A campus teaching equipment management classification method and system based on label classification

Abstract

The present invention relates to the field of information technology, and in particular to a campus teaching equipment management classification method and system based on label classification, comprising: constructing an equipment management space based on a campus layout diagram, updating equipment in each sub-management space in the equipment management space according to preset label information, generating a standard management space, processing equipment allocation information of a allocation end in response to a allocation instruction, obtaining a demand allocation interface, allocating equipment to a corresponding standard management space based on the demand allocation interface, acquiring an image group corresponding to each standard management space according to a verification time point, determining an image verification strategy based on image attributes of the image group for verification, obtaining a verification result, the image verification strategy including a combined verification strategy and a single verification strategy, calling an indication model to perform position judgment on an abnormal verification result, generating a quick indication space and sending it to a management end.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a campus teaching equipment management classification method and system based on label classification. Background Art

[0002] With the continuous advancement of educational informatization, the number and types of teaching equipment on campus are increasing, including not only conventional classroom desks and chairs and other infrastructure, but also various high-tech equipment and advanced teaching tools, such as interactive whiteboards, projectors, etc. These devices are key tools in the teaching process.

[0003] At present, due to the lack of effective management measures, the use, maintenance and storage of teaching equipment are not standardized. They are easily lost in the circulation links such as allocation, borrowing and returning, and the loss of teaching equipment cannot be discovered in time. This not only affects the teaching process, but the loss of expensive teaching equipment will also cause additional economic losses to the school.

[0004] Therefore, how to automate the management of teaching equipment and improve management efficiency has become an urgent problem to be solved. Summary of the invention

[0005] The embodiment of the present invention provides a campus teaching equipment management classification method and system based on label classification, which can automatically manage teaching equipment and improve management efficiency.

[0006] In order to solve the above technical problems, a technical solution adopted in the implementation mode of the present invention is: to provide a campus teaching equipment management classification method based on label classification, including: constructing an equipment management space based on a campus layout diagram, updating equipment in each sub-management space in the equipment management space according to preset label information, generating a standard management space, processing the equipment allocation information of the allocation end in response to the allocation instruction, obtaining a demand allocation interface, and allocating equipment to the corresponding standard management space based on the demand allocation interface, obtaining the image group corresponding to each standard management space according to the verification time point, determining the image verification strategy based on the image attributes of the image group for verification, and obtaining the verification result, the image verification strategy includes a combined verification strategy and a single verification strategy, calling the indication model to judge the position of the abnormal verification result, and generating a quick indication space to send to the management end.

[0007] Optionally, the responding to the deployment instruction processes the equipment deployment information of the deployment end to obtain a demand deployment interface, including: responding to the deployment instruction generates an equipment deployment interface according to the equipment deployment information of the deployment end, the equipment deployment interface includes an equipment identification area, an equipment call-out area and an equipment call-in area, receives call-out area configuration information, parses the call-out area configuration information, obtains call-out quantity information and call-out space information, divides the equipment call-out area into regions based on the call-out quantity information, constructs multiple call-out sub-regions, generates call-out identifications for each call-out sub-region based on the call-out space information, The call-out sub-areas are updated one by one according to the call-out identifier to obtain a customized call-out area, the call-in area configuration information is received, the call-in area configuration information is parsed, the call-in quantity information and the call-in space information are obtained, the device call-in area is divided into regions based on the call-in quantity information, a plurality of call-in sub-areas are constructed, a call-in identifier is generated for each call-in sub-area based on the call-in space information, the call-in sub-areas are updated one by one according to the call-in identifier to obtain a customized call-in area, and a demand allocation interface is generated based on the device identification area, the customized call-out area and the customized call-in area.

[0008] Optionally, the device allocation for the corresponding standard management space based on the demand allocation interface includes: responding to a click operation on a customized call-out area in the demand allocation interface, triggering a call-out device tag acquisition request, scanning a preset tag of the device to be allocated according to the call-out device tag acquisition request, acquiring call-out device tag information, calling a preset display database based on the call-out device tag information, generating call-out identification data for the corresponding call-out sub-area according to the preset display database, capturing a user's drag operation based on each call-out identification data, identifying the drag operation, acquiring a mobilization start position and a mobilization end position, associating the mobilization start position with the mobilization end position, generating a mobilization trajectory of the call-out identification data, acquiring a mobilization trajectory set based on multiple mobilization trajectories, generating a mobilization interface based on the mobilization trajectory set, sending the mobilization interface to the management end, receiving a confirmation instruction triggered by the user based on the mobilization interface, and performing device allocation for the corresponding standard management space according to the confirmation instruction.

[0009] Optionally, any two of the multiple maneuvering trajectories are combined to generate multiple maneuvering trajectory groups, the two maneuvering trajectories in each maneuvering trajectory group are identified, the pixel point coordinates corresponding to the two maneuvering trajectories are respectively obtained, a first trajectory pixel point set and a second trajectory pixel point set are obtained based on the pixel point coordinates corresponding to the two maneuvering trajectories, the first trajectory pixel point set is compared with the second trajectory pixel point set, and it is determined whether the first trajectory pixel point set and the second trajectory pixel point set have overlapping pixels, and when the first trajectory pixel point set and the second trajectory pixel point set have overlapping pixels, a de-interference request is received, the overlapping pixels are combined according to the de-interference request, and a trajectory intersection is obtained, an anti-interference line is located based on the trajectory intersection, the anti-interference line in multiple maneuvering trajectory groups is obtained, and the two maneuvering trajectories in each maneuvering trajectory group are associated with the anti-interference line.

[0010] Optionally, the method of obtaining an image group corresponding to each of the standard management spaces according to the verification time point, determining an image verification strategy based on image attributes of the image group for verification, and obtaining a verification result includes: obtaining an image group corresponding to each of the standard management spaces according to the verification time point, identifying the image group, generating an image to be completed according to the image group if a human body exists in any image in the image group, obtaining a human body contour based on the image to be completed, determining a center point of the image to be completed, coordinate processing of the image to be completed based on the center point, obtaining an invalid coordinate set and an invalid area corresponding to the human body contour, obtaining the number of human body contours, processing the number of contours according to a preset matching table, determining a corresponding interval duration, and matching the verification time based on the interval duration. Perform update processing to obtain a filling time, obtain a filled image corresponding to the image to be filled according to the filling time, determine the center point of the filled image, coordinate the filled image based on the center point, locate the invalid coordinate set in the filled image, and obtain a filling judgment area. If there is no human body in the filling judgment area, cut the filling judgment area and fill it to the invalid area, repeat the above steps of filling the invalid area until all invalid areas of the image to be filled are filled, obtain the filled image, perform quantity detection on the filled image, obtain the image acquisition amount, determine the image attributes according to the image acquisition amount, confirm the image verification strategy based on the image attributes, verify according to the image verification strategy, and obtain the verification result.

[0011] Optionally, the image attribute includes a single attribute, and the confirming the image verification strategy based on the image attribute, and performing verification according to the image verification strategy to obtain the verification result includes:

[0012] Based on the single attribute, the image verification strategy is confirmed to be a single verification strategy. According to the single verification strategy, the current image is input into the object detection model for detection, single detection data is obtained, historical data of the previous image group is obtained, the single detection data is compared with the historical data, verification data is obtained, and a verification result is generated based on the verification data.

[0013] Optionally, the image attributes also include combined attributes, and the image verification strategy is confirmed based on the image attributes, and verification is performed according to the image verification strategy to obtain a verification result, including: confirming the image verification strategy as the combined verification strategy based on the combined attributes, identifying the image group according to the combined verification strategy, obtaining a front view image and a rear view image, segmenting the front view image and the rear view image, obtaining a target verification image, inputting the target verification image into an object detection model for detection, obtaining combined detection data, obtaining historical data of the front image group, comparing the combined detection data with the historical data, obtaining verification data, and generating a verification result based on the verification data.

[0014] Optionally, the method includes: classifying the single detection data or combined detection data according to object attributes to obtain fixed detection data and / or active detection data, the fixed detection data includes a fixed image position and a fixed object image, the active detection data includes an active object type and a corresponding number of active objects, acquiring historical fixed data and historical active data of a previous image group, comparing the fixed image position and the fixed object image according to the historical fixed data to obtain fixed verification data, comparing the active object type and the corresponding number of active objects according to the historical activity data to obtain active verification data, and generating a verification result based on the fixed verification data and the active verification data.

[0015] Optionally, the front view image and the rear view image are segmented to obtain a target verification image, and the target verification image is input into an object detection model for detection to obtain combined detection data, including: identifying a front wall outline in the front view image, segmenting the front view image according to the front wall outline to obtain a rear view blind area located inside the front wall outline, and a front view common area located outside the front wall outline, identifying a rear wall outline in the rear view image, segmenting the rear view image according to the rear wall outline to obtain a front view blind area located inside the rear wall outline, and a rear view common area located outside the rear wall outline, and obtaining combined detection data based on the front view common area or the rear view common area, and the rear view blind area and the front view blind area.

[0016] Optionally, the calling of the indication model to perform position judgment on the abnormal verification result, generate a quick indication space and send it to the management end, including: parsing the abnormal verification result to obtain abnormal objects and abnormal quantities, when the abnormal quantity is of an increase type, determining the number of historical objects corresponding to the abnormal objects in the historical image group as the judgment number of the abnormal objects, when the abnormal quantity is of a decrease type, determining the number of historical objects corresponding to the abnormal objects in the historical image group as a basic number, obtaining the judgment number of the abnormal objects according to the difference between the basic number and the reduced number, obtaining the position-identical number corresponding to each abnormal object according to a position comparison relationship between the current image group and the historical image group, and triggering a quick indication request when the position-identical number is consistent with the judgment number, calling the indication model based on the quick indication request, determining the abnormal objects with inconsistent position comparison among the abnormal objects as quick indication objects, and obtaining the object model of the quick indication object and the object position of the object model, performing highlighting and updating processing on the standard management space according to the object model and the object position, generating a quick indication space and sending it to the management end.

[0017] In order to solve the above technical problems, another technical solution adopted by the embodiment of the present invention is: to provide a campus teaching equipment management classification system based on label classification, including: a space construction module, which is used to construct an equipment management space based on a campus layout diagram, and update the equipment of each sub-management space in the equipment management space according to preset label information to generate a standard management space; a deployment processing module, which is used to respond to the deployment instruction to process the equipment deployment information of the deployment end to obtain a demand deployment interface, and deploy equipment for the corresponding standard management space based on the demand deployment interface; a strategy determination module, which is used to obtain the image group corresponding to each standard management space according to the verification time point, determine the image verification strategy based on the image attributes of the image group, and obtain the verification result, wherein the image verification strategy includes a combined verification strategy and a single verification strategy; a position indication module, which calls the indication model to perform position judgment on the abnormal verification result, and generates a quick indication space to send to the management end.

[0018] The beneficial effects of the present invention are as follows:

[0019] The present invention can automatically manage teaching equipment and improve the management efficiency of teaching equipment. The present invention can construct a standard management space so that the acquired teaching equipment can be updated and displayed later, which is convenient for the management personnel to intuitively view and quickly obtain the deployment status of the teaching equipment. The present invention can automatically manage teaching equipment and improve the management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] One or more embodiments are exemplarily described by corresponding drawings, which do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and the figures in the drawings do not constitute proportional limitations unless otherwise stated.

[0021] Figure 1 It is a flow chart of a campus teaching equipment management classification method based on label classification provided in an embodiment of the present application;

[0022] Figure 2 is a schematic diagram of a device management space provided in an embodiment of the present application;

[0023] Figure 3 is a schematic diagram of a mobilization interface provided by an embodiment of the present invention;

[0024] Figure 4 is a schematic diagram of another mobilization interface provided in an embodiment of the present application;

[0025] Figure 5 is a schematic diagram of a teacher provided by an embodiment of the present invention;

[0026] Figure 6 It is a structural diagram of a campus teaching equipment management classification system based on label classification provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0028] It should be noted that, if there is no conflict, the various features in the embodiments of the present invention can be combined with each other, and all are within the protection scope of the present invention. In addition, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a different order from the module division in the device schematic diagram or the order in the flow chart.

[0029] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in sequences other than those illustrated or described herein.

[0030] It should be understood that in the present invention, "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0031] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0032] See also Figure 1 , Figure 1 It is a flow chart of a campus teaching equipment management classification method based on label classification provided by an embodiment of the present application, including steps S1 to S4, which are as follows:

[0033] S1. Construct a device management space based on a campus layout diagram, and perform device updates on each sub-management space in the device management space according to preset tag information to generate a standard management space.

[0034] Among them, the campus layout map is a diagram showing the spatial distribution and relationship of various elements in the campus, including but not limited to information such as the building structure and location distribution of each classroom; the equipment management space is an area for managing teaching equipment established based on equipment management needs, the building structure and location distribution of each classroom, etc.; the preset tag information represents the attribute information carried by the tags pre-set on the teaching equipment; the sub-management space represents the sub-area or sub-space further divided within the equipment management space; the standard management space represents a management area that meets specific standards or specifications.

[0035] Specifically, in order to manage the teaching equipment on campus, it is necessary to determine the equipment management needs based on the campus layout map, that is, to determine the specific scope of teaching equipment management, including which buildings and areas on campus need to manage teaching equipment. For example, if only the teaching equipment of the classroom on the second floor of Teaching Building A needs to be managed, then the equipment management space can be established based on the building structure and location distribution information of the classroom on the second floor of Teaching Building A in the campus layout map.

[0036] Example: See Figure 2 , Figure 2It is a schematic diagram of a device management space provided in an embodiment of the present application. There are 8 classrooms on the second floor of the A teaching building, each classroom corresponds to a sub-management space, and each sub-management space is numbered, namely sub-management space A, sub-management space B, sub-management space C, sub-management space D, sub-management space E, sub-management space F, sub-management space G and sub-management space H.

[0037] At this time, each sub-management space is in the initial state. In order to update the equipment of each sub-management space to reach the standard state, the corresponding scanning label can be set on the surface of each teaching device in advance according to the device attributes. The device attribute is whether the device can be moved. The scanning label represents a specific label attached or implanted on the teaching device, such as a barcode, a QR code, an RFID tag, etc. After completing the corresponding scanning label setting, the corresponding attribute information is obtained by scanning it, including but not limited to the device type, device number, device specifications, and device placement information. According to the obtained attribute information, the equipment of each sub-management space can be updated until each sub-management space reaches the standard state, realizing the generation of multiple standard management spaces.

[0038] For example: School is about to start, and the 8 classrooms on the 2nd floor need to be equipped with equipment. Each classroom is required to be equipped with 30 sets of desks and chairs, 1 podium, a loudspeaker and a blackboard. Take the equipment update of sub-management space A as an example. The teaching equipment in the classroom corresponding to sub-management space A is placed in the preset position. The 30 sets of desks and chairs and the loudspeaker can be moved, which is called arrangable equipment. When setting scanning labels for arrangable equipment, K001, K002, K003... can be used as the equipment number of the arrangable equipment, that is, the first desk uses K001 as the equipment number, the second desk uses K002 as the equipment number, until the equipment number is set for all arrangable equipment. The podium and blackboard have fixed slots, which are called fixed equipment. When setting scanning labels for fixed equipment, G001 can be used as the equipment number of the blackboard and G002 as the equipment number of the podium.

[0039] S2. In response to the deployment instruction, the device deployment information of the deployment end is processed to obtain a demand deployment interface, and the device deployment is performed on the corresponding standard management space based on the demand deployment interface.

[0040] Among them, the deployment instruction represents the instruction issued by the administrator for the deployment of teaching equipment; the deployment end represents the teaching equipment that needs to be deployed; the equipment deployment information represents the specific content contained in the deployment instruction, which describes the specific operations that need to be performed on the teaching equipment; the demand deployment interface is an interface for managing the deployment of teaching equipment generated according to the specific operations required in the equipment deployment information, through which the administrator can perform equipment deployment operations; equipment deployment is the process of moving, updating, adding or deleting teaching equipment on campus according to demand.

[0041] In some embodiments, step S2 (processing the device allocation information of the allocation terminal in response to the allocation instruction to obtain the demand allocation interface) specifically includes steps S20-S25:

[0042] S20. In response to the deployment instruction, generate a device deployment interface according to the device deployment information of the deployment terminal, wherein the device deployment interface includes a device identification area, a device deployment-out area, and a device deployment-in area.

[0043] See also Figure 3 , Figure 3 It is a schematic diagram of a demand allocation interface provided in an embodiment of the present application.

[0044] Among them, the equipment deployment interface, equipment identification area, equipment transfer area, equipment transfer area

[0045] S21. Receive call-out area configuration information, parse the call-out area configuration information, obtain call-out quantity information and call-out space information, divide the device call-out area into regions based on the call-out quantity information, and construct multiple call-out sub-regions.

[0046] Among them, the calling out area configuration information represents, analyzes, calls out quantity information, calls out space information, area division, calls out sub-areas

[0047] S22: Generate a call-out mark for each call-out sub-area based on the call-out space information, and update the call-out sub-areas one by one according to the call-out mark to obtain a customized call-out area.

[0048] Among them, call out identification, one by one update, custom call out area

[0049] S23, receiving the call-in area configuration information, parsing the call-in area configuration information, obtaining the call-in quantity information and the call-in space information, dividing the device call-in area based on the call-in quantity information, and constructing a plurality of call-in sub-areas.

[0050] Among them, the call-in area configuration information is configuration information used to determine which areas the device is called into, parsing refers to the process of analyzing and processing the call-in area configuration information, the call-in quantity information represents the number of devices that need to be called in extracted from the call-in area configuration information; the call-in space information represents the relevant information of the call-in space extracted from the call-in area configuration information, the area division represents the process of dividing the device call-in area according to the call-in quantity information; the call-in sub-area represents each small area obtained in the area division process.

[0051] S24, generating a call-in identifier for each call-in sub-area based on the call-in space information, and updating the call-in sub-areas one by one according to the call-in identifier to obtain a customized call-in area.

[0052] The call-in mark indicates a symbol generated according to the call-in space information for identifying the call-in sub-area, and the one-to-one update indicates updating each call-in sub-area one by one, and the call-in area is obtained after the customized call-in area is updated.

[0053] S25. Generate a demand allocation interface based on the device identification area, the customization call-out area, and the customization call-in area.

[0054] In some embodiments, step S2 (configuring equipment for the corresponding standard management space based on the demand configuration interface) specifically includes steps S26-S29:

[0055] S26, in response to a click operation on the customized call-out area in the demand allocation interface, triggering a call-out device tag acquisition request, scanning a preset tag of the device to be allocated according to the call-out device tag acquisition request, and acquiring the call-out device tag information.

[0056] Click on the operation to call up the device tag acquisition request, scan, preset tags, and call up device tag information.

[0057] S27: calling a preset display database based on the calling-out device tag information, and generating call-out identification data corresponding to the calling-out sub-area according to the preset display database.

[0058] The preset display database refers to a database storing predefined display information.

[0059] S28, capturing the user's dragging operation based on each call-out identification data, identifying the dragging operation, obtaining a mobilization start position and a mobilization end position, associating the mobilization start position and the mobilization end position, generating a mobilization track of the call-out identification data, and obtaining a mobilization track set according to the multiple mobilization tracks.

[0060] Among them, capture, drag operation, identification, mobilization start position, mobilization end position, association, mobilization data, mobilization trajectory collection

[0061] In some embodiments, step S28 (obtaining a set of movement trajectories according to the plurality of movement trajectories) specifically includes steps S281-S284:

[0062] S281. Combining any two of the plurality of movement trajectories to generate a plurality of movement trajectory groups.

[0063] The combination refers to combining multiple objects or elements together to form a new set or group; and the movement trajectory group refers to a set of two movement trajectories.

[0064] Specifically, any two call traces in all call traces are paired to form a call trace group, ensuring that each call trace is paired with the remaining call traces.

[0065] S282: Identify two movement trajectories in each movement trajectory group, respectively obtain pixel point coordinates corresponding to the two movement trajectories, and obtain a first trajectory pixel point set and a second trajectory pixel point set based on the pixel point coordinates corresponding to the two movement trajectories.

[0066] S283, comparing the first trajectory pixel point set with the second trajectory pixel point set, determining whether the first trajectory pixel point set and the second trajectory pixel point set have overlapping pixel points, and when the first trajectory pixel point set and the second trajectory pixel point set have overlapping pixel points, receiving a de-interference request, combining the overlapping pixel points according to the de-interference request, and obtaining a trajectory intersection point.

[0067] Among them, comparison, overlapping pixels, interference removal request, combination, track intersection

[0068] S284: positioning the anti-interference line based on the track intersection, obtaining the anti-interference lines in a plurality of maneuvering track groups, and associating two maneuvering tracks in each maneuvering track group with the anti-interference line.

[0069] S29, generating a mobilization interface based on the mobilization track set, sending the mobilization interface to the management end, receiving a confirmation instruction triggered by the user based on the mobilization interface, and performing equipment deployment on the corresponding standard management space according to the confirmation instruction.

[0070] Among them, the call trajectory set represents a set of trajectory data; the mobilization interface represents the interface for user operation or interaction; the management end represents the management interface of the device deployment system or platform, the trigger represents the action of initiating a deployment event; the confirmation instruction represents the operation of confirming the deployment, and the device deployment represents the process of scheduling the device.

[0071] S3. Acquire the image groups corresponding to the standard management spaces according to the verification time point, determine the image verification strategy based on the image attributes of the image group, and obtain the verification result. The image verification strategy includes a combined verification strategy and a single verification strategy.

[0072] In some embodiments, step S3 (obtaining the image group corresponding to each of the standard management spaces according to the verification time point, determining the image verification strategy based on the image attributes of the image group for verification, and obtaining the verification result) specifically includes steps S31-S34:

[0073] Step S31, obtaining the image group corresponding to each of the standard management spaces according to the verification time, identifying the image group, and if there is a human body in any image in the image group, generating an image to be completed according to the image group, and obtaining the human body contour based on the image to be completed.

[0074] Step S32: determine the center point of the image to be completed, perform coordinate processing on the image to be completed based on the center point, and obtain an invalid coordinate set and an invalid area corresponding to the human body contour.

[0075] Step S33, obtaining the number of contours of the human body, processing the number of contours according to a preset matching table, determining the corresponding interval duration, and updating the verification time based on the interval duration to obtain the completion time.

[0076] Step S34: acquiring a completed image corresponding to the image to be completed according to the completion moment, determining a center point of the completed image, and performing coordinate processing on the completed image based on the center point.

[0077] Step S35: locate the invalid coordinate set in the padded image to obtain a padded judgment area. If no human body exists in the padded judgment area, the padded judgment area is cropped and padded to the invalid area.

[0078] Step S36, repeat the above step of filling the invalid area until all the invalid areas of the image to be filled are filled, and obtain the filled image.

[0079] Step S37, perform quantity detection on the padded images to obtain the image acquisition amount, determine the image attributes according to the image acquisition amount, confirm the image verification strategy based on the image attributes, verify according to the image verification strategy, and obtain the verification result.

[0080] The image attribute includes a single attribute, and the image verification strategy is determined based on the image attribute, and verification is performed according to the image verification strategy to obtain a verification result, including:

[0081] The image verification strategy is confirmed to be a single verification strategy based on the single attribute, and the current image is input into the object detection model for detection according to the single verification strategy to obtain single detection data.

[0082] Acquire historical data of a previous image group, compare the single detection data with the historical data, acquire verification data, and generate a verification result based on the verification data.

[0083] The image attributes further include combined attributes, and the image verification strategy is determined based on the image attributes, and verification is performed according to the image verification strategy to obtain a verification result, including:

[0084] The image verification strategy is confirmed as a combination verification strategy based on the combination attribute, and the image group is identified according to the combination verification strategy to obtain a front view image and a rear view image.

[0085] The front view image and the rear view image are segmented to obtain a target verification image, and the target verification image is input into an object detection model for detection to obtain combined detection data.

[0086] The step of segmenting the front view image and the rear view image to obtain a target verification image, inputting the target verification image into an object detection model for detection, and obtaining combined detection data includes:

[0087] The front wall outline in the front view image is identified, and the front view image is segmented according to the front wall outline to obtain a rear view blind area located inside the front wall outline and a front view common area located outside the front wall outline.

[0088] The rear wall contour in the rear view image is identified, and the rear view image is segmented according to the rear wall contour to obtain a front view blind area located inside the rear wall contour and a rear view common area located outside the rear wall contour.

[0089] Combined detection data is obtained based on the forward vision common area or the rearward vision common area, and the rearward vision blind area and the forward vision blind area.

[0090] Acquire historical data of a previous image group, compare the combined detection data with the historical data, acquire verification data, and generate a verification result based on the verification data.

[0091] Classifying the single detection data or the combined detection data according to the object attributes to obtain fixed detection data and / or active detection data, wherein the fixed detection data includes a fixed image position and a fixed object image, and the active detection data includes an active object type and a corresponding number of active objects;

[0092] Obtaining historical fixed data and historical activity data of a previous image group;

[0093] Comparing the fixed image position with the fixed object image according to the historical fixed data to obtain fixed verification data;

[0094] Comparing the types of active objects and the corresponding numbers of active objects according to the historical activity data to obtain activity verification data;

[0095] A verification result is generated based on the fixed verification data and the active verification data.

[0096] S4. Retrieve the indication model to determine the location of the abnormal verification result, generate a quick indication space and send it to the management end.

[0097] In some embodiments, step S4 (calling the indication model to determine the location of the abnormal verification result, generating a quick indication space and sending it to the management end) specifically includes steps S41-S47:

[0098] S41, analyzing and processing the abnormal verification results to obtain abnormal objects and abnormal quantities.

[0099] S42: When the abnormal number is of an increasing type, determine the number of historical objects corresponding to the abnormal object in the historical image group as the determined number of the abnormal objects.

[0100] S43: When the abnormal number is of a decreasing type, determine the number of historical objects in the historical image group corresponding to the abnormal object as a basic number, and obtain the determined number of the abnormal objects according to a difference between the basic number and the decreasing number.

[0101] S44. Obtain the number of identical positions corresponding to each of the abnormal objects based on a position comparison relationship between the current image group and the historical image group, and trigger a quick indication request when the number of identical positions is consistent with the determined number.

[0102] S45. Retrieve the indication model based on the quick indication request, determine the abnormal objects with inconsistent position comparison among the abnormal objects as quick indication objects, and obtain the object model of the quick indication object and the object position of the object model.

[0103] S46: Perform highlighting and updating processing on the standard management space according to the object model and the object position, generate a quick indication space and send it to the management terminal.

[0104] As shown in the figure, it is a structural diagram of a campus teaching equipment management classification system provided by an embodiment of the present invention, and the campus teaching equipment management classification system includes:

[0105] A space construction module is used to construct a device management space based on a campus layout diagram, and to perform device updates on each sub-management space in the device management space according to preset tag information to generate a standard management space;

[0106] A deployment processing module, used for processing the equipment deployment information of the deployment end in response to the deployment instruction, obtaining a demand deployment interface, and performing equipment deployment on the corresponding standard management space based on the demand deployment interface;

[0107] a strategy determination module, used to obtain the image group corresponding to each of the standard management spaces according to the verification time point, determine the image verification strategy based on the image attributes of the image group, and perform verification to obtain a verification result, wherein the image verification strategy includes a combined verification strategy and a single verification strategy;

[0108] The location indication module calls the indication model to determine the location of the abnormal verification result, generates a quick indication space and sends it to the management end.

[0109] Through the description of the above embodiments, it can be clearly understood by those skilled in the art that each embodiment can be implemented by means of software plus a general hardware platform, or by hardware. It can be understood by those skilled in the art that all or part of the processes in the above embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may also be combined, the steps may be implemented in any order, and there are many other changes in different aspects of the present invention as described above, which are not provided in detail for the sake of simplicity. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person of ordinary skill in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A campus teaching equipment management classification method based on label classification, characterized in that: include: Building a device management space based on the campus layout diagram, and performing device updates on each sub-management space in the device management space according to preset tag information to generate a standard management space; In response to the allocation instruction, the equipment allocation information of the allocation terminal is processed to obtain a demand allocation interface, and equipment allocation is performed on the corresponding standard management space based on the demand allocation interface; Acquire the image groups corresponding to the standard management spaces according to the verification time point, determine the image verification strategy based on the image attributes of the image group to perform verification, and obtain the verification result, wherein the image verification strategy includes a combined verification strategy and a single verification strategy; The indication model is retrieved to determine the location of the abnormal verification result, and a quick indication space is generated and sent to the management end.

2. The campus teaching equipment management classification method based on label classification according to claim 1 is characterized in that: The responding allocation instruction processes the equipment allocation information of the allocation end to obtain a demand allocation interface, including: In response to the deployment instruction, a device deployment interface is generated according to the device deployment information of the deployment terminal, wherein the device deployment interface includes a device identification area, a device call-out area, and a device call-in area; Receiving call-out area configuration information, parsing the call-out area configuration information, obtaining call-out quantity information and call-out space information, dividing the device call-out area into regions based on the call-out quantity information, and constructing a plurality of call-out sub-regions; Generate a call-out mark for each call-out sub-area based on the call-out space information, and update the call-out sub-areas one by one according to the call-out mark to obtain a customized call-out area; Receiving the transfer-in area configuration information, parsing the transfer-in area configuration information, obtaining transfer-in quantity information and transfer-in space information, dividing the device transfer-in area into regions based on the transfer-in quantity information, and constructing a plurality of transfer-in sub-regions; Generate a call-in identifier for each call-in sub-area based on the call-in space information, and update the call-in sub-areas one by one according to the call-in identifier to obtain a customized call-in area; A demand allocation interface is generated based on the device identification area, the customization call-out area, and the customization call-in area.

3. The campus teaching equipment management classification method based on label classification according to claim 2 is characterized in that: The performing equipment allocation on the corresponding standard management space based on the demand allocation interface includes: In response to a click operation on a customized call-out area in the demand allocation interface, a call-out device tag acquisition request is triggered, and a preset tag of the device to be allocated is scanned according to the call-out device tag acquisition request to acquire the call-out device tag information; Based on the label information of the calling-out device, a preset display database is called, and calling-out identification data corresponding to the calling-out sub-area is generated according to the preset display database; Capturing a dragging operation of a user based on each call-out identification data, identifying the dragging operation, obtaining a mobilization start position and a mobilization end position, associating the mobilization start position and the mobilization end position, generating a mobilization track of the call-out identification data, and obtaining a mobilization track set according to the plurality of mobilization tracks; A mobilization interface is generated based on the mobilization track set, the mobilization interface is sent to the management end, a confirmation instruction triggered by a user based on the mobilization interface is received, and equipment is deployed for the corresponding standard management space according to the confirmation instruction.

4. The campus teaching equipment management classification method based on label classification according to claim 3 is characterized in that: The method further comprises: Combining any two of the plurality of mobilization trajectories to generate a plurality of mobilization trajectory groups; Identify two maneuvering trajectories in each maneuvering trajectory group, respectively obtain pixel point coordinates corresponding to the two maneuvering trajectories, and obtain a first trajectory pixel point set and a second trajectory pixel point set based on the pixel point coordinates corresponding to the two maneuvering trajectories; Comparing the first track pixel point set with the second track pixel point set, determining whether the first track pixel point set and the second track pixel point set have overlapping pixel points, and when the first track pixel point set and the second track pixel point set have overlapping pixel points, receiving a de-interference request, combining the overlapping pixel points according to the de-interference request, and obtaining a track intersection point; The anti-interference line is located based on the track intersection, the anti-interference line in a plurality of maneuvering track groups is obtained, and two maneuvering tracks in each maneuvering track group are associated with the anti-interference line.

5. The campus teaching equipment management classification method based on label classification according to claim 1 is characterized in that: The acquiring of the image groups corresponding to the standard management spaces according to the verification time point, determining the image verification strategy based on the image attributes of the image groups for verification, and obtaining the verification results includes: Acquire an image group corresponding to each of the standard management spaces according to the verification time, identify the image group, and if a human body exists in any image in the image group, generate an image to be completed according to the image group, and acquire a human body contour based on the image to be completed; Determine the center point of the image to be completed, perform coordinate processing on the image to be completed based on the center point, and obtain an invalid coordinate set and an invalid area corresponding to the human body contour; Acquire the number of contours of the human body contour, process the number of contours according to a preset matching table, determine the corresponding interval duration, and update the verification time based on the interval duration to obtain the completion time; Acquire a completed image corresponding to the image to be completed according to the completion time, determine the center point of the completed image, and perform coordinate processing on the completed image based on the center point; Positioning the invalid coordinate set in the padded image to obtain a padded judgment area, and if no human body exists in the padded judgment area, cutting the padded judgment area and padded to the invalid area; Repeat the above step of filling the invalid area until all the invalid areas of the image to be filled are filled, and obtain the filled image; Perform quantity detection on the padded images to obtain image acquisition quantity, determine image attributes according to the image acquisition quantity, confirm image verification strategy based on the image attributes, verify according to the image verification strategy, and obtain verification results.

6. The campus teaching equipment management classification method based on label classification according to claim 5 is characterized in that: The image attribute includes a single attribute, and the image verification strategy is determined based on the image attribute, and verification is performed according to the image verification strategy to obtain a verification result, including: Confirming that the image verification strategy is a single verification strategy based on the single attribute, inputting the current image into the object detection model for detection according to the single verification strategy, and obtaining single detection data; Acquire historical data of a previous image group, compare the single detection data with the historical data, acquire verification data, and generate a verification result based on the verification data.

7. The campus teaching equipment management classification method based on label classification according to claim 6 is characterized in that: The image attributes further include combined attributes, and the image verification strategy is determined based on the image attributes, and verification is performed according to the image verification strategy to obtain a verification result, including: confirming that the image verification strategy is a combination verification strategy based on the combination attribute, identifying the image group according to the combination verification strategy, and acquiring a front view image and a rear view image; Segmenting the front view image and the rear view image to obtain a target verification image, inputting the target verification image into an object detection model for detection, and obtaining combined detection data; Acquire historical data of a previous image group, compare the combined detection data with the historical data, acquire verification data, and generate a verification result based on the verification data.

8. The campus teaching equipment management classification method based on label classification according to claim 6 or 7 is characterized in that: The method comprises: Classifying the single detection data or the combined detection data according to the object attributes to obtain fixed detection data and / or active detection data, wherein the fixed detection data includes a fixed image position and a fixed object image, and the active detection data includes an active object type and a corresponding number of active objects; Obtaining historical fixed data and historical activity data of a previous image group; Comparing the fixed image position with the fixed object image according to the historical fixed data to obtain fixed verification data; Comparing the types of active objects and the corresponding numbers of active objects according to the historical activity data to obtain activity verification data; A verification result is generated based on the fixed verification data and the active verification data.

9. The campus teaching equipment management classification method based on label classification according to claim 7 is characterized in that: The step of segmenting the front view image and the rear view image to obtain a target verification image, inputting the target verification image into an object detection model for detection, and obtaining combined detection data includes: Identify the front wall outline in the front view image, and segment the front view image according to the front wall outline to obtain a rear view blind area located inside the front wall outline and a front view common area located outside the front wall outline; Identify the rear wall outline in the rear view image, and segment the rear view image according to the rear wall outline to obtain a front view blind area located inside the rear wall outline and a rear view common area located outside the rear wall outline; Combined detection data is obtained based on the forward vision common area or the rearward vision common area, and the rearward vision blind area and the forward vision blind area.

10. The campus teaching equipment management classification method based on label classification according to claim 8 is characterized in that: The calling indication model determines the position of the abnormal verification result, generates a quick indication space and sends it to the management end, including: Analyze and process the abnormal verification results to obtain abnormal objects and abnormal quantities; When the abnormal number is of an increasing type, determining the number of historical objects corresponding to the abnormal object in the historical image group as the judgment number of the abnormal object; When the abnormal number is of a decreasing type, determining the number of historical objects in the historical image group corresponding to the abnormal object as a basic number, and obtaining the determined number of the abnormal object according to a difference between the basic number and the decreasing number; According to the position comparison relationship between the current image group and the historical image group, the number of identical positions corresponding to each of the abnormal objects is obtained, and when the number of identical positions is consistent with the judged number, a quick indication request is triggered; Retrieving the indication model based on the quick indication request, determining the abnormal object with inconsistent position comparison among the abnormal objects as a quick indication object, and acquiring the object model of the quick indication object and the object position of the object model; According to the object model and the object position, the standard management space is updated with highlighted display, and a quick indication space is generated and sent to the management terminal.

11. A campus teaching equipment management classification system based on label classification, characterized in that: include: A space construction module is used to construct a device management space based on a campus layout diagram, and to perform device updates on each sub-management space in the device management space according to preset tag information to generate a standard management space; A deployment processing module, used for processing the equipment deployment information of the deployment end in response to the deployment instruction, obtaining a demand deployment interface, and performing equipment deployment on the corresponding standard management space based on the demand deployment interface; a strategy determination module, configured to obtain an image group corresponding to each of the standard management spaces according to a verification time point, determine an image verification strategy based on image attributes of the image group, and perform verification to obtain a verification result, wherein the image verification strategy includes a combined verification strategy and a single verification strategy; The location indication module calls the indication model to determine the location of the abnormal verification result, generates a quick indication space and sends it to the management end.

Images