predetermined hot event component and the candidate campus event includes: Performing semantic extraction on the candidate campus event to obtain semantic information of the candidate campus event; Matching the hot event component with the semantic information at a semantic level to obtain a semantic matching result; According to the semantic matching result, it is determined whether there is a campus hot event in the campus surveillance video.

4. The campus hot event monitoring method according to claim 3, wherein: When it is determined that the campus hot event exists in the campus surveillance video, extracting a target video corresponding to the campus hot event and sending it to the campus management department includes: When it is determined that the campus hot event exists in the campus surveillance video, extracting the original video corresponding to the campus hot event from the campus surveillance video; Post-processing the original video to obtain a target video corresponding to the campus hot event; The target video is sent to the campus administration.

5. The campus hot event monitoring method according to claim 4, characterized in that: After sending the target video to the campus management department, the method further includes: Determine the attributes of the campus hot event; Determining a solution for handling the campus hotspot event based on the attributes of the campus hotspot event; The treatment plan is sent to the campus administration.

6. A campus hot event monitoring device, characterized in that: The device comprises: A first acquisition module is used to acquire the campus surveillance video to be processed; A first determining module is configured to determine whether a campus hot event exists in the campus surveillance video based on a predetermined hot event component and the campus surveillance video; A first sending module is configured to extract a target video corresponding to the campus hot event and send it to a campus management department when determining that the campus hot event exists in the campus surveillance video; Before determining whether a campus hot event exists in the campus surveillance video based on the predetermined hot event component and the campus surveillance video, the method further includes: The second acquisition module is used to obtain online hot event data and local hot event data; A second determining module is configured to determine the hot event component based on the online hot event data and the local hot event data; The second determining module includes: The clustering submodule is used to cluster the online hot event data and the local hot event data, and divide the online hot event data and the local hot event data into different classes or clusters; The first determination submodule is used to perform semantic extraction on all hot event data in each class or cluster, and obtain the corresponding semantic information in each class or cluster as a candidate hot event component; The second determination submodule is used to use principal component analysis to take the candidate hot event components corresponding to each class or cluster as variables, and to select a smaller number of important variables as the hot event components of the corresponding class or cluster through linear transformation; and to remove duplicates from the hot event components of all classes or clusters to obtain the final hot event components.

7. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the campus hotspot event monitoring method as described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the campus hotspot event monitoring method according to any one of claims 1 to 5.

Images