Intelligent patrol system and method for home-based elderly care

Abstract

The embodiment of the present application discloses a smart patrol system and method for home-based elderly care, which are applied to a control platform device in the smart patrol system for home-based elderly care. The smart patrol system for home-based elderly care also includes: a camera, a proximity sensor, and a positioning sensor. The method includes: monitoring a target object through the camera to obtain a monitoring video; identifying the behavior of the target object through the monitoring video, and when the behavior is walking behavior, determining the target position of the target object through the proximity sensor and the positioning sensor, and identifying the walking direction of the target object through the monitoring video; estimating the walking trajectory of the target object according to the target position and the walking direction; identifying dangerous positions in the walking trajectory, and processing the dangerous positions to ensure the safety of the target object walking along the walking trajectory.

Description

Technical Field

[0001] The present application relates to the field of Internet of Things technology or smart home technology, and specifically to a smart patrol system and method for home-based elderly care. Background Art

[0002] With the development of science and technology, smart homes are gradually entering thousands of households, and smart home care has become a trend of future development, that is, the elderly can live a high-quality and enjoyable old age life at home without being bound by time, geography and other environments. At present, if lonely elderly people fall at home, the consequences are very serious. Therefore, the problem of how to improve the efficiency of elderly care needs to be solved urgently. Summary of the invention

[0003] The embodiments of the present application provide a smart patrol system and method for home-based elderly care, which can improve the efficiency of monitoring the elderly.

[0004] In a first aspect, an embodiment of the present application provides a method for intelligent patrolling of home-based elderly care, which is applied to a control platform device in an intelligent patrolling system of home-based elderly care, wherein the intelligent patrolling system of home-based elderly care further includes: a camera, a proximity sensor, and a positioning sensor, and the method includes:

[0005] The target object is monitored by the camera to obtain a monitoring video;

[0006] identifying the behavior of the target object through the monitoring video, and when the behavior is walking, determining the target position of the target object through the proximity sensor and the positioning sensor, and identifying the walking direction of the target object through the monitoring video;

[0007] estimating the walking trajectory of the target object according to the target position and the walking direction;

[0008] A dangerous position in the walking track is identified and processed to ensure the safety of the target object walking along the walking track.

[0009] In a second aspect, an embodiment of the present application provides a home-based elderly care smart patrol system, which is applied to a control platform device in the home-based elderly care smart patrol system. The home-based elderly care smart patrol system also includes: a camera, a proximity sensor, and a positioning sensor. The system includes:

[0010] The camera is used to monitor the target object to obtain a monitoring video; and identify the behavior of the target object through the monitoring video;

[0011] The proximity sensor and the positioning sensor are used to determine the target position of the target object when the behavior is walking, and to identify the walking direction of the target object through the monitoring video;

[0012] The control platform device is used to estimate the walking trajectory of the target object according to the target position and the walking direction; identify dangerous positions in the walking trajectory, and process the dangerous positions to ensure the safety of the target object walking along the walking trajectory.

[0013] In a third aspect, an embodiment of the present application provides a control platform device, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps in the first aspect of the embodiment of the present application.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the embodiment of the present application.

[0015] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiment of the present application. The computer program product may be a software installation package.

[0016] The implementation of the embodiments of the present application has the following beneficial effects:

[0017] It can be seen that the smart patrol system and method for home-based elderly care described in the embodiments of the present application are applied to the control platform equipment in the smart patrol system for home-based elderly care. The smart patrol system for home-based elderly care also includes: a camera, a proximity sensor, and a positioning sensor. The camera is used to monitor the target object to obtain a monitoring video, and the behavior of the target object is identified through the monitoring video. When the behavior is walking behavior, the target position of the target object is determined by the proximity sensor and the positioning sensor, and the walking direction of the target object is identified through the monitoring video. The walking trajectory of the target object is estimated according to the target position and the walking direction, and the dangerous positions in the walking trajectory are identified and processed to ensure the safety of the target object walking along the walking trajectory. During the user's walking process, the dangerous positions are predicted in advance and processed, thereby ensuring walking safety and improving the efficiency and safety of elderly care. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is a structural diagram of a home-based elderly care intelligent patrol system provided by an embodiment of the present application;

[0020] Figure 2 It is a flowchart of a smart patrol method for home-based elderly care provided by an embodiment of the present application;

[0021] Figure 3 This is a schematic diagram of a scene in a smart patrol method for home-based elderly care provided in an embodiment of the present application;

[0022] Figure 4 This is another schematic diagram of a scenario in a smart patrol method for home-based elderly care provided by an embodiment of the present application;

[0023] Figure 5 It is a structural diagram of a control platform device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0025] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0026] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0027] The control platform device described in the embodiment of the present application may be a server, such as an edge server or a local server. The control platform device may also include other devices.

[0028] The following is a detailed description of the embodiments of the present application.

[0029] See also Figure 1 , Figure 1 This is a structural diagram of a smart patrol system for home-based elderly care provided by an embodiment of the present application. As shown in the figure, the smart patrol system for home-based elderly care includes: a control platform device, a camera, a proximity sensor, and a positioning sensor. Among them, the smart patrol system for home-based elderly care can be set in the elderly care place of the target object, for example, at home. The control platform device is the control center. The number of cameras can be multiple, which can achieve all-weather monitoring. The number of proximity sensors can also be multiple, which are distributed in the user's elderly care place to detect the approach behavior of the target object. The number of positioning sensors can also be multiple, which can be used to achieve positioning.

[0030] Among them, the target object can be a pension object, that is, a user.

[0031] The proximity sensor can be set in different locations, which can include at least one of the following: living room, bedroom, bathroom, kitchen, gym, yard, study, balcony, etc., which are not limited here. Of course, multiple proximity sensors can also be set in the living room.

[0032] The positioning sensor can be set in different locations, which can include at least one of the following: living room, bedroom, bathroom, kitchen, gym, yard, study, balcony, etc., which are not limited here. Of course, multiple positioning sensors can also be set in the living room.

[0033] Among them, the smart patrol system for home-based elderly care may also include other equipment, which may include at least one of the following: smart refrigerators, smart washing machines, sweeping robots, companion robots, smart massage chairs, smart TVs, smart curtains, smart phones, smart cars, smart gateways, smart routers, etc., without limitation here.

[0034] The camera is used to monitor the target object to obtain a monitoring video; and identify the behavior of the target object through the monitoring video;

[0035] The proximity sensor and the positioning sensor are used to determine the target position of the target object when the behavior is walking, and to identify the walking direction of the target object through the monitoring video;

[0036] The control platform device is used to estimate the walking trajectory of the target object according to the target position and the walking direction; identify dangerous positions in the walking trajectory, and process the dangerous positions to ensure the safety of the target object walking along the walking trajectory.

[0037] Optionally, when the dangerous position is an obstacle, in the aspect of identifying the dangerous position in the walking trajectory, the control platform device is specifically used for:

[0038] Acquire a scene image corresponding to the walking trajectory;

[0039] Performing image segmentation on the scene image to obtain multiple targets, each target corresponding to an obstacle;

[0040] Identifying distances between the multiple targets and the walking track to obtain multiple distances;

[0041] Acquire the attribute information of the multiple targets to obtain multiple attribute information;

[0042] Determine a risk factor corresponding to each of the plurality of attribute information to obtain a plurality of risk factors;

[0043] Determine weights corresponding to the multiple distances to obtain multiple weights, wherein the greater the distance, the smaller the weight, and the smaller the distance, the greater the weight;

[0044] Performing a weighted operation according to the multiple risk coefficients and the multiple weights to obtain multiple weighted risk coefficients;

[0045] Determining at least one weighted risk factor among the plurality of weighted risk factors when the weighted risk factor is greater than a first preset threshold;

[0046] A dangerous position corresponding to the at least one weighted dangerous coefficient is obtained.

[0047] Optionally, in the aspect of processing the dangerous location, the control platform device is specifically used for:

[0048] According to the mapping relationship between the preset risk factor and the processing strategy, determining the processing strategy corresponding to the at least one weighted risk factor, and obtaining at least one processing strategy; the processing strategy includes at least one of the following: voice prompt, alarm prompt, moving the target, and focusing on shooting;

[0049] The at least one processing strategy is executed.

[0050] Optionally, when the dangerous position is a ground stain, in the aspect of identifying the dangerous position in the walking track, the control platform device is specifically used for:

[0051] Extracting the ground area of ​​the scene image to obtain a ground area image;

[0052] Segmenting the ground area image into a plurality of areas, each area having a size related to the size of the footprint area of ​​the target object;

[0053] Identify the stain attribute information of each of the multiple regions to obtain multiple stain attribute information, wherein the stain attribute information includes at least one of the following: stain type and stain area;

[0054] Determine the danger level value of each area according to the plurality of stain attribute information to obtain a plurality of danger level values;

[0055] Merging the multiple regions in a nine-square grid format to obtain multiple merged regions, each merged region corresponds to nine regions among the multiple regions, and each merged region is an independent region;

[0056] Determine an average danger level value and a mean square error of each of the plurality of merged regions according to the plurality of danger level values;

[0057] Selecting a merged area whose average danger level value is greater than a second preset threshold and whose mean square error is less than a third preset threshold from the multiple merged areas, to obtain at least one merged area;

[0058] The at least one merged area is identified as the dangerous position, and each merged area corresponds to a dangerous position.

[0059] Optionally, in the aspect of processing the dangerous location, the control platform device is specifically used for:

[0060] Determine the center of each of the at least one merged area, determine the vertical distance between the center and the walking trajectory and the straight-line distance between the center and the target position, and obtain at least one distance pair, each distance pair corresponding to a vertical distance and a straight-line distance;

[0061] Determine an evaluation value of each of the at least one merged area according to the at least one distance pair to obtain at least one reference evaluation value;

[0062] estimating a cleaning time duration of each of the at least one merged area to obtain at least one cleaning time duration;

[0063] Determine a first adjustment coefficient corresponding to the at least one cleaning duration to obtain at least one first adjustment coefficient;

[0064] Determine a corresponding adjustment coefficient according to the average danger level value and the mean square error of each merged area in the at least one merged area to obtain at least one second adjustment coefficient;

[0065] Adjusting the at least one reference evaluation value according to the at least one first adjustment coefficient and the at least one second adjustment coefficient to obtain at least one target evaluation value;

[0066] Determining a cleaning priority order according to the at least one target evaluation value;

[0067] The at least one merged region is cleaned up according to the cleaning priority order.

[0068] Optionally, in the aspect of determining a corresponding adjustment coefficient according to an average danger level value and a mean square error of each merged area in the at least one merged area to obtain at least one second adjustment coefficient, the control platform device is specifically used to:

[0069] Determine a reference adjustment coefficient corresponding to an average danger level value of a merged area i, where the merged area i is any merged area in the at least one merged area;

[0070] Determine an optimization parameter corresponding to the mean square error of the merged region i;

[0071] The reference adjustment coefficient is optimized according to the optimization parameter to obtain a second adjustment coefficient of the merged area i.

[0072] See also Figure 2 , Figure 2 It is a flow chart of a smart patrol method for home-based elderly care provided by an embodiment of the present application, which is applied to a control platform device in a smart patrol system for home-based elderly care. The smart patrol system for home-based elderly care also includes: a camera, a proximity sensor, and a positioning sensor. As shown in the figure, the smart patrol method for home-based elderly care includes:

[0073] 201. Monitor a target object through the camera to obtain a monitoring video.

[0074] In the embodiment of the present application, the camera may include at least one of the following: a visible light camera, an infrared camera, etc., which is not limited here. The camera may also include a single camera or a dual camera.

[0075] In a specific implementation, a camera can be used to monitor a target object to obtain a monitoring video, through which user behavior, user location, user expression, etc. can be identified, which is not limited here.

[0076] 202. Identify the behavior of the target object through the monitoring video. When the behavior is walking, determine the target position of the target object through the proximity sensor and the positioning sensor, and identify the walking direction of the target object through the monitoring video.

[0077] In the embodiment of the present application, the behavior of the target object can be identified through the monitoring video. Specifically, the corresponding behavior can be obtained by identifying the action through the monitoring video. The behavior can include at least one of the following: walking behavior, cooking behavior, reading behavior, tea drinking behavior, exercise behavior, etc., which are not limited here. When the behavior is walking behavior, the target position of the target object is determined by the proximity sensor and the positioning sensor, that is, the positioning sensor can locate the user's indoor position, and the proximity sensor can detect the user's approach behavior, and then use the positioning sensor closest to the proximity sensor to locate the target object. Of course, the orientation of the target object can also be detected by the proximity sensor, and the position of the proximity sensor itself is known. With the help of the position of other positioning sensors, the coordinates of the target object in the room, that is, the target position, can be accurately marked. Furthermore, the walking direction of the target object can also be identified through the monitoring video.

[0078] 203. Estimate a walking trajectory of the target object according to the target position and the walking direction.

[0079] In the embodiment of the present application, since the target position and the walking direction are known, the walking trajectory of the target object can be estimated based on the target position and the walking direction. For example, the trajectory of the preset distance or preset walking duration in the walking direction can be determined as the walking trajectory. The preset distance can be preset or the system defaults, and the preset walking duration can also be preset or the system defaults. Of course, the target walking speed of the target object can be obtained in advance, and the product between the preset walking duration and the target walking speed is used as the walking distance. The walking trajectory can be determined based on the walking distance in the walking direction. The walking trajectory can be a straight line or a curve, which can be determined based on the actual application environment. The specific direction trajectory can be obtained based on the experience of the actual scene. For example, if the user is accustomed to walking in a straight line at a certain position, the walking trajectory is a straight line. If the user is accustomed to walking in a curve at a certain position, the walking trajectory is a curve.

[0080] 204. Identify dangerous positions in the walking trajectory, and process the dangerous positions to ensure safety of the target object walking along the walking trajectory.

[0081] The dangerous location may be a location point or an area.

[0082] In an embodiment of the present application, image recognition technology can be used to identify dangerous positions in the walking trajectory and process the dangerous positions, for example, removing dangerous objects or cleaning stains to ensure the safety of the target object walking along the walking trajectory. In this way, dangerous positions can be predicted in advance while the user is walking and processed, thereby ensuring walking safety and improving the efficiency and safety of elderly care.

[0083] Optionally, when the dangerous position is an obstacle, the above step 204, identifying the dangerous position in the walking trajectory, can be implemented as follows:

[0084] Acquire a scene image corresponding to the walking trajectory;

[0085] Performing image segmentation on the scene image to obtain multiple targets, each target corresponding to an obstacle;

[0086] Identifying distances between the multiple targets and the walking track to obtain multiple distances;

[0087] Acquire the attribute information of the multiple targets to obtain multiple attribute information;

[0088] Determine a risk factor corresponding to each of the plurality of attribute information to obtain a plurality of risk factors;

[0089] Determine weights corresponding to the multiple distances to obtain multiple weights, wherein the greater the distance, the smaller the weight, and the smaller the distance, the greater the weight;

[0090] Performing a weighted operation according to the multiple risk coefficients and the multiple weights to obtain multiple weighted risk coefficients;

[0091] Determining at least one weighted risk factor among the plurality of weighted risk factors when the weighted risk factor is greater than a first preset threshold;

[0092] A dangerous position corresponding to the at least one weighted dangerous coefficient is obtained.

[0093] The obstacles may include at least one of the following: chairs, stools, tables, trash cans, etc., which are not limited here.

[0094] The attribute information may include at least one of the following: object type, object size, object shape, object weight, whether the object is fragile, the number of edges and corners of the object, the material of the object, etc., which are not limited here.

[0095] The first preset threshold may be preset or set by system default.

[0096] In the embodiment of the present application, when the dangerous position is an obstacle, a scene image corresponding to the walking track can be obtained. Specifically, the walking track area can be photographed to obtain a scene image, and then the scene image can be segmented to obtain multiple targets, each target corresponding to an obstacle. The distances between the multiple targets and the walking track can also be identified to obtain multiple distances, such as Figure 3 As shown, the scene image may include a walking track and at least one target. A perpendicular line is drawn from the target to the walking track, which will generate an intersection between the target and the walking track. The distance between the center of the target and the intersection is the distance between the target and the walking track.

[0097] Next, the attribute information of each target among the multiple targets can be obtained to obtain multiple attribute information. Each target corresponds to one attribute information. The mapping relationship between the preset attribute information and the risk factor can be pre-stored. Then, the risk factor corresponding to each attribute information among the multiple attribute information can be determined based on the mapping relationship to obtain multiple risk factors. The mapping relationship between the preset distance and the weight can also be pre-stored. The larger the distance, the smaller the weight, and the smaller the distance, the larger the weight. Then, the weight corresponding to each distance among the multiple distances can be determined based on the mapping relationship to obtain multiple weights. Then, weighted operations are performed according to the multiple risk factors and the multiple weights to obtain multiple weighted risk factors, that is, the risk factor can be multiplied by its corresponding weight to obtain multiple weighted risk factors.

[0098] Furthermore, at least one weighted risk coefficient among multiple weighted risk coefficients that is greater than a first preset threshold value can be determined, and then a dangerous position corresponding to at least one weighted risk coefficient can be obtained. In this way, obstacles with potential dangers can be identified and walking safety can be ensured.

[0099] Optionally, the above step 204, processing the dangerous position, can be implemented in the following manner:

[0100] According to the mapping relationship between the preset risk factor and the processing strategy, determining the processing strategy corresponding to the at least one weighted risk factor, and obtaining at least one processing strategy; the processing strategy includes at least one of the following: voice prompt, alarm prompt, moving the target, and focusing on shooting;

[0101] The at least one processing strategy is executed.

[0102] In an embodiment of the present application, the processing strategy may include at least one of the following: voice prompts, alarm prompts, moving targets, key shots, etc., which are not limited here. The voice prompts can provide voice prompts of the obstacle location, or the distance to the target object. The alarm prompts can be local or remote. The moving target can remove the obstacle with the help of a companion robot. The key shot can capture the target object's walking process in high definition. Even if the user falls, the user's injury level can be identified to a certain extent.

[0103] Optionally, when the dangerous position is a ground stain, the above-mentioned identifying the dangerous position in the walking track includes:

[0104] Extracting the ground area of ​​the scene image to obtain a ground area image;

[0105] Segmenting the ground area image into a plurality of areas, each area having a size related to the size of the footprint area of ​​the target object;

[0106] Identify the stain attribute information of each of the multiple regions to obtain multiple stain attribute information, wherein the stain attribute information includes at least one of the following: stain type and stain area;

[0107] Determine the danger level value of each area according to the plurality of stain attribute information to obtain a plurality of danger level values;

[0108] Merging the multiple regions in a nine-square grid format to obtain multiple merged regions, each merged region corresponds to nine regions among the multiple regions, and each merged region is an independent region;

[0109] Determine an average danger level value and a mean square error of each of the plurality of merged regions according to the plurality of danger level values;

[0110] Selecting a merged area whose average danger level value is greater than a second preset threshold and whose mean square error is less than a third preset threshold from the multiple merged areas to obtain at least one merged area,

[0111] The at least one merged area is identified as the dangerous position, and each merged area corresponds to a dangerous position.

[0112] The second preset threshold value may be preset or set by system default. The third preset threshold value may also be preset or set by system default.

[0113] Among them, different objects have different footprint area sizes. For example, if a user wears size 42 shoes, the area size of size 42 is certain, that is, the mapping relationship between the user's shoe size and the area size can be preset, and then the user's corresponding footprint area can be obtained. For example, the area size can be half of the user's footprint size, or the area size can be 1 / 3 of the user's footprint size.

[0114] The stain attribute information may include at least one of the following: stain type, stain area, stain thickness, stain state, etc., which are not limited here.

[0115] In a specific implementation, the walking track area can be photographed to obtain a scene image, and then the ground area can be extracted from the scene image to obtain a ground area image, that is, only the ground area is focused on, and then the ground area image is divided into multiple areas. The size of each area is related to the size of the footprint area of ​​the target object. Image recognition technology can be used to identify the stain attribute information of each area in the multiple areas to obtain multiple stain attribute information.

[0116] Next, the mapping relationship between the preset stain attribute information and the danger level value can be pre-stored, and then the danger level value of each area can be determined based on the mapping relationship to obtain multiple danger level values, and then the multiple areas are merged in a nine-square grid format to obtain multiple merged areas, each merged area corresponds to nine areas in the multiple areas, and each merged area is an independent area, and the average danger level value and mean square error of each area in the multiple merged areas are determined according to the multiple danger level values. Specifically, 9 danger level values ​​in each merged area can be determined to obtain the average danger level value, and the mean square error is determined based on the 9 danger level values. On the one hand, based on the user's footprints, personalized area division can be performed to identify the stain situation of each area. On the other hand, the adjacent areas can be associated in the form of a nine-square grid, that is, the neighborhood characteristics between areas and the user's personality (footprint size, walking habits) are combined to deeply analyze the danger level of each merged area. After all, during the user's walking process, the actual impact area of ​​the footprints is often related to the depth of the merged area. In addition, even if the user slips, it will be affected by the adjacent areas. In this way, this method deeply identifies the sliding risk during the user's walking process from micro to macro, from area to neighborhood.

[0117] Among them, the average danger level value reflects the overall danger level of the merged area, and the mean square error reflects the influence between neighbors. The smaller the mean square error, the smaller the difference between neighbors, and the larger the mean square error, the larger the difference between neighbors. If the average danger level value is greater than the second preset threshold, it means that the entire merged area is relatively dangerous. If the average danger level value is less than or equal to the second preset threshold, it means that the danger level of the entire merged area is average or not dangerous. If the mean square error is less than the third preset threshold, it means that the difference between neighbors is small and the correlation between neighbors is higher. Conversely, if the mean square error is greater than or equal to the third preset threshold, it means that the correlation between neighbors is weaker.

[0118] Furthermore, a merged area whose average danger level value is greater than the second preset threshold and whose mean square error is less than the third preset threshold can be selected from multiple merged areas to obtain at least one merged area. In this way, a more dangerous area can be selected, and at least one merged area can be identified as a dangerous location. Each merged area corresponds to a dangerous location. In this way, the dangerous location can be identified first, and then the dangerous location can be efficiently processed to ensure safety.

[0119] Optionally, the above step 204, processing the dangerous position, can be implemented in the following manner:

[0120] Determine the center of each of the at least one merged area, determine the vertical distance between the center and the walking trajectory and the straight-line distance between the center and the target position, and obtain at least one distance pair, each distance pair corresponding to a vertical distance and a straight-line distance;

[0121] Determine an evaluation value of each of the at least one merged area according to the at least one distance pair to obtain at least one reference evaluation value;

[0122] estimating a cleaning time duration of each of the at least one merged area to obtain at least one cleaning time duration;

[0123] Determine a first adjustment coefficient corresponding to the at least one cleaning duration to obtain at least one first adjustment coefficient;

[0124] Determine a corresponding adjustment coefficient according to the average danger level value and the mean square error of each merged area in the at least one merged area to obtain at least one second adjustment coefficient;

[0125] Adjusting the at least one reference evaluation value according to the at least one first adjustment coefficient and the at least one second adjustment coefficient to obtain at least one target evaluation value;

[0126] Determining a cleaning priority order according to the at least one target evaluation value;

[0127] The at least one merged region is cleaned up according to the cleaning priority order.

[0128] In the embodiment of the present application, the center of each merged area in at least one merged area can be determined, and then the vertical distance between the center and the walking trajectory and the straight-line distance between the center and the target position can be determined to obtain at least one distance pair, each distance pair corresponding to a vertical distance and a straight-line distance, such as Figure 4 As shown, the scene image may include the current position, the target, and the walking track. Then, a vertical line may be drawn from the target to the walking track. The length of the vertical line is the vertical distance, and the distance between the current position and the center of the target is the straight-line distance. Among them, the smaller the vertical distance, the larger the evaluation value. The larger the vertical distance, the smaller the evaluation value. The larger the straight-line distance, the smaller the evaluation value. The smaller the straight-line distance, the larger the evaluation value. The vertical distance may correspond to a first weight, and the straight-line distance may correspond to a second weight. The first weight + the second weight = 1. The first weight is between 0 and 1, and the second weight is between 0 and 1. Both the first weight and the second weight may be preset or the system defaults.

[0129] Further, the evaluation value of each merged area in at least one merged area is determined based on at least one distance pair to obtain at least one reference evaluation value. Specifically, a first mapping relationship between a preset vertical distance and an evaluation value and a second mapping relationship between a preset straight-line distance and an evaluation value can be pre-stored. Two evaluations corresponding to each distance pair are determined based on the first mapping relationship and the second mapping relationship, and then these two evaluation values ​​are weighted with the first weight and the second weight to obtain a reference evaluation value. The larger the evaluation value, the higher the cleaning priority. Conversely, the smaller the evaluation value, the lower the cleaning priority.

[0130] Next, the cleaning time of each merged area in at least one merged area can be estimated to obtain at least one cleaning time. In a specific implementation, at least one cleaning time can be obtained based on the corresponding cleaning time of the stain type, stain area, stain state, stain thickness, etc. of the merged area. For example, a mapping relationship between preset stain attribute information and cleaning time can be pre-stored, and a corresponding cleaning time can be determined based on the mapping relationship. A mapping relationship between a preset cleaning time and an adjustment coefficient can also be pre-stored, and a first adjustment coefficient corresponding to at least one cleaning time can be determined based on the mapping relationship to obtain at least one first adjustment coefficient, wherein the value range of the adjustment coefficient is 0 to 0.2, and the larger the cleaning time, the smaller the cleaning time. The longer the cleaning time is, the smaller the adjustment coefficient is. Conversely, the shorter the cleaning time is, the larger the adjustment coefficient is. Then, the corresponding adjustment coefficient is determined according to the average danger level value and the mean square error of each merged area in at least one merged area to obtain at least one second adjustment coefficient, and at least one reference evaluation value is adjusted according to at least one first adjustment coefficient and at least one second adjustment coefficient to obtain at least one target evaluation value, that is, the target evaluation value = reference evaluation value * (1 + first adjustment coefficient) * (1 + second adjustment coefficient). Then, the cleaning priority order is determined according to at least one target evaluation value, and at least one merged area is cleaned according to the cleaning priority order. For example, a sweeping robot can be used to clean the merged area. In this way, the smaller the vertical distance, the greater the evaluation value, the larger the vertical distance, the smaller the evaluation value, the larger the straight-line distance, the smaller the evaluation value, and the smaller the straight-line distance, the larger the evaluation value. The cleaning priority can be preliminarily evaluated based on the relative position between the target object and the dangerous position, and then the evaluation value can be deeply adjusted based on the cleaning time, the regional characteristics of the stains, and the neighborhood characteristics, so that the judgment result of the evaluation value is in line with the actual situation, ensuring the cleaning order, and ensuring the rationality and scientificity of the treatment of dangerous positions, thereby ensuring walking safety and improving the efficiency and safety of elderly care.

[0131] Optionally, the above step of determining a corresponding adjustment coefficient according to the average danger level value and the mean square error of each merged area in the at least one merged area to obtain at least one second adjustment coefficient may include the following steps:

[0132] Determine a reference adjustment coefficient corresponding to an average danger level value of a merged area i, where the merged area i is any merged area in the at least one merged area;

[0133] Determine an optimization parameter corresponding to the mean square error of the merged region i;

[0134] The reference adjustment coefficient is optimized according to the optimization parameter to obtain a second adjustment coefficient of the merged area i.

[0135] Among them, the average risk level and mean square error reflect the risk level to a certain extent.

[0136] In the embodiment of the present application, taking the merged area i as an example, the merged area i is any merged area in at least one merged area, and the mapping relationship between the preset danger level value and the adjustment coefficient can be pre-stored. The larger the danger level value, the larger the adjustment coefficient. Then, the reference adjustment coefficient corresponding to the average danger level value of the merged area i can be determined based on the mapping relationship. The mapping relationship between the preset mean square error and the optimization parameter can also be pre-stored. The larger the mean square error, the larger the optimization coefficient, which means that the consistency between the neighbors in the merged area is poor, that is, the difference in stains is large and it is more difficult to clean; the smaller the mean square error, the larger the optimization coefficient. The smaller it is, that is, the larger the mean square error is, the better the consistency between the neighbors in the merged area, that is, the difference in stains is not large, and they can be cleaned in a concentrated mode to improve the cleaning efficiency. The value range of the optimization coefficient can be 0-0.05. Furthermore, the optimization parameter corresponding to the mean square error of the merged area i can be determined based on the mapping relationship, and the reference adjustment coefficient is optimized according to the optimization parameter to obtain the second adjustment coefficient of the merged area i. The second adjustment coefficient = (1+optimization parameter) * reference adjustment coefficient. In this way, the evaluation value of each area can be deeply adjusted based on the regional characteristics of the stains and the neighborhood characteristics, which is helpful to accurately realize the cleaning priority order.

[0137] It can be seen that the smart patrol method for home-based elderly care described in the embodiment of the present application is applied to the control platform equipment in the smart patrol system for home-based elderly care. The smart patrol system for home-based elderly care also includes: a camera, a proximity sensor, and a positioning sensor. The camera is used to monitor the target object to obtain a monitoring video, and the behavior of the target object is identified through the monitoring video. When the behavior is walking behavior, the target position of the target object is determined by the proximity sensor and the positioning sensor, and the walking direction of the target object is identified through the monitoring video. The walking trajectory of the target object is estimated according to the target position and the walking direction, and the dangerous positions in the walking trajectory are identified and processed to ensure the safety of the target object walking along the walking trajectory. During the user's walking process, the dangerous positions are predicted in advance and processed, thereby ensuring walking safety and improving the efficiency and safety of elderly care.

[0138] In accordance with the above embodiment, please refer to Figure 5 , Figure 5: is a structural diagram of a control platform device provided in an embodiment of the present application. As shown in the figure, the control platform device includes a processor, a memory, a communication interface and one or more programs. The one or more programs are stored in the memory and are configured to be executed by the processor. In the embodiment of the present application, the control platform device is applied to a home-based elderly care smart patrol system. The home-based elderly care smart patrol system includes: the control platform device, a camera, a proximity sensor, and a positioning sensor. The program includes instructions for executing the following steps:

[0139] The target object is monitored by the camera to obtain a monitoring video;

[0140] identifying the behavior of the target object through the monitoring video, and when the behavior is walking, determining the target position of the target object through the proximity sensor and the positioning sensor, and identifying the walking direction of the target object through the monitoring video;

[0141] estimating the walking trajectory of the target object according to the target position and the walking direction;

[0142] A dangerous position in the walking track is identified and processed to ensure the safety of the target object walking along the walking track.

[0143] Optionally, when the dangerous position is an obstacle, in the aspect of identifying the dangerous position in the walking trajectory, the program includes instructions for executing the following steps:

[0144] Acquire a scene image corresponding to the walking trajectory;

[0145] Performing image segmentation on the scene image to obtain multiple targets, each target corresponding to an obstacle;

[0146] Identifying distances between the multiple targets and the walking track to obtain multiple distances;

[0147] Acquire the attribute information of the multiple targets to obtain multiple attribute information;

[0148] Determine a risk factor corresponding to each of the plurality of attribute information to obtain a plurality of risk factors;

[0149] Determine weights corresponding to the multiple distances to obtain multiple weights, wherein the greater the distance, the smaller the weight, and the smaller the distance, the greater the weight;

[0150] Performing a weighted operation according to the multiple risk coefficients and the multiple weights to obtain multiple weighted risk coefficients;

[0151] Determining at least one weighted risk factor among the plurality of weighted risk factors when the weighted risk factor is greater than a first preset threshold;

[0152] A dangerous position corresponding to the at least one weighted dangerous coefficient is obtained.

[0153] Optionally, in the aspect of processing the hazardous location, the program includes instructions for performing the following steps:

[0154] According to the mapping relationship between the preset risk factor and the processing strategy, determining the processing strategy corresponding to the at least one weighted risk factor, and obtaining at least one processing strategy; the processing strategy includes at least one of the following: voice prompt, alarm prompt, moving the target, and focusing on shooting;

[0155] The at least one processing strategy is executed.

[0156] Optionally, when the dangerous position is a ground stain, in the aspect of identifying the dangerous position in the walking trajectory, the program includes instructions for executing the following steps:

[0157] Extracting the ground area of ​​the scene image to obtain a ground area image;

[0158] Segmenting the ground area image into a plurality of areas, each area having a size related to the size of the footprint area of ​​the target object;

[0159] Identify the stain attribute information of each of the multiple regions to obtain multiple stain attribute information, wherein the stain attribute information includes at least one of the following: stain type and stain area;

[0160] Determine the danger level value of each area according to the plurality of stain attribute information to obtain a plurality of danger level values;

[0161] Merging the multiple regions in a nine-square grid format to obtain multiple merged regions, each merged region corresponds to nine regions among the multiple regions, and each merged region is an independent region;

[0162] Determine an average danger level value and a mean square error of each of the plurality of merged regions according to the plurality of danger level values;

[0163] Selecting a merged area whose average danger level value is greater than a second preset threshold and whose mean square error is less than a third preset threshold from the multiple merged areas, to obtain at least one merged area;

[0164] The at least one merged area is identified as the dangerous position, and each merged area corresponds to a dangerous position.

[0165] Optionally, in the aspect of processing the hazardous location, the program includes instructions for performing the following steps:

[0166] Determine the center of each of the at least one merged area, determine the vertical distance between the center and the walking trajectory and the straight-line distance between the center and the target position, and obtain at least one distance pair, each distance pair corresponding to a vertical distance and a straight-line distance;

[0167] Determine an evaluation value of each of the at least one merged area according to the at least one distance pair to obtain at least one reference evaluation value;

[0168] estimating a cleaning time duration of each of the at least one merged area to obtain at least one cleaning time duration;

[0169] Determine a first adjustment coefficient corresponding to the at least one cleaning duration to obtain at least one first adjustment coefficient;

[0170] Determine a corresponding adjustment coefficient according to the average danger level value and the mean square error of each merged area in the at least one merged area to obtain at least one second adjustment coefficient;

[0171] Adjusting the at least one reference evaluation value according to the at least one first adjustment coefficient and the at least one second adjustment coefficient to obtain at least one target evaluation value;

[0172] Determining a cleaning priority order according to the at least one target evaluation value;

[0173] The at least one merged region is cleaned up according to the cleaning priority order.

[0174] Optionally, in the aspect of determining a corresponding adjustment coefficient according to the average danger level value and the mean square error of each merged area in the at least one merged area to obtain at least one second adjustment coefficient, the program includes instructions for executing the following steps:

[0175] Determine a reference adjustment coefficient corresponding to an average danger level value of a merged area i, where the merged area i is any merged area in the at least one merged area;

[0176] Determine an optimization parameter corresponding to the mean square error of the merged region i;

[0177] The reference adjustment coefficient is optimized according to the optimization parameter to obtain a second adjustment coefficient of the merged area i.

[0178] It can be seen that the control platform device in the smart patrol system for home-based elderly care described in the embodiment of the present application, the smart patrol system for home-based elderly care also includes: a camera, a proximity sensor, and a positioning sensor. The target object is monitored by the camera to obtain a monitoring video, and the behavior of the target object is identified by the monitoring video. When the behavior is walking behavior, the target position of the target object is determined by the proximity sensor and the positioning sensor, and the walking direction of the target object is identified by the monitoring video. The walking trajectory of the target object is estimated according to the target position and the walking direction, the dangerous positions in the walking trajectory are identified, and the dangerous positions are processed to ensure the safety of the target object walking along the walking trajectory. During the user's walking process, the dangerous positions are predicted in advance and processed, thereby ensuring walking safety and improving the efficiency and safety of elderly care.

[0179] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiments.

[0180] The present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps of any method described in the above method embodiment. The computer program product may be a software installation package.

[0181] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0182] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0183] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0184] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0185] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0186] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0187] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0188] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A smart patrol method for home-based elderly care, characterized in that: A control platform device applied to a home-based elderly care smart patrol system, wherein the home-based elderly care smart patrol system further comprises: a camera, a proximity sensor, and a positioning sensor, and the method comprises: The target object is monitored by the camera to obtain a monitoring video; The behavior of the target object is identified through the monitoring video. When the behavior is walking, the target position of the target object is determined through the proximity sensor and the positioning sensor, and the walking direction of the target object is identified through the monitoring video; the positioning sensor locates the user's indoor position, the proximity sensor detects the user's approach behavior, and then the positioning sensor closest to the proximity sensor is used to locate the target object; The walking trajectory of the target object is estimated according to the target position and the walking direction, and the preset distance in the walking direction is determined as the walking trajectory, specifically: the target walking speed of the target object is obtained in advance, and the product of the preset walking time and the target walking speed is used as the walking distance. The walking trajectory can be determined based on the walking distance in the walking direction; the direction trajectory is obtained based on the experience learning of the actual scene; Identifying dangerous positions in the walking track and processing the dangerous positions to ensure the safety of the target object walking along the walking track, the processing including: removing dangerous objects or cleaning stains; Wherein, when the dangerous position is an obstacle, the identifying the dangerous position in the walking trajectory includes: Acquire a scene image corresponding to the walking trajectory; Performing image segmentation on the scene image to obtain multiple targets, each target corresponding to an obstacle; Identifying distances between the multiple targets and the walking track to obtain multiple distances; Acquire attribute information of the multiple targets to obtain multiple attribute information; the attribute information includes: object type, object size, object shape, object weight, whether the object is fragile, the number of edges and corners of the object, and the material of the object; Determine a risk factor corresponding to each of the plurality of attribute information to obtain a plurality of risk factors; Determine weights corresponding to the multiple distances to obtain multiple weights, wherein the greater the distance, the smaller the weight, and the smaller the distance, the greater the weight; Performing a weighted operation according to the multiple risk coefficients and the multiple weights to obtain multiple weighted risk coefficients; Determining at least one weighted risk factor among the plurality of weighted risk factors when the weighted risk factor is greater than a first preset threshold; Obtaining a dangerous position corresponding to the at least one weighted dangerous coefficient; Wherein, when the dangerous position is a ground stain, the identifying the dangerous position in the walking track includes: Extracting the ground area of ​​the scene image to obtain a ground area image; The ground area image is divided into a plurality of areas, each area size is related to the footprint area size of the target object; each area size is half of the user's footprint size, or each area size is 1 / 3 of the user's footprint size; Identify the stain attribute information of each of the multiple regions to obtain multiple stain attribute information, wherein the stain attribute information includes: stain type and stain area; Determine the danger level value of each area according to the plurality of stain attribute information to obtain a plurality of danger level values; Merging the multiple regions in a nine-square grid format to obtain multiple merged regions, each merged region corresponds to nine regions among the multiple regions, and each merged region is an independent region; Determine an average danger level value and a mean square error of each of the plurality of merged regions according to the plurality of danger level values; Selecting a merged area whose average danger level value is greater than a second preset threshold and whose mean square error is less than a third preset threshold from the multiple merged areas, to obtain at least one merged area; Identify the at least one merged area as the dangerous location, each merged area corresponds to a dangerous location; Wherein, the processing of the dangerous position includes: Determine the center of each of the at least one merged area, determine the vertical distance between the center and the walking trajectory and the straight-line distance between the center and the target position, and obtain at least one distance pair, each distance pair corresponding to a vertical distance and a straight-line distance; Determine an evaluation value of each of the at least one merged area according to the at least one distance pair to obtain at least one reference evaluation value; estimating a cleaning time duration of each of the at least one merged area to obtain at least one cleaning time duration; Determine a first adjustment coefficient corresponding to the at least one cleaning duration to obtain at least one first adjustment coefficient; Determine a corresponding adjustment coefficient according to the average danger level value and the mean square error of each merged area in the at least one merged area to obtain at least one second adjustment coefficient; The at least one reference evaluation value is adjusted according to the at least one first adjustment coefficient and the at least one second adjustment coefficient to obtain at least one target evaluation value, that is, the target evaluation value = reference evaluation value * (1 + first adjustment coefficient) * (1 + second adjustment coefficient); Determining a cleaning priority order according to the at least one target evaluation value; The at least one merged region is cleaned up according to the cleaning priority order.

2. The method according to claim 1, characterized in that The processing of the dangerous position includes: According to the mapping relationship between the preset risk factor and the processing strategy, determining the processing strategy corresponding to the at least one weighted risk factor, and obtaining at least one processing strategy; the processing strategy includes at least one of the following: voice prompt, alarm prompt, moving the target, and focusing on shooting; The at least one processing strategy is executed.

3. The method according to claim 1, characterized in that The step of determining a corresponding adjustment coefficient according to the average danger level value and the mean square error of each merged area in the at least one merged area to obtain at least one second adjustment coefficient comprises: Determine a reference adjustment coefficient corresponding to an average danger level value of a merged area i, where the merged area i is any merged area in the at least one merged area; Determine an optimization parameter corresponding to the mean square error of the merged region i; The reference adjustment coefficient is optimized according to the optimization parameter to obtain a second adjustment coefficient of the merged area i.

4. A smart patrol system for home-based elderly care, characterized in that: A control platform device applied to a home-based elderly care smart patrol system, wherein the home-based elderly care smart patrol system further comprises: a camera, a proximity sensor, and a positioning sensor. The system comprises: The camera is used to monitor the target object and obtain a monitoring video; the behavior of the target object is identified through the monitoring video; the positioning sensor locates the user's indoor position, the proximity sensor detects the user's approach behavior, and then the positioning sensor closest to the proximity sensor is used to locate the target object; The proximity sensor and the positioning sensor are used to determine the target position of the target object when the behavior is walking behavior, identify the walking direction of the target object through the monitoring video, and determine the preset distance in the walking direction as the walking trajectory, specifically: pre-acquire the target walking speed of the target object, take the product of the preset walking time and the target walking speed as the walking distance, and determine the walking trajectory based on the walking distance in the walking direction; the direction trajectory is obtained based on the experience learning of the actual scene; The control platform device is used to estimate the walking trajectory of the target object according to the target position and the walking direction; identify dangerous positions in the walking trajectory, and process the dangerous positions to ensure the safety of the target object walking along the walking trajectory, and the processing includes: removing dangerous objects, or cleaning stains; Wherein, when the dangerous position is an obstacle, in the aspect of identifying the dangerous position in the walking trajectory, the control platform device is specifically used for: Acquire a scene image corresponding to the walking trajectory; Performing image segmentation on the scene image to obtain multiple targets, each target corresponding to an obstacle; Identifying distances between the multiple targets and the walking track to obtain multiple distances; Acquire attribute information of the multiple targets to obtain multiple attribute information; the attribute information includes: object type, object size, object shape, object weight, whether the object is fragile, the number of edges and corners of the object, and the material of the object; Determine a risk factor corresponding to each of the plurality of attribute information to obtain a plurality of risk factors; Determine weights corresponding to the multiple distances to obtain multiple weights, wherein the greater the distance, the smaller the weight, and the smaller the distance, the greater the weight; Performing a weighted operation according to the multiple risk coefficients and the multiple weights to obtain multiple weighted risk coefficients; Determining at least one weighted risk factor among the plurality of weighted risk factors when the weighted risk factor is greater than a first preset threshold; Obtaining a dangerous position corresponding to the at least one weighted danger coefficient; wherein, when the dangerous position is a ground stain, identifying the dangerous position in the walking trajectory includes: Extracting the ground area of ​​the scene image to obtain a ground area image; The ground area image is divided into a plurality of areas, each area size is related to the footprint area size of the target object; each area size is half of the user's footprint size, or each area size is 1 / 3 of the user's footprint size; Identify the stain attribute information of each of the multiple regions to obtain multiple stain attribute information, wherein the stain attribute information includes: stain type and stain area; Determine the danger level value of each area according to the plurality of stain attribute information to obtain a plurality of danger level values; Merging the multiple regions in a nine-square grid format to obtain multiple merged regions, each merged region corresponds to nine regions among the multiple regions, and each merged region is an independent region; Determine an average danger level value and a mean square error of each of the plurality of merged regions according to the plurality of danger level values; Selecting a merged area whose average danger level value is greater than a second preset threshold and whose mean square error is less than a third preset threshold from the multiple merged areas, to obtain at least one merged area; Identify the at least one merged area as the dangerous location, each merged area corresponds to a dangerous location; Wherein, the processing of the dangerous position includes: Determine the center of each of the at least one merged area, determine the vertical distance between the center and the walking trajectory and the straight-line distance between the center and the target position, and obtain at least one distance pair, each distance pair corresponding to a vertical distance and a straight-line distance; Determine an evaluation value of each of the at least one merged area according to the at least one distance pair to obtain at least one reference evaluation value; estimating a cleaning time duration of each of the at least one merged area to obtain at least one cleaning time duration; Determine a first adjustment coefficient corresponding to the at least one cleaning duration to obtain at least one first adjustment coefficient; Determine a corresponding adjustment coefficient according to the average danger level value and the mean square error of each merged area in the at least one merged area to obtain at least one second adjustment coefficient; The at least one reference evaluation value is adjusted according to the at least one first adjustment coefficient and the at least one second adjustment coefficient to obtain at least one target evaluation value, that is, the target evaluation value = reference evaluation value * (1 + first adjustment coefficient) * (1 + second adjustment coefficient); Determining a cleaning priority order according to the at least one target evaluation value; The at least one merged region is cleaned up according to the cleaning priority order.

5. The system according to claim 4, characterized in that In the aspect of processing the dangerous position, the control platform device is specifically used for: According to the mapping relationship between the preset risk factor and the processing strategy, determining the processing strategy corresponding to the at least one weighted risk factor, and obtaining at least one processing strategy; the processing strategy includes at least one of the following: voice prompt, alarm prompt, moving the target, and focusing on shooting; The at least one processing strategy is executed.

Images