A target monitoring method, device, equipment and medium

Abstract

The present application relates to the field of video surveillance technology, and specifically to a target monitoring method, device, equipment and medium for improving the efficiency of target monitoring. The method is applied to a target monitoring system, the target monitoring system includes a camera device deployed outside a target building, and the method includes: obtaining multiple first building images taken by the camera device of the target building within a preset time length; wherein the first building image includes the activity areas of residents on multiple floors in the target building; identifying the activity area of ​​the target resident from the first building image, calculating the similarity between the characteristics of the activity area of ​​the target resident and the pre-stored area characteristics corresponding to the target resident, and obtaining multiple similarities; wherein the target resident is a resident that meets the preset conditions; according to the number of similarities less than the first threshold value among the multiple similarities, determining the number of activities of the target resident within the preset time length; if the number of activities is less than the second threshold value, determining that the target resident is abnormal.

Description

Technical Field

[0001] The present application relates to the field of video surveillance technology, and in particular to a target monitoring method, device, equipment and medium. Background Art

[0002] As the trend of population aging increases, the proportion of elderly people in society is getting higher and higher, especially those living alone. Once an elderly person living alone has an accident, such as falling and falling into a coma, it is difficult for others to find them in time, which may lead to serious consequences. At present, community staff visit the elderly living alone regularly through manual visits to obtain information about their activities. However, this monitoring method is inefficient. Summary of the invention

[0003] Embodiments of the present application provide a target monitoring method, apparatus, device and medium for improving the efficiency of target monitoring.

[0004] In a first aspect, the present application provides a target monitoring method, which is applied to a target monitoring system, wherein the target monitoring system includes a camera device deployed outside a target building, and the method includes:

[0005] Within a preset time period, a plurality of first building images taken by the camera device of the target building are obtained; wherein the first building images include activity areas of residents on multiple floors of the target building;

[0006] Identifying the activity area of ​​a target resident from the first building map, calculating the similarity between the characteristics of the activity area of ​​the target resident and the pre-stored area characteristics corresponding to the target resident, and obtaining multiple similarities; wherein the target resident is a resident that meets a preset condition;

[0007] Determining the number of activities of the target resident within the preset time period according to the number of similarities less than a first threshold among the multiple similarities;

[0008] If the number of activities is less than a second threshold, it is determined that the target household is abnormal.

[0009] In the embodiment of the present application, by deploying a camera device outside the target building, multiple first building images of the activity areas of residents on multiple floors in the target building are taken within a preset time period, and the number of activities of the target resident within the preset time period is determined based on the similarity between the characteristics of the activity area of ​​the target resident in the first building image and the pre-stored area characteristics corresponding to the target resident, and then based on the number of activities of the target resident within the preset time period, it is determined whether the target resident is abnormal. Compared with the door-to-door visit method, this method can improve the efficiency of target monitoring, and does not need to install a monitoring system for each household, which can reduce costs and is more conducive to promotion.

[0010] In a possible embodiment, identifying the activity area of ​​the target resident from the first building map includes:

[0011] Based on the house information associated with the target user, determining the activity area of ​​the target resident in the first building map; or,

[0012] Based on the location information of the target resident's activity area in the second building map, the target resident's activity area is determined in the first building map; wherein the second building map is taken by the camera device of the target building before taking the multiple first building maps.

[0013] In the embodiment of the present application, the activity area of ​​the target resident can be identified from the first building map in a variety of ways, thereby improving the flexibility and intelligence of identifying the activity area.

[0014] In a possible embodiment, the residents satisfying the preset condition include a plurality of residents, and before calculating the similarity between the feature of the activity area of ​​the target resident and the pre-stored area feature corresponding to the target resident, the method further includes:

[0015] Determine the target number of the activity area of ​​the target resident according to the patrol rule; wherein the patrol rule is used to indicate the processing order of the activity areas of the multiple residents;

[0016] According to the correspondence between a plurality of pre-stored area numbers and a plurality of area features, the area feature corresponding to the target number is determined as the pre-stored area feature corresponding to the target household.

[0017] In an embodiment of the present application, the detection device uses a rotation method to process the activity areas of each resident in multiple first building maps, without simultaneously processing the activity areas of multiple residents that meet preset conditions. While ensuring the target monitoring effect, the computing power requirements are effectively reduced, which can further improve the efficiency of feature extraction and the efficiency of target monitoring.

[0018] In a possible embodiment, the pre-stored regional features corresponding to the target household are stored in the base map data, and after calculating the similarity between the features of the activity area of ​​the target household and the pre-stored regional features corresponding to the target household, the method further includes:

[0019] If the similarity is greater than or equal to the first threshold, the pre-stored area features corresponding to the target household are replaced with the features of the activity area of ​​the target household and stored in the base map data.

[0020] In an embodiment of the present application, the pre-stored area features can be updated in real time, and can be subsequently compared with the updated pre-stored area features to avoid false alarms caused by large feature differences due to changes in ambient brightness over a long period of time, thereby making the similarity comparison results more accurate.

[0021] In a possible embodiment, after determining that the target household is abnormal, the method further includes:

[0022] Sending alarm information and geographic location information associated with the target resident; wherein the geographic location information is used to indicate the geographic location of the activity area of ​​the target resident in the target building, and the alarm information is used to indicate that the target resident is abnormal.

[0023] In an embodiment of the present application, after determining that the target resident is abnormal, the alarm information and the geographic location information associated with the target resident are sent together so that community personnel can go to the target resident's home in time according to the geographic location information to check the specific situation of the target resident.

[0024] In a possible embodiment, calculating the similarity between the feature of the activity area of ​​the target household and the pre-stored area feature corresponding to the target household includes:

[0025] If the activity area of ​​the target resident includes multiple areas, the multiple areas and the wall areas connecting the multiple areas are merged into the target area;

[0026] The similarity between the characteristics of the target area and the pre-stored area characteristics corresponding to the target household is calculated.

[0027] In a possible embodiment, the preset condition is living alone and being older than a preset age.

[0028] In a possible embodiment, the first building image and the second building image are taken by the camera device at a preset angle while looking up at the target building.

[0029] In an embodiment of the present application, the camera equipment looks up at the target building at a preset angle to avoid capturing details inside the residents' homes and protect the residents' privacy.

[0030] In a second aspect, the present application provides a target monitoring device, which is arranged in a target monitoring system, wherein the target monitoring system includes a camera device deployed outside a target building, and the device includes:

[0031] An acquisition module, used to acquire a plurality of first building images taken by the camera device of the target building within a preset time period; wherein the first building images include activity areas of residents on multiple floors of the target building;

[0032] an obtaining module, configured to identify an activity area of ​​a target resident from the first building map, calculate a similarity between a feature of the activity area of ​​the target resident and a pre-stored area feature corresponding to the target resident, and obtain a plurality of similarities; wherein the target resident is a resident that meets a preset condition;

[0033] A determination module, configured to determine the number of activities of the target resident within the preset time period according to the number of similarities less than a first threshold among the multiple similarities;

[0034] The determination module is further configured to determine that the target household is abnormal if the number of activities is less than a second threshold.

[0035] In a possible embodiment, the obtaining module is specifically used for:

[0036] Based on the house information associated with the target user, determining the activity area of ​​the target resident in the first building map; or,

[0037] Based on the location information of the target resident's activity area in the second building map, the target resident's activity area is determined in the first building map; wherein the second building map is taken by the camera device of the target building before taking the multiple first building maps.

[0038] In a possible embodiment, the household that meets the preset condition includes a plurality of households, and the determination module is further configured to:

[0039] Before calculating the similarity between the characteristics of the activity area of ​​the target resident and the pre-stored area characteristics corresponding to the target resident, determining the target number of the activity area of ​​the target resident according to a patrol rule; the patrol rule is used to indicate the processing order of the activity areas of the multiple residents;

[0040] According to the correspondence between a plurality of pre-stored area numbers and a plurality of area features, the area feature corresponding to the target number is determined as the pre-stored area feature corresponding to the target household.

[0041] In a possible embodiment, the pre-stored regional features corresponding to the target household are stored in base map data; the device further includes a storage module, and the storage module is used to:

[0042] After calculating the similarity between the characteristics of the target resident's activity area and the pre-stored area characteristics corresponding to the target resident, if the similarity is greater than or equal to the first threshold, the pre-stored area characteristics corresponding to the target resident are replaced with the characteristics of the target resident's activity area and saved in the base map data.

[0043] In a possible embodiment, the device further includes a sending module, and the sending module is used to:

[0044] Sending alarm information and geographic location information associated with the target resident; wherein the geographic location information is used to indicate the geographic location of the activity area of ​​the target resident in the target building, and the alarm information is used to indicate that the target resident is abnormal.

[0045] In a possible embodiment, the obtaining module is specifically used for:

[0046] If the activity area of ​​the target resident includes multiple areas, the multiple areas and the wall areas connecting the multiple areas are merged into the target area;

[0047] The similarity between the characteristics of the target area and the pre-stored area characteristics corresponding to the target household is calculated.

[0048] In a possible embodiment, the preset condition is living alone and being older than a preset age.

[0049] In a possible embodiment, the first building image and the second building image are taken by the camera device at a preset angle while looking up at the target building.

[0050] In a third aspect, the present application provides a target electronic device, including:

[0051] A memory for storing program instructions;

[0052] The processor is used to call the program instructions stored in the memory, and execute any one of the methods in the first aspect according to the obtained program instructions.

[0053] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes any one of the methods described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0055] Figure 1 A schematic diagram of an application scenario of a target monitoring method provided in an embodiment of the present application;

[0056] Figure 2 A schematic diagram of the deployment of a camera device provided in an embodiment of the present application;

[0057] Figure 3 A schematic diagram of a target monitoring method provided in an embodiment of the present application Figure 1 ;

[0058] Figure 4 A schematic diagram of a target monitoring method provided in an embodiment of the present application Figure 2 ;

[0059] Figure 5 A structural diagram of a target monitoring device provided in an embodiment of the present application;

[0060] Figure 6 A structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] To make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other arbitrarily. In addition, although the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in an order different from that here.

[0062] The terms "first" and "second" 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 term "comprising" and any variation thereof are intended to cover non-exclusive protection. For example, a process, method, system, product or device comprising 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.

[0063] In the embodiment of the present application, "multiple" may mean at least two, for example, two, three or more, and the embodiment of the present application does not limit this.

[0064] In order to improve the efficiency of target monitoring, an embodiment of the present application provides a target monitoring method, which can be executed by an electronic device of a target monitoring system. The electronic device can be implemented by a terminal or a server, and the terminal is, for example, a mobile terminal, a fixed terminal or a portable terminal, such as a mobile phone, a multimedia computer, a multimedia tablet, a desktop computer, a notebook computer, a tablet computer, etc. The server can be an independent physical server, or a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms, but is not limited to this.

[0065] The following briefly introduces the application scenarios to which the technical solutions of the embodiments of the present application can be applied. It should be noted that the application scenarios introduced below are only used to illustrate the embodiments of the present application and are not limited. In the specific implementation process, the technical solutions provided by the embodiments of the present application can be flexibly applied according to actual needs.

[0066] Please refer to Figure 1 , which is a schematic diagram of an application scenario of the target monitoring method provided in an embodiment of the present application, or can be understood as a structural schematic diagram of a target monitoring system, which includes a camera device 101 and an electronic device 102.

[0067] The camera device 101 is a device with a camera function, such as a camera or a video recorder. The camera device 101 is deployed outside the target building. The installation height of the camera device is generally between 3 meters and 4 meters. The installation distance between the camera device and the target building is generally 15 meters. The camera device 101 can shoot upward at the target building at a preset angle. The preset angle is an angle at which the camera device can only shoot the outside areas such as the windows and balconies of the residents, so that the camera device 101 can only capture the image of the outside area, avoiding shooting the details of the residents' houses and protecting the privacy of the residents.

[0068] Please refer to Figure 2 , is a schematic diagram of the deployment of a camera device provided in an embodiment of the present application. The camera device 101 looks up at the target building 201 and shoots, α represents the coverage angle of the camera area of ​​the camera device 101, which can cover all floors of the target building 201.

[0069] It should be noted that Figure 1 and Figure 2 One camera device 101 is taken as an example, but the number of camera devices 101 is not limited in practice.

[0070] Figure 1In the example, the camera device 101 and the electronic device 102 are two independent devices. The camera device 101 is deployed outside the target building. The camera device 101 sends the image of the target building to the electronic device 102. The electronic device 102 analyzes the image of the target building to determine whether there is any abnormality in the residents of the target building. How to analyze the image of the target building will be described in detail below.

[0071] However, in practice, the camera device 101 can also be coupled with the electronic device 102. For example, the camera device 101 integrated with the functions of the electronic device 102 is deployed outside the target building. After the camera device 101 captures the image of the target building, the image of the target building can be analyzed to determine whether there is any abnormality in the residents of the target building. Specifically, how to analyze the image of the target building will be described in detail below.

[0072] As described above, the application scenarios are Figure 1 The application scenario shown is Figure 1 The target monitoring method performed by the electronic device 102 in the example is introduced as an example. Figure 3 , which is a flow chart of a target monitoring method provided in an embodiment of the present application Figure 1 .

[0073] S301. Acquire multiple first building images of a target building taken by a camera device within a preset time period.

[0074] Specifically, there are a large number of residents living in the target building. After obtaining permission from all residents in the target building, the installer can deploy camera equipment outside the target building, where the target building is a building where it is necessary to monitor whether there are safety hazards in the residents, for example, a building with a large number of elderly people living alone.

[0075] After the installer has installed the camera equipment, the camera equipment is started. The camera equipment can take a first building image of the target building and immediately send the first building image to the electronic device. After multiple moments within a preset time, the electronic device can obtain multiple first building images of the target building taken by the camera equipment. The first building image includes the activity areas of residents on multiple floors in the target building, such as windows, balconies and other outer areas.

[0076] Considering that some target buildings have higher floors, the camera range of one camera device may not cover the entire target building. Therefore, in a possible embodiment, the number of camera devices to be deployed can be determined according to the number of floors of the target building.

[0077] Specifically, when the number of floors in the target building is less than the preset number, the number of camera devices is one, and the camera range of the one camera device can cover the activity areas of the residents on all floors in the target building. When the number of floors in the target building is greater than or equal to the preset number, the number of camera devices is multiple, wherein the camera range of each camera device can cover the activity areas of the residents on some floors in the target building, and the sum of the camera ranges of the multiple camera devices can cover the activity areas of the residents on all floors in the target building.

[0078] For example, when the target building has 7 floors, a camera device may be deployed outside the target building, and the camera device is responsible for capturing images of the activity areas of the residents on floors 1 to 7 of the target building. Or, for example, when the target building has 15 floors, two cameras may be deployed outside the target building, the first camera device is responsible for capturing images of the activity areas of the residents on floors 1 to 7 of the target building, and the second camera device is responsible for capturing images of the activity areas of the residents on floors 8 to 15 of the target building.

[0079] S302: Identify the activity area of ​​the target resident from the first building map, calculate the similarity between the characteristics of the activity area of ​​the target resident and the pre-stored area characteristics corresponding to the target resident, and obtain multiple similarities.

[0080] After the electronic device obtains the first building map, the process of processing the first building map is as described in S1.1-S1.3.

[0081] S1.1. Identify target households.

[0082] Since there are many residents in the target building, the electronic device can first determine the target residents from among them, where the target residents are residents who meet preset conditions, such as living alone, being older than a preset age, being physically disabled, etc.

[0083] In a possible embodiment, the preset condition is that the resident lives alone and is older than the preset age. The resident who meets the preset condition refers to an elderly person living alone. The preset ages corresponding to residents of different genders may be different. For example, the preset age corresponding to a male resident is 60 years old, and the preset age corresponding to a female resident is 55 years old.

[0084] The residents in the target building who meet the preset conditions may include multiple residents, which involves how to determine the target residents from the multiple residents who meet the preset conditions. The following is an introduction based on different situations.

[0085] Case 1: The target households are multiple households that meet the preset conditions.

[0086] The residents who meet the preset conditions include multiple residents, and the target residents are these multiple residents. For example, there are three residents who meet the preset conditions in the target building, namely, resident A, resident B and resident C, then these three residents are all target residents.

[0087] Case 2: The target household is one of multiple households that meet the preset conditions.

[0088] The residents meeting the preset conditions include multiple residents, the target resident is one of the multiple residents, and the electronic device can determine the target user (ie, the one resident) from the multiple residents according to the patrol rule, and the patrol rule is used to indicate the processing order of the activity areas of the multiple residents.

[0089] For example, there are two residents in the target building that meet the preset conditions. The activity area of ​​resident A is area 1, and the activity area of ​​resident B is area 2. The patrol rule can indicate that the processing order of the activity areas of these two residents is: area 1, area 2, area 1, area 2... and so on. If the electronic device processed area 1 at the last moment, and the area to be processed at the current moment is area 2, then the resident B corresponding to area 2 is the target resident. If the electronic device processed area 2 at the last moment, and the area to be processed at the current moment is area 1, then the resident A corresponding to area 1 is the target resident.

[0090] S1.2. Identify the activity area of ​​the target residents from the first building map.

[0091] After the electronic device determines the target resident, it can identify the activity area of ​​the target resident from the first building map. There are multiple identification methods, which are introduced below.

[0092] The first identification method: Based on the housing information associated with the target user, the activity area of ​​the target resident is determined in the first building map.

[0093] Specifically, after the electronic device determines multiple households that meet preset conditions in the target building, it can save the housing information of these multiple households, and the housing information includes house number information, apartment type information, etc.

[0094] For the above situation one, if the target residents are multiple residents who meet the preset conditions, the electronic device can determine the house information associated with each of the multiple residents from the pre-stored house information of the multiple residents, and determine the activity area of ​​each resident in the first building map based on the house information associated with each resident.

[0095] For the second situation mentioned above, if the target resident is one of multiple households that meet the preset conditions, the electronic device can determine the house information associated with the target resident (i.e., this one household) from the pre-stored house information of multiple households, and determine the activity area of ​​the target resident (i.e., this one household) in the first building map based on the house information.

[0096] The second identification method: based on the location information of the target resident's activity area in the second building map, determine the target resident's activity area in the first building map.

[0097] Specifically, before taking multiple pictures of the first building, the camera device first takes a picture of the second building of the target building and sends it to the electronic device. In other words, the second building picture is taken by the camera device of the target building before taking multiple pictures of the first building. After the electronic device obtains the second building picture, the user can manually mark the activity areas of multiple residents in the target building that meet preset conditions in the second building picture. The electronic device can receive the marked second building picture in response to the user's input operation, identify multiple location information of the activity areas of the multiple residents in the second building picture, and save the multiple location information.

[0098] The first building map and the second building map are taken by the camera device at a preset angle looking up at the target building. After the camera device is installed, its installation height, installation distance, and preset angle remain unchanged, so the location information of the activity area of ​​each household in the first building map and the second building map is the same.

[0099] For example, a rectangular coordinate system is established with the center point of the second building map as the origin. The location information of the activity area of ​​the i-th household in the second building map is [(x i ,y i ),w i ,h i ], then the location information of the activity area of ​​the i-th resident in the first building map should also be [(x i ,y i ),w i ,h i ]. Among them, x i The horizontal coordinate of the center point of the household's activity area, y i The vertical coordinate of the center point of the household's activity area, w i Indicates the width of the resident's activity area, h i Indicates the height of the resident's activity area.

[0100] For the above situation one, if the target residents are multiple residents who meet the preset conditions, after obtaining the first building map, the electronic device can determine the location information of the activity area of ​​each of the multiple residents in the second building map from the pre-stored multiple location information, and determine the activity area of ​​each resident in the first building map based on each location information.

[0101] For the second situation mentioned above, if the target resident is one of multiple households that meet the preset conditions, the electronic device can, after obtaining the first building map, determine the location information of the activity area of ​​the target resident (i.e., this one household) in the second building map from multiple pre-stored location information, and determine the activity area of ​​the target resident (i.e., this one household) in the first building map based on the location information.

[0102] It should be noted that no matter whether the electronic device adopts the first identification method or the second identification method, if the target residents are multiple residents who meet the preset conditions, for multiple first building maps obtained within a preset time period, the electronic device can determine the activity area of ​​each resident among the multiple residents in each first building map.

[0103] Example 1: There are two residents in the target building who meet the preset conditions. The activity area of ​​resident A is area 1, and the activity area of ​​resident B is area 2. If the preset time includes 10 moments N1-N10, the electronic device obtains 10 first building maps during these 10 moments. The activity area of ​​resident A, i.e., area 1, and the activity area of ​​resident B, i.e., area 2, can be determined in each first building map.

[0104] Regardless of whether the electronic device adopts the first identification method or the second identification method, if the target resident is one of multiple households that meet the preset conditions, the electronic device can determine the activity area of ​​the target resident (i.e., this one resident) in some of the first building maps obtained within a preset time period.

[0105] Example 2: There are two residents in the target building that meet the preset conditions. The activity area of ​​resident A is area 1, and the activity area of ​​resident B is area 2. The patrol rules indicate that the processing order of the activity areas of the two residents is: area 1, area 2, area 1, area 2... and so on. If the preset time length includes 10 moments N1-N10, the electronic device obtains 10 first building maps at 10 moments within the preset time length. For the 5 first building maps at the 5 moments N1, N3, N5, N7, and N9, the electronic device determines the activity area of ​​resident A, that is, area 1, in these 5 first building maps. For the 5 first building maps at the 5 moments N2, N4, N6, N8, and N10, the electronic device determines the activity area of ​​resident B, that is, area 2, in the remaining 5 first building maps.

[0106] S1.3. Calculate the similarity between the characteristics of the activity area of ​​the target resident and the pre-stored area characteristics corresponding to the target resident.

[0107] Specifically, the electronic device can pre-build a feature extraction model, which can be various convolutional neural networks or twin networks, such as Siamese Network, Triplet network, etc. Model training can use some public and annotated data sets, and the data sets can come from the fields of target detection, target classification, etc. The embodiment of the present application uses an existing data set as the initial data set, and there is no need to re-collect a large amount of data for a specific target, saving a lot of manpower collection costs and labeling costs.

[0108] The electronic device pre-acquires a second building map of the target building, determines multiple households in the target building that meet preset conditions, performs feature extraction on the second building map through the feature extraction model, extracts features of the activity areas of the multiple households in the second building map, and saves them in the base map data as pre-stored area features. In other words, the base map data includes pre-stored area features associated with each of the multiple households. After the electronic device obtains the first building map, it performs feature extraction on the first building map through the feature extraction model, extracts features of the activity areas of the target residents in the first building map, and then calculates the similarity between the features of the activity areas of the target residents and the pre-stored area features corresponding to the target residents, such as Euclidean distance, cosine similarity, etc.

[0109] For example, the formula for calculating cosine similarity is as follows:

[0110]

[0111] Where n represents the total number of features, X i represents the i-th feature of the activity area of ​​the target resident in the first building map, Y i It represents the i-th pre-stored regional feature corresponding to the target household, that is, the i-th feature of the activity area of ​​the target household in the second building map. The closer cos(θ) is to 1, the higher the similarity.

[0112] Since the target resident's activity area may include one or more areas, the process of calculating the similarity is different, which is introduced below.

[0113] If the activity area of ​​the target resident includes only one area, the electronic device can directly calculate the similarity between the features of the activity area of ​​the target resident (ie, the one area) and the pre-stored area features corresponding to the target resident.

[0114] If the target resident's activity area includes multiple areas, the electronic device can merge the multiple areas and the wall areas connecting the multiple areas into a target area, and calculate the similarity between the characteristics of the target area and the pre-stored area characteristics corresponding to the target resident. For example, if the activity area of ​​an elderly person living alone includes the balcony and the bedroom window, the balcony, the bedroom window, and the wall connecting the balcony and the bedroom window are merged into one target area.

[0115] Since the target household may be multiple households or one household, the process of calculating the similarity is also different, which is introduced below.

[0116] For the above situation one, if the target residents are multiple residents who meet the preset conditions, the electronic device identifies the activity areas of the multiple residents from the first building map, and calculates the similarity between the characteristics of the activity area of ​​each resident and the pre-stored area characteristics corresponding to each resident.

[0117] After the electronic device performs the above processing on the multiple first building images obtained within the preset time, multiple similarities corresponding to each household within the preset time can be obtained. The process of how to extract features and calculate similarities can be referred to the content discussed above, which will not be repeated here.

[0118] Continuing with Example 1 above, the electronic device obtains 10 first building maps at 10 moments, determines area 1 and area 2 in each first building map, calculates the similarity between the features of area 1 of household A and the pre-stored area features corresponding to household A, and obtains the 10 similarities corresponding to household A at 10 moments, and calculates the similarity between the features of area 2 of household B and the pre-stored area features corresponding to household B, and obtains the 10 similarities corresponding to household B at 10 moments.

[0119] For the above situation 2, if the target resident is one of the multiple residents that meet the preset conditions, the electronic device can determine the target number of the target resident's activity area according to the patrol rule, and determine the area feature corresponding to the target number as the pre-stored area feature corresponding to the target resident according to the correspondence between the multiple pre-stored area numbers and the multiple area features, and calculate the similarity between the feature of the target resident's activity area and the area feature corresponding to the target number. Please refer to the content discussed above for the meaning of the patrol rule, which will not be repeated here.

[0120] After the electronic device performs the above processing on some of the first building images among the multiple first building images obtained within the preset time, multiple similarities corresponding to each household within the preset time can be obtained. The process of how to extract features and calculate similarities can be referred to the content discussed above, which will not be repeated here.

[0121] Continuing with the above example 2, for the five first building images at five moments N1, N3, N5, N7, and N9, the electronic device determines area 1 in these five first building images, calculates the similarity between the features of area 1 and the features of the area corresponding to target number 1, and obtains the five similarities corresponding to household A at the five moments. For the five first building images at five moments N2, N4, N6, N8, and N10, the electronic device determines area 2 in the remaining five first building images, calculates the similarity between the features of area 2 and the features of the area corresponding to target number 2, and obtains the five similarities corresponding to household B at the five moments.

[0122] Considering that if the pre-stored regional features are extracted based on the second building map collected in the morning, and the first building map is collected in the evening, the large change in ambient brightness will cause a large difference between the features extracted from the first building map and the pre-stored regional features, thereby generating a false alarm. Therefore, in a possible embodiment, the pre-stored regional features corresponding to the target resident are stored in the base map data, and when the electronic device calculates the similarity between the features of the target resident's activity area and the pre-stored regional features corresponding to the target resident, if the similarity is greater than or equal to the first threshold, the pre-stored regional features corresponding to the target resident are replaced with the features of the target resident's activity area and stored in the base map data.

[0123] Continuing with the above example 2, the base map data includes the correspondence between multiple area numbers and multiple area features. The feature of area 1 is extracted from the first building map at time N1 as feature T1. If the similarity between feature T1 and the area feature corresponding to target number 1 is greater than or equal to the first threshold, the area feature corresponding to target number 1 is replaced with feature T1 and saved in the base map data. The feature of area 1 is extracted from the first building map at time N3 as feature T3. If the similarity between feature T3 and feature T1 in the base map data is greater than or equal to the first threshold, feature T1 is replaced with feature T3 and saved in the base map data.

[0124] Taking into account that the target resident will not appear in activity areas such as windows and balconies most of the time, that is, the similarity between the characteristics of the target resident's activity area and the pre-stored area characteristics corresponding to the target resident is mostly greater than or equal to the first threshold. In the embodiment of the present application, the pre-stored area characteristics are updated in real time to avoid false alarms caused by large changes in the surrounding environment brightness after a long time.

[0125] S303: Determine the number of activities of the target household within a preset time period according to the number of similarities that are smaller than a first threshold among the multiple similarities.

[0126] Since the target household may be multiple households or one household, the process of determining the number of activities of the target household within a preset time period is different, which are introduced below respectively.

[0127] For the above situation 1, if the target resident is a plurality of residents that meet the preset conditions, after the electronic device processes the plurality of first building images, a plurality of similarities corresponding to each of the plurality of residents within the preset time period can be obtained. For the plurality of similarities corresponding to each resident within the preset time period, the number of activities of each resident within the preset time period is determined according to the number of similarities less than the first threshold value among the plurality of similarities.

[0128] Continuing with the above example 1, the electronic device obtains 10 similarities corresponding to resident A at 10 moments N1-N10. If 2 of the 10 similarities are less than the first threshold, it is determined that the number of activities of resident A within the preset time is 2. The electronic device obtains 10 similarities corresponding to resident B at 10 moments N1-N10. If 3 of the 10 similarities are less than the first threshold, it is determined that the number of activities of resident B within the preset time is 3.

[0129] For the above situation 2, if the target resident is one of the multiple residents that meet the preset conditions, after the electronic device processes the multiple first building images, multiple similarities corresponding to the target resident (i.e., one resident) within the preset time period can be obtained. The number of activities of the target resident (i.e., one resident) within the preset time period is determined based on the number of similarities that are less than the first threshold among the multiple similarities.

[0130] Continuing with the above example 2, if the target resident is resident A, the electronic device obtains 5 similarities corresponding to resident A at 5 moments N1, N3, N5, N7, and N9. If there are 2 similarities less than the first threshold value among these 5 similarities, it is determined that the number of activities of resident A within the preset time length is 2 times. Similarly, if the target resident is resident B, the electronic device obtains 5 similarities corresponding to resident B at 5 moments N2, N4, N6, N8, and N10. If there are 3 similarities less than the first threshold value among these 5 similarities, it is determined that the number of activities of resident B within the preset time length is 3 times.

[0131] S304: If the number of activities is less than the second threshold, it is determined that the target household is abnormal.

[0132] Since the target household may be multiple households or one household, the process of determining whether the target household is abnormal is different, which are introduced below respectively.

[0133] For the above situation 1, if the target household is a plurality of households that meet the preset conditions, after the electronic device determines the number of activities of each of the plurality of households within the preset time, if the number of activities of the first household among the plurality of households within the preset time is less than the second threshold, the first household is determined to be abnormal. If the number of activities of each household among the plurality of households within the preset time is greater than or equal to the second threshold, the plurality of households are determined to be normal.

[0134] Continuing with the above example 1, the electronic device determines that the number of activities of resident A within the preset time is 2 times, and the number of activities of resident B within the preset time is 3 times. If the second threshold is 3, it is determined that resident A is abnormal and resident B is normal.

[0135] For the second situation above, if the target household is one of the multiple households that meet the preset conditions, after the electronic device determines the number of activities of the target household (i.e., the one household) within the preset time, if the number of activities of the target household (i.e., the one household) is less than the second threshold, the target household (i.e., the one household) is determined to be abnormal. If the number of activities of the target household (i.e., the one household) within the preset time is greater than or equal to the second threshold, the target household (i.e., the one household) is determined to be normal.

[0136] Continuing with the above example 2, the electronic device can determine that the number of activities of household A within the preset time is 2 times, and determine that the number of activities of household B within the preset time is 3 times. If the target household is household A and the second threshold is 3, then household A is determined to be abnormal. If the target household is household B and the second threshold is 3, then household B is determined to be normal.

[0137] In order to facilitate community personnel to go to the target resident's home in time to check the situation, in a possible embodiment, after determining that the target resident is abnormal, the electronic device can send an alarm message and the geographic location information associated with the target resident.

[0138] Specifically, when the residents who meet the preset conditions include multiple residents, the electronic device may pre-store geographic location information associated with each of the multiple residents, for example, the base map data also includes geographic location information associated with each of the multiple residents. The geographic location information associated with each resident is used to indicate the geographic location of the activity area of ​​each resident in the target building, and the alarm information is used to indicate that the target resident is abnormal.

[0139] In the above situation 1, if the target resident is a plurality of residents that meet the preset conditions, after the electronic device determines that the first resident among the plurality of residents is abnormal, it can determine the geographic location information associated with the first resident from the pre-stored geographic location information, and send the alarm information and the geographic location information associated with the first resident to the target terminal. The target terminal is, for example, a mobile phone, computer or other terminal of a community member.

[0140] For the second situation above, if the target resident is one of the multiple residents that meet the preset conditions, after the electronic device determines that the target resident (i.e., the one resident) is abnormal, it can determine the geographic location information associated with the target resident (i.e., the one resident) from the pre-stored geographic location information, and send the alarm information and the geographic location information associated with the target resident (i.e., the one resident) to the target terminal. The meanings of the alarm information and the target terminal are referred to the content discussed above, and will not be repeated here.

[0141] For a clearer explanation of the target monitoring method, please refer to Figure 4 , which is a flow chart of a target monitoring method provided in an embodiment of the present application Figure 2 , the following combination Figure 4 The process of electronic equipment processing a first building map is introduced in detail.

[0142] The process starts by executing S401, that is, obtaining a first building map.

[0143] S401. Obtain a first building map.

[0144] The electronic device obtains a first building map at the current moment. The method of obtaining the first building map and the meaning of the first building map can be found in the previous discussion and will not be repeated here.

[0145] S402: Determine the activity area of ​​the target residents.

[0146] The electronic device determines the activity area of ​​the target resident according to the patrol rules. The meaning of the patrol rules can be found in the previous discussion and will not be repeated here.

[0147] S403: Feature extraction.

[0148] After the electronic device determines the target resident's activity area, it extracts the features of the target resident's activity area from the first building map. The process of extracting features can be found in the previous article and will not be described here.

[0149] S404: Feature comparison.

[0150] The electronic device calculates the similarity between the characteristics of the target resident's activity area and the pre-stored area characteristics corresponding to the target resident. The similarity calculation method and the pre-stored area characteristics acquisition method please refer to the content discussed above and will not be repeated here.

[0151] S405: Determine whether to update the base map data.

[0152] If the similarity between the characteristics of the activity area of ​​the target household and the characteristics of the pre-stored area corresponding to the target household is greater than or equal to the first threshold, S406 is executed, that is, the base map data is updated.

[0153] If the similarity between the characteristics of the activity area of ​​the target resident and the pre-stored area characteristics corresponding to the target resident is less than the first threshold, S407 is directly executed, that is, determining whether the preset time duration has been reached.

[0154] S406: Update base map data.

[0155] The electronic device replaces the pre-stored area features corresponding to the pre-targeted resident with the features of the activity area of ​​the target resident, and stores them in the base map data.

[0156] S407: Determine whether the preset time has been reached.

[0157] If the duration between the current moment and the set initial moment is less than the preset duration, the electronic device records the similarity between the characteristics of the target resident's activity area at the current moment and the pre-stored area characteristics corresponding to the target resident, and continues to execute S401, that is, obtaining the next first building map.

[0158] If the duration between the current time and the set initial time is greater than or equal to the preset duration, S408 is executed to determine whether to alarm.

[0159] S408: Determine whether to alarm.

[0160] If the electronic device determines that the number of the multiple similarities between the characteristics of the target resident's activity area and the pre-stored area characteristics corresponding to the target resident within the preset time period is less than the first threshold, and if the number is less than the second threshold, it is determined to alarm and execute S409, that is, alarm output. If the number is greater than or equal to the second threshold, it is determined not to alarm and the process ends.

[0161] S409, alarm output.

[0162] The electronic device can send an alarm message to the target terminal, or send an alarm message and geographic location information associated with the target user to the target terminal. The meanings of the target terminal, alarm message and geographic location information are as discussed above and will not be repeated here.

[0163] After executing S409, the process ends.

[0164] To summarize, the embodiment of the present application provides a target monitoring system, in which a camera device is deployed outside a target building. A target monitoring method is applied to the target monitoring system, which determines whether the target residents have normal activities by comparing the activities of target residents such as elderly people living alone in activity areas such as balconies and windows, and further determines whether the target residents have safety hazards, thereby improving the efficiency of target monitoring.

[0165] Based on the same inventive concept, the present application also provides a target monitoring device, which is arranged in a target monitoring system, and can be specifically arranged in the electronic device discussed above. The target monitoring system includes a camera device deployed outside the target building, please refer to Figure 5 , the device comprises:

[0166] The acquisition module 501 is used to acquire a plurality of first building images taken by a camera device of a target building within a preset time period; wherein the first building image includes activity areas of residents on multiple floors of the target building;

[0167] The obtaining module 502 is used to identify the activity area of ​​the target resident from the first building map, calculate the similarity between the characteristics of the activity area of ​​the target resident and the pre-stored area characteristics corresponding to the target resident, and obtain multiple similarities; wherein the target resident is a resident that meets the preset conditions;

[0168] A determination module 503, configured to determine the number of activities of the target resident within a preset time period according to the number of similarities less than a first threshold among the plurality of similarities;

[0169] The determination module 503 is further configured to determine that the target household is abnormal if the number of activities is less than a second threshold.

[0170] In a possible embodiment, the obtaining module 502 is specifically used for:

[0171] Based on the house information associated with the target user, determine the activity area of ​​the target resident in the first building map; or,

[0172] Based on the position information of the target resident's activity area in the second building map, the target resident's activity area is determined in the first building map; wherein the second building map is taken by the camera equipment of the target building before taking the first building map.

[0173] In a possible embodiment, the household meeting the preset condition includes multiple households, and the determination module 503 is further configured to:

[0174] Before calculating the similarity between the characteristics of the target resident's activity area and the pre-stored area characteristics corresponding to the target resident, determining the target number of the target resident's activity area according to the patrol rule; wherein the patrol rule is used to indicate the processing order of the activity areas of multiple residents;

[0175] According to the correspondence between multiple pre-stored area numbers and multiple area features, the area feature corresponding to the target number is determined as the pre-stored area feature corresponding to the target household.

[0176] In a possible embodiment, the pre-stored regional features corresponding to the target household are stored in the base map data, and the device further includes a storage module 504, which is used to:

[0177] After calculating the similarity between the characteristics of the target resident's activity area and the pre-stored area characteristics corresponding to the target resident, if the similarity is greater than or equal to a first threshold, the pre-stored area characteristics corresponding to the target resident are replaced with the characteristics of the target resident's activity area and saved in the base map data.

[0178] In a possible embodiment, the device further includes a sending module 505, and the sending module 505 is used to:

[0179] Send alarm information and geographical location information associated with the target resident; wherein the geographical location information is used to indicate the geographical location of the target resident's activity area in the target building, and the alarm information is used to indicate that the target resident is abnormal.

[0180] In a possible embodiment, the obtaining module 502 is specifically used for:

[0181] If the activity area of ​​the target resident includes multiple areas, the multiple areas and the wall areas connecting the multiple areas are merged into the target area;

[0182] Calculate the similarity between the characteristics of the target area and the pre-stored regional characteristics corresponding to the target household.

[0183] In a possible embodiment, the preset condition is living alone and being older than a preset age.

[0184] In a possible embodiment, the first building image and the second building image are taken by a camera device at a preset angle while looking up at the target building.

[0185] Based on the same inventive concept, an electronic device is also provided in the embodiment of the present application, which is equivalent to the electronic device discussed above. Please refer to Figure 6 , the device comprises:

[0186] At least one processor 601, and a memory 602 connected to the at least one processor 601. The specific connection medium between the processor 601 and the memory 602 is not limited in the embodiment of the present application. Figure 6 In the example, the processor 601 and the memory 602 are connected via a bus 600. Figure 6The connection between other components is shown by bold lines, and is not intended to be limiting. The bus 600 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. Alternatively, the processor 601 can also be called a controller, and there is no limitation on the name.

[0187] In the embodiment of the present application, the memory 602 stores instructions that can be executed by at least one processor 601. The at least one processor 601 can execute the instructions stored in the memory 602. Figure 3 and Figure 4 The processor 601 can also implement any of the target monitoring methods. Figure 5 The functions of each module in the device shown.

[0188] Among them, the processor 601 is the control center of the device, and can use various interfaces and lines to connect the various parts of the entire control device. By running or executing instructions stored in the memory 602 and calling the data stored in the memory 602, the various functions of the device and processing data, the device can be monitored as a whole.

[0189] In one possible design, the processor 601 may include one or more processing units, and the processor 601 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the modem processor may not be integrated into the processor 601. In some embodiments, the processor 601 and the memory 602 may be implemented on the same chip, and in some embodiments, they may also be implemented separately on separate chips.

[0190] Processor 601 can be a general-purpose processor, such as a central processing unit (CPU), a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the target monitoring method disclosed in conjunction with the embodiments of the present application can be directly embodied as a hardware processor to execute, or the hardware and software modules in the processor are combined to execute.

[0191] The memory 602 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The memory 602 may include at least one type of storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory, a random access memory (Random Access Memory, RAM), a static random access memory (Static Random Access Memory, SRAM), a programmable read-only memory (Programmable Read Only Memory, PROM), a read-only memory (Read Only Memory, ROM), an electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), a magnetic memory, a disk, an optical disk, etc. The memory 602 is any other medium that can be used to carry or store a desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 602 in the embodiment of the present application can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0192] By programming the processor 601, the code corresponding to the target monitoring method described in the above embodiment can be fixed into the chip, so that the chip can execute the target monitoring method when running. Figure 3 and Figure 4 The steps of the target monitoring method are shown in FIG. How to design and program the processor 601 is a technique known to those skilled in the art and will not be described in detail here.

[0193] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes any target monitoring method discussed above. Since the principle of solving the problem by the above-mentioned computer-readable storage medium is similar to that of the target monitoring method, the implementation of the above-mentioned computer-readable storage medium can refer to the implementation of the method, and the repeated parts will not be repeated.

[0194] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0195] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0196] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0197] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0198] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A target monitoring method, characterized in that: Applied in a target monitoring system, the target monitoring system includes a camera device deployed outside a target building, and the method includes: Within a preset time period, a plurality of first building images taken by the camera device of the target building are obtained; wherein the first building images include activity areas of residents on multiple floors of the target building; Identifying the activity area of ​​a target resident from the first building map, calculating the similarity between the characteristics of the activity area of ​​the target resident and the pre-stored area characteristics corresponding to the target resident, and obtaining multiple similarities; wherein the target resident is a resident that meets a preset condition; Determining the number of activities of the target resident within the preset time period according to the number of similarities less than a first threshold among the multiple similarities; If the number of activities is less than a second threshold, it is determined that the target household is abnormal.

2. The method according to claim 1, characterized in that Identifying the activity area of ​​the target resident from the first building map includes: Based on the house information associated with the target household, determining the activity area of ​​the target household in the first building map; or, Based on the location information of the target resident's activity area in the second building map, the target resident's activity area is determined in the first building map; wherein the second building map is taken by the camera device of the target building before taking the multiple first building maps.

3. The method according to claim 1, characterized in that The residents meeting the preset conditions include a plurality of residents. Before calculating the similarity between the characteristics of the activity area of ​​the target resident and the pre-stored area characteristics corresponding to the target resident, the method further includes: Determine the target number of the activity area of ​​the target resident according to the patrol rule; wherein the patrol rule is used to indicate the processing order of the activity areas of the multiple residents; According to the correspondence between a plurality of pre-stored area numbers and a plurality of area features, the area feature corresponding to the target number is determined as the pre-stored area feature corresponding to the target household.

4. The method according to claim 1, characterized in that The pre-stored regional features corresponding to the target household are stored in the base map data. After calculating the similarity between the features of the activity area of ​​the target household and the pre-stored regional features corresponding to the target household, the method further comprises: If the similarity is greater than or equal to the first threshold, the pre-stored area features corresponding to the target household are replaced with the features of the activity area of ​​the target household and stored in the base map data.

5. The method according to claim 1, characterized in that After determining that the target household is abnormal, the method further includes: Sending alarm information and geographic location information associated with the target resident; wherein the geographic location information is used to indicate the geographic location of the activity area of ​​the target resident in the target building, and the alarm information is used to indicate that the target resident is abnormal.

6. The method according to claim 1, characterized in that Calculating the similarity between the characteristics of the activity area of ​​the target household and the pre-stored area characteristics corresponding to the target household, including: If the activity area of ​​the target resident includes multiple areas, the multiple areas and the wall areas connecting the multiple areas are merged into the target area; The similarity between the characteristics of the target area and the pre-stored area characteristics corresponding to the target household is calculated.

7. The method according to any one of claims 1 to 6, characterized in that: The preset condition is living alone and being older than a preset age.

8. The method according to claim 2, characterized in that The first building image and the second building image are taken by the camera device at a preset angle while looking up at the target building.

9. A target monitoring device, characterized in that: Set in a target monitoring system, the target monitoring system includes a camera device deployed outside the target building, and the device includes: An acquisition module, used to acquire a plurality of first building images taken by the camera device of the target building within a preset time period; wherein the first building images include activity areas of residents on multiple floors of the target building; an obtaining module, configured to identify an activity area of ​​a target resident from the first building map, calculate a similarity between a feature of the activity area of ​​the target resident and a pre-stored area feature corresponding to the target resident, and obtain a plurality of similarities; wherein the target resident is a resident that meets a preset condition; A determination module, configured to determine the number of activities of the target resident within the preset time period according to the number of similarities less than a first threshold among the multiple similarities; The determination module is further configured to determine that the target household is abnormal if the number of activities is less than a second threshold.

10. An electronic device, characterized in that: include: A memory for storing program instructions; A processor is used to call the program instructions stored in the memory, and execute the method according to any one of claims 1 to 8 according to the obtained program instructions.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes the method according to any one of claims 1 to 8.

Images