Camera position determination method and device and nonvolatile storage medium

Abstract

The invention discloses a camera position determination method and device and a nonvolatile storage medium. The method comprises the steps that target object attribute information in a preset range is acquired, the target object attribute information at least comprises a target object behavior index and a target object hardware index, and the target object behavior index is used for indicating behavior information associated with a target object; the target object hardware index is used for indicating hardware information associated with the target object in the data transmission process; determining a behavior feature portrait based on the target object attribute information; a target audience portrait is determined based on the target object attribute information and the behavior feature portrait, and the target audience portrait is used for representing the association condition of the behavior feature of the target object and a camera collecting the behavior feature; and determining the position of the camera based on the target audience portrait. The technical problem that the security and protection requirements cannot be met due to the fact that camera tracking cannot be carried out on the target object in the preset range currently is solved.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular, to a method and device for determining a camera position and a non-volatile storage medium. Background Art

[0002] With the rapid development of the Internet of Things, cameras, as an important tool for information collection, are widely used in different scenarios, such as monitoring and data collection. However, when traditional cameras monitor target objects within a preset range, there are the following problems: 1) The increase in the number of cameras leads to a decrease in information collection efficiency and an increase in blind spots; 2) The deployment of cameras often depends on the subjective consciousness of the installer and cannot be considered comprehensively; 3) The unreasonable deployment of cameras leads to the inability of cameras to play their due role. For example, in a community monitored by a community management system, the public security protection of the community needs to be strengthened. There are a lot of hidden dangers in the management and safety protection of the surrounding and internal areas of the community. Some old communities are relatively lacking in basic public facilities, and there are blind spots in video surveillance. The level of intelligence of community security and fire emergency management is low, and many community video surveillance cannot meet the needs of safety control. Therefore, there is currently a problem that it is impossible to achieve camera tracking of target objects within the preset range, resulting in failure to meet security requirements.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a method, device and non-volatile storage medium for determining the position of a camera, so as to at least solve the current technical problem that it is impossible to implement camera tracking for a target object within a preset range, resulting in failure to meet security requirements.

[0005] According to one aspect of an embodiment of the present application, a method for determining a camera position is provided, comprising: obtaining target object attribute information within a preset range, wherein the target object attribute information at least includes a target object behavior indicator and a target object hardware indicator, the target object behavior indicator is used to indicate the behavior information associated with the target object, and the target object hardware indicator is used to indicate the hardware information associated with the target object during data transmission; determining a behavior feature portrait based on the target object attribute information, wherein the behavior feature portrait is used to represent the attribute distribution of different behavior features of the target object; determining a target audience portrait based on the target object attribute information and the behavior feature portrait, wherein the target audience portrait is used to represent the association between the behavior features of the target object and a camera that collects the behavior features; and determining the camera position based on the target audience portrait.

[0006] In some embodiments of the present application, before obtaining the target object attribute information within a preset range, the method also includes: obtaining all data within the preset range, wherein all data includes the target object attribute information; determining the level to which all data belongs; clustering all data with each level as the cluster center, and determining the target data collected at each level.

[0007] In some embodiments of the present application, obtaining target object attribute information within a preset range includes: obtaining log data associated with the target object; after preprocessing the log data, extracting target object behavior indicators and target object hardware indicators and scene information and camera information associated with the target object in the preprocessed log data; determining the target object attribute information based on the target object behavior indicators, target object hardware indicators, scene information and camera information.

[0008] In some embodiments of the present application, determining a behavior feature portrait based on target object attribute information includes: clustering target object behavior indicators in the target object attribute information to obtain multiple behavior feature sets, wherein each behavior feature set includes a behavior feature and a target object classified into the behavior feature; determining the attribute distribution of each behavior feature set, wherein the attribute distribution is used to represent the probability distribution of the attribute of each behavior feature in the corresponding behavior feature set; and determining the behavior feature portrait based on the behavior feature set and the attribute distribution of the behavior feature set.

[0009] In some embodiments of the present application, a target audience portrait is determined based on target object attribute information and a behavior characteristic portrait, including: obtaining the target object hardware indicators in the target object attribute information and the scene information and camera information associated with the target object; associating the behavior characteristic portrait with the target object hardware indicators, the scene information and camera information associated with the target object, and determining the hardware requirements for each behavior feature set in the behavior characteristic portrait, wherein the hardware requirements are used to indicate the hardware resource usage and camera location of the target object under the corresponding behavior characteristics; and determining the target audience portrait based on the hardware requirements.

[0010] In some embodiments of the present application, determining the location of a camera based on a target audience portrait includes: determining a first behavior feature set corresponding to a first target object in the behavior feature portrait, wherein the first target object is any target object; determining a first hardware requirement corresponding to the first behavior feature set in the target audience portrait; and determining the location of the camera based on the first hardware requirement.

[0011] In some embodiments of the present application, the method also includes: when there is overlap in the monitoring scenes corresponding to multiple cameras, determining the transmission nodes corresponding to the overlapping data of the multiple cameras in the monitoring scenes; determining two adjacent transmission nodes as a main node, and the main node manages the transmission data of the cameras corresponding to the two adjacent transmission nodes.

[0012] In some embodiments of the present application, the method also includes: obtaining a target file stored in a database, wherein the target file is a file used to store attribute information of a target object; after identifying that the target file has been tampered with, determining an attack path corresponding to the target file; marking files that overlap with the attack path as isolated files, and marking files that do not overlap with the attack path as non-isolated files; deleting the isolated files, and feeding back the processing results to the terminal.

[0013] According to another aspect of an embodiment of the present application, a device for determining a camera position is also provided, including: an acquisition module, used to acquire target object attribute information within a preset range, wherein the target object attribute information at least includes target object behavior indicators and target object hardware indicators, the target object behavior indicators are used to indicate behavior information associated with the target object, and the target object hardware indicators are used to indicate hardware information associated with the target object during data transmission; a first determination module, used to determine a behavior feature portrait based on the target object attribute information, wherein the behavior feature portrait is used to represent the attribute distribution of different behavior features of the target object; a second determination module, used to determine a target audience portrait based on the target object attribute information and the behavior feature portrait, wherein the target audience portrait is used to represent the association between the behavior features of the target object and the camera that collects the behavior features; a third determination module, used to determine the camera position based on the target audience portrait.

[0014] According to another aspect of an embodiment of the present application, a non-volatile storage medium is further provided, in which a program is stored, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the above-mentioned method for determining the camera position.

[0015] According to another aspect of an embodiment of the present application, there is further provided an electronic device, including: a memory and a processor, the processor being configured to run a program stored in the memory, wherein the above-mentioned method for determining a camera position is executed when the program is run.

[0016] According to another aspect of an embodiment of the present application, a computer program product is also provided, including computer instructions, which implement the above-mentioned method for determining the camera position when the computer instructions are executed by a processor.

[0017] In an embodiment of the present application, a method is adopted to obtain target object attribute information within a preset range, wherein the target object attribute information includes at least a target object behavior indicator and a target object hardware indicator, wherein the target object behavior indicator is used to indicate the behavior information associated with the target object, and the target object hardware indicator is used to indicate the hardware information associated with the target object during data transmission; a behavior feature portrait is determined based on the target object attribute information, wherein the behavior feature portrait is used to represent the attribute distribution of different behavior features of the target object; a target audience portrait is determined based on the target object attribute information and the behavior feature portrait, wherein the target audience portrait is used to represent the association between the behavior features of the target object and the camera for collecting the behavior features; a method is adopted to determine the location of the camera based on the target audience portrait, by obtaining the target object attribute information within a preset range, constructing a behavior feature portrait based on the target object attribute information, further determining the target audience portrait, and then determining the location of the camera based on the target audience portrait, thereby performing camera tracking on the target object, thereby solving the current technical problem that camera tracking on the target object within a preset range cannot be achieved, resulting in failure to meet security requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 It is a hardware structure block diagram of a computer terminal for implementing a method for determining a camera position according to an embodiment of the present application;

[0020] Figure 2 is a flowchart of a method for determining a camera position provided in an embodiment of the present application;

[0021] Figure 3 It is a structural schematic diagram of a device for determining a camera position provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] 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 should fall within the scope of protection of the present application.

[0023] The information collected in the embodiments of the present application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or reject automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] In order to better understand the embodiments of the present application, the technical terms involved in the embodiments of the present application are explained as follows:

[0026] K-means++: is an algorithm for selecting initial values ​​(or "seeds") for the K-means clustering algorithm. The location of the K initial centroids has a great impact on the final clustering results and running time, so it is necessary to select K appropriate centroids. The basic idea of ​​the K-means algorithm is still to minimize the sum of squared deviations, but in the specific implementation, it adopts the method of successive iterative correction.

[0027] RedCap is a new technology standard protocol launched by the 3rd Generation Partnership Project (3GPP) in the 5G R17 stage. Its goal is to comprehensively improve the quality and coverage of 5G networks. It has deleted some functions and can be regarded as "lightweight 5G". RedCap has many application scenarios, including power, industrial data acquisition, security, Internet of Vehicles, wearable devices and other fields.

[0028] In the related art, the traditional cameras have the following problems when monitoring the target objects within the preset range: 1) The increase in the number of cameras leads to a decrease in the efficiency of information collection and an increase in blind spots; 2) The deployment of cameras often depends on the subjective consciousness of the installer and cannot be fully considered; 3) The unreasonable deployment of cameras leads to the inability of cameras to perform their due functions, etc. For example, in a community monitored by a community management system, the public security protection of the community needs to be strengthened. Therefore, there is currently a problem that it is impossible to achieve camera tracking of target objects within the preset range, resulting in failure to meet security requirements. In order to solve this problem, a relevant solution is provided in the embodiments of the present application.

[0029] According to an embodiment of the present application, a method embodiment of a method for determining a camera position is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal for implementing a method for determining a camera position. Figure 1 As shown, the computer terminal 10 may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0031] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0032] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the method for determining the position of the camera in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the method for determining the position of the camera described above is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0033] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0034] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .

[0035] In the above operating environment, the embodiment of the present application provides a flow chart of a method for determining a camera position, such as Figure 2 As shown, the following steps are included:

[0036] Step S202, obtaining target object attribute information within a preset range, wherein the target object attribute information at least includes a target object behavior indicator and a target object hardware indicator, the target object behavior indicator is used to indicate the behavior information associated with the target object, and the target object hardware indicator is used to indicate the hardware information associated with the target object during data transmission.

[0037] In the technical solution provided in step S202, before obtaining the target object attribute information within the preset range, all data within the preset range are obtained, wherein all data include the target object attribute information; the level to which all data belongs is determined; all data are clustered with each level as the cluster center, and the target data collected at each level is determined.

[0038] The following is a specific embodiment:

[0039] Currently, there is a large amount of repetitive and non-shared data collected in different communities. These data are entered into different platforms and are uniformly managed by the smart community management platform. The smart community management platform consists of infrastructure layer, platform layer, application layer, user layer, management and guarantee system and other parts. There are duplicate data at different levels in the preset range managed by the smart community management platform. Therefore, before obtaining the attribute information of the target object within the preset range, all data within the preset range is obtained, where all data includes the attribute information of the target object; the level to which all data belongs is determined; all data is clustered with each level as the clustering center, and the target data collected at each level is determined. For example, the following methods can be used:

[0040] First, all relevant data are obtained from the infrastructure layer, platform layer, application layer, user layer, management and security system of the smart community management platform. These data include but are not limited to video surveillance records, access control system data, IoT sensor information, community service usage records, basic information of residents, etc. The preset range can be data within a specific time period or data in a specific geographical area. Using the K-means++ algorithm, all data are clustered and analyzed with each layer as the clustering center. This step ensures that data at each level can be efficiently processed and accurately classified. Through clustering, data with similar characteristics are merged into the same category to reduce data redundancy and improve data processing efficiency. After clustering is completed, the specific target data collected at each level is determined. For example, the infrastructure layer may focus on video surveillance and IoT sensor data, while the application layer may focus more on community service usage records. Clarifying the data focus of each level will help to analyze and use data more targetedly when constructing behavioral feature portraits and target audience portraits (or monitoring audience portraits) in the future. The clustering process is as follows:

[0041] 1. Randomly select a data point from each level of data in the smart community management platform as the first cluster center. For example, the first data point in the infrastructure layer, the second data point in the platform layer, the third data point in the application layer, the fourth data point in the user layer, and the fifth data point in the management and security system can be selected as candidates for K center points, and one of them is randomly selected as the initial center u i .

[0042] 2. For each data point x that has not been selected as a center, calculate its distance to the closest cluster center that has been selected. For example, the distance is calculated by the following formula:

[0043] in, Indicates that x is closest to the selected center u i The distance between them; the distance here can also be Euclidean distance, Manhattan distance or other distance indicators suitable for measuring the similarity of data points.

[0044] 3. Use weighted probability distribution to randomly select a new data point as the cluster center, where the probability of data point x being selected as the new center is proportional to the square of its distance to the closest cluster center that has been selected. This strategy ensures that data points farther away from the current center are more likely to be selected as new centers, thereby improving the efficiency and accuracy of the selection of the initial center point.

[0045] Repeat steps 2 and 3 until K cluster centers (j=k) are selected. This process ensures that the K center points can cover the data set more evenly, reduces the number of iterations, and improves the stability and efficiency of clustering.

[0046] There are many ways to obtain the target object attribute information within a preset range, such as: obtaining log data associated with the target object; preprocessing the log data, extracting the target object behavior indicators and target object hardware indicators in the preprocessed log data, as well as the scene information and camera information associated with the target object; determining the target object attribute information based on the target object behavior indicators, target object hardware indicators, scene information and camera information. This method can efficiently extract key information from massive log data, laying a solid foundation for the subsequent construction of behavioral feature portraits and target audience portraits, and is particularly suitable for big data analysis and intelligent monitoring systems.

[0047] The following is a specific embodiment:

[0048] For the preset scope of management of the smart community management platform, the application layer managed by the smart community management platform mainly includes three categories of applications: community management, community services, and community security. The monitoring process for key personnel is a possibility of moving in different scenarios, and the monitoring data range should include different scenarios. Therefore, it is necessary to adopt a log hierarchical correlation mining strategy for the data source to ensure the integrity of data analysis. For example: use the log service to obtain the log data associated with the target object in the massive monitoring information managed by the smart community management platform, pre-process the log data, and mine the log data for correlation to obtain the target object behavior indicators, target object hardware indicators, and scene information and camera information associated with the target object; the target object behavior indicators at least include the correlation data of conversations, shopping and other behaviors generated by the current target object. The target object hardware indicators at least include the correlation relationships of the server CPU, memory, disk, process, virtual machine, etc. through which the data is transmitted, which can assist data analysis in complex scenarios to quickly find the target object through hardware positioning and obtain data for identification features from different angles. After merging the target object behavior indicators and the target object hardware indicators, the scene information (for example, the scene and building coordinates, conversation content ID, etc.) and camera information (for example, camera IP, associated camera IP, etc.) are marked to obtain the target object attribute information.

[0049] The above-mentioned target objects can be determined in the following ways: For example, identifying abnormal behaviors that do not conform to normal activity patterns, such as wandering in the community late at night, frequently entering sensitive areas, and abnormal contact with specific people. The objects of these abnormal behaviors will be marked as target objects. Some known people who need to be paid special attention, such as people with special needs in the community (such as elderly people living alone, minors who need supervision), residents who frequently report inappropriate behavior, etc., will be pre-marked as target objects. In the event of emergencies, such as intrusions, fires, medical emergencies, etc., key figures or suspicious individuals in the incident will be automatically marked as target objects for rapid response and processing. Long-term tracking and analysis of certain specific types of activities or personnel, such as residents who frequently use community resources, active participants in community activities, etc., will also be marked as target objects. For example, suspicious packages, vehicles that have been stagnant for a long time, unauthorized device access, etc., these entities or people associated with these events will also be considered target objects.

[0050] Step S204, determining a behavior feature portrait based on the target object attribute information, wherein the behavior feature portrait is used to represent the attribute distribution of different behavior features of the target object.

[0051] In the technical solution provided in step S204, there are multiple ways to determine the behavior feature portrait based on the target object attribute information, for example, the following methods can be used: clustering the target object behavior indicators in the target object attribute information to obtain multiple behavior feature sets, wherein each behavior feature set includes a behavior feature and a target object classified into the behavior feature; determining the attribute distribution of each behavior feature set, wherein the attribute distribution is used to represent the probability distribution of the attributes of each behavior feature in the corresponding behavior feature set; determining the behavior feature portrait based on the behavior feature set and the attribute distribution of the behavior feature set.

[0052] The following is a specific embodiment:

[0053] First, the data in the target object behavior indicators are cleaned and standardized to ensure the validity and consistency of each record, laying the foundation for subsequent cluster analysis. From the pre-processed target object behavior indicators, specific behavior indicators are extracted. The extracted behavior indicators are clustered using the K-means++ algorithm, and the initial cluster center is selected (refer to the above implementation method). The distance between each data point and the current cluster center is calculated, and a new center is selected based on the weighted probability distribution until K center points are determined. The standard K-means algorithm is applied for iterative clustering until the clustering results converge to obtain multiple behavior feature sets. Each behavior feature set contains a behavior feature and a target object divided into the behavior feature. For each behavior feature set, the attribute distribution of the behavior indicators is counted, such as the "frequent late night out" feature set may contain attributes such as time period distribution and location distribution of late night activities. Calculate the probability distribution of each attribute in the behavior feature set, which will be used for the subsequent construction of behavior feature portraits. Based on each behavior feature set and its attribute distribution, a behavior feature portrait is constructed to intuitively describe the typical behavior pattern of the target object in the behavior feature set. The portrait includes the attributes of the behavior characteristics (such as activity time, location, frequency, etc.), the quantitative description of these attributes, and the probability distribution of the attributes in the feature set. For example, the following formula can be used to determine the corresponding probability value of the feature value of attribute a in the attribute distribution of the audience of the behavior characteristic (the probability value of the corresponding attribute distribution in the behavior characteristic portrait):

[0054]

[0055] in, Indicates the value of the corresponding attribute of the person. Represents the probability value of the corresponding attribute distribution in the behavior feature profile.

[0056] Assume that the smart community management platform is concerned about the issue of "youth activity safety", and the target is the teenagers in the community. The following is a specific implementation example: Assume that K = 3, use the K-means++ algorithm to cluster the quantified behavioral indicators to obtain three behavioral feature sets: "Active after school", "Learning preference", and "Social intensive". Each feature set represents the behavioral patterns of teenagers who are active in the community after school, prefer to study in the community (such as the library), and frequently socialize in the community. For the "active after school" feature set, the analysis of the activity time is concentrated in the calculation time, location preference, and the probability distribution of frequency attributes in the "active after school" feature set, and the highest probabilities are: 16:00-19:00, location preference basketball courts and parks, and frequency is at least once every weekend.

[0057] Based on the above analysis, a portrait of the "active after-school" behavior feature set is constructed: teenagers often appear in community basketball courts and parks between 16:00 and 19:00 after school, and frequently participate in sports activities, with a frequency of at least once every weekend.

[0058] Step S206, determining a target audience portrait based on the target object attribute information and the behavior characteristic portrait, wherein the target audience portrait is used to represent the association between the behavior characteristics of the target object and the camera that collects the behavior characteristics.

[0059] In the technical solution provided in step S206, there are many ways to implement determining the target audience portrait based on the target object attribute information and the behavior feature portrait, for example: obtaining the target object hardware indicators in the target object attribute information and the scene information and camera information associated with the target object; associating the behavior feature portrait with the target object hardware indicators, the scene information and camera information associated with the target object, and determining the hardware requirements for each behavior feature set in the behavior feature portrait, wherein the hardware requirements are used to indicate the hardware resource usage and camera location of the target object under the corresponding behavior characteristics; determining the target audience portrait based on the hardware requirements.

[0060] The following is a specific embodiment:

[0061] The hardware indicators of the target object are obtained, including the association relationship between the server CPU, memory, disk, process, virtual machine, etc. through which the data is transmitted, and the behavior feature portrait obtained in step S206 is associated with the hardware indicators, scene information and camera information of the target object for analysis. Hardware requirements not only include equipment performance requirements, but may also involve the layout and number of cameras in specific scenarios. Hardware requirements are used to indicate the hardware resource usage and camera location of the target object under the corresponding behavior characteristics. For example, the behavior characteristic of the target object of teenagers being active after school, based on the teenagers associated in the behavior feature portrait who often appear in the community basketball court and park from 16:00 to 19:00 after school and frequently participate in sports activities, the hardware resource usage and camera location of the community basketball court and park during this time period can be used as hardware requirements, thereby obtaining the target audience portrait of the target object being the behavior characteristic of teenagers being active after school. The target audience portrait integrates the target object attribute information, the behavior feature portrait and its hardware requirements to construct the target audience portrait. The portrait not only describes the behavior pattern of the target object, but also includes the hardware configuration information that meets the monitoring requirements under these modes, providing a basis for the smart community management platform to plan hardware resource allocation and optimize monitoring strategies.

[0062] Step S208, determining the location of the camera based on the target audience portrait.

[0063] In the technical solution provided in step S208, there are multiple ways to determine the location of the camera based on the target audience portrait, for example: determining a first behavior feature set corresponding to the first target object in the behavior feature portrait, wherein the first target object is any target object; determining a first hardware requirement corresponding to the first behavior feature set in the target audience portrait; and determining the location of the camera based on the first hardware requirement.

[0064] The following is a specific embodiment:

[0065] When the first target object is a teenager, the first behavioral feature set corresponding to the behavioral feature portrait is active after school. The first hardware requirement corresponding to active after school in the target audience portrait is the hardware resource usage and camera location of the community basketball court and park during this time period. The location of the camera can be directly determined by the hardware requirement, so as to carry out key monitoring of existing cameras or deployment of new cameras. The camera can be a camera that supports the RedCap protocol. In large-scale distributed scenarios, the application demand data volume is large and the transmission protocol requirements are high. There are many application scenarios using RedCap. The "lightweight 5G" feature efficiently transmits the business points and solution targets involved in the images. Among them, the business point is the focus on different requirements for pictures in different scenarios. For example, when the camera data transmission image is applied to the security monitoring system, the image requirements focus on clarity and resolution, etc., and the business point includes clarity and resolution.

[0066] When the monitoring scenes corresponding to multiple cameras overlap, the transmission nodes corresponding to the overlapping data of the multiple cameras in the monitoring scenes are determined; two adjacent transmission nodes are determined as a main node, and the main node manages the transmission data of the cameras corresponding to the two adjacent transmission nodes.

[0067] The following is a specific embodiment:

[0068] The three main scenarios and sub-scenarios of community management, community services, and community security in the application layer of the smart community management platform include video surveillance, access control, entrance and exit personnel, vehicles, etc. Information is provided to provide video data such as videos and pictures, which are matched with IoT sensor data. If the matching data has overlapping scenarios and sub-scenarios, the nodes with adjacent relationships between overlapping data transmissions are shrunk into a new node according to the node contraction algorithm to manage the transmission data of the two groups of cameras. This improves network utilization and the timeliness of key personnel tracking.

[0069] Node contraction is to contract a node and its neighboring nodes into a new node. i is a very important core node. After shrinking it, the entire network will be better cohesive. The most typical example is that after the core node of a star network shrinks, the entire network will condense into a large node. For example, the more convenient the connections between people in a social network are (the smaller the average shortest path length d), the fewer people there are (the smaller the number of nodes n), and the higher the cohesion of the network. Therefore, the cohesion of the network is defined as

[0070]

[0071] Among them, d ij Indicates v i With v j The shortest path length.j `For another not with v i Repeated nodes, when n = 1, let the network cohesion Apparently The node shrinkage method mainly examines the change in network cohesion before and after node shrinkage, thereby determining the importance of nodes in the network. Therefore, the node v is defined as i The importance index IMC(i) is:

[0072]

[0073] in, Indicates that the node v i The cohesion of the network obtained after shrinkage can be further determined by the following formula:

[0074]

[0075] Where n represents the total number of nodes in the network, d(G) represents the average shortest path length of the original network (G), and k i Represents node v i The number of neighbor nodes directly connected to v i The number of connected nodes, d(G --i ) indicates that the network (G) is i The average shortest path length after .

[0076] The importance of a node in the node contraction method is determined by the number of its neighbors and the position of the node in the network path. Since the average path length of the network must be calculated each time a node is contracted, the time complexity is relatively high, so the node contraction method is not suitable for calculating large-scale networks. The connection between the cameras in this application and the platform is a dedicated network line and does not have this disadvantage.

[0077] The system can also be processed in the event of an attack: the target file stored in the database is obtained, where the target file is a file used to store target object attribute information; after identifying that the target file has been tampered with, the attack path corresponding to the target file is determined; files overlapping with the attack path are marked as isolated files, and files that do not overlap with the attack path are marked as non-isolated files; the isolated files are deleted, and the processing results are fed back to the terminal.

[0078] For example, the following is a specific embodiment:

[0079] First, after the deployed target file is tampered with, when the path and related information of the ransomware process file are traced back through fanotify technology, the traceability range is first increased by combining the network nodes included in the smart business chain before sending it to the web front end. Among them, fanotify is a file monitoring technology that is often used as malicious access control for antivirus software or virus programs. When the user receives an alert that the file has been encrypted and tampered with, the path of the target file, and other information on the front end, he can choose to isolate or delete the target file. At the same time, it is compared with all nodes in the smart business chain, and the nodes in the non-repeated part are marked as non-virus isolation to prevent misoperation when isolating or deleting the target file. Then, the processing results are fed back. After the virus file is isolated or deleted, the processing results are fed back to the front end to tell the user whether the processing is successful.

[0080] You can also build a cost model, calculate the benefit-cost ratio, and calculate the network traffic-related costs of the tracking target object. For example, the total actual resource of the smart business chain nodes and links is 10G traffic, and the proportion of non-isolated files is 60%. The actual resource impact caused by security hazards is 40%. Then, based on the main indicators of network hazards, the specific cost of the hazard can be further obtained from the 40%.

[0081] From the perspective of infrastructure, the benefit is determined by the resource requirements of the network, including node resource requirements and link resource requirements, and the mapping benefit I(G v ) is determined by the following formula:

[0082]

[0083] in, is the computing capacity requirement of virtual link j, is the computing capacity requirement of virtual node i, α is the weight factor, N v is the set of virtual nodes, L v A collection of virtual links.

[0084] The overhead of a mapped virtual network is defined as the sum of the actual resources allocated by the underlying network to the virtual network. The mapping overhead C(G v ) is determined by the following formula:

[0085]

[0086] in, is the computing capacity requirement of virtual link j, is the computing power requirement of virtual node i, α is the weight factor, represents the actual path length occupied by virtual link j on the underlying network after being mapped, N v is the set of virtual nodes, L vA collection of virtual links.

[0087] After determining the definitions of mapping benefit and mapping overhead, the benefit-overhead ratio can be defined as the ratio of the two (mapping benefit / mapping overhead).

[0088] Finally, the benefit-to-cost ratio is recalculated after node contraction optimization to obtain a new benefit-to-cost ratio. If the new benefit-to-cost ratio is lower than the above benefit-to-cost ratio, the new benefit-to-cost ratio is used as the optimal benefit-to-cost ratio; otherwise, the above benefit-to-cost ratio is used as the optimal benefit-to-cost ratio. In this way, the benefit-to-cost ratio of network resources can be scientifically calculated based on the behavioral feature set of the target object, and the resource allocation strategy can be continuously adjusted through the optimization algorithm to ensure the efficient use of network resources while meeting the monitoring efficiency and security requirements.

[0089] Through the above steps, the K-means++ algorithm is used to aggregate and classify data at different layers to clarify the data source and collection channel to avoid repeated collection, and the log layered correlation mining strategy is used for the data source to ensure the integrity of data analysis. And by building a target audience portrait, it is faster to match the target audience portrait of the current target object to analyze the situation of the target object, accurately identify the behavior pattern and hardware requirements of the target object, and provide a scientific basis for the reasonable layout of the camera, especially in large public places or scenes that require refined management, which can significantly improve monitoring efficiency and safety.

[0090] The present application embodiment provides a structural diagram of a device for determining a camera position, such as Figure 3 As shown, including:

[0091] The acquisition module 302 is used to obtain the target object attribute information within a preset range, wherein the target object attribute information at least includes a target object behavior indicator and a target object hardware indicator, the target object behavior indicator is used to indicate the behavior information associated with the target object, and the target object hardware indicator is used to indicate the hardware information associated with the target object during data transmission.

[0092] The acquisition module 302 is also used to acquire all data within a preset range, wherein all data includes target object attribute information; determine the level to which all data belongs; cluster all data with each level as the cluster center, and determine the target data collected at each level.

[0093] The acquisition module 302 is also used to obtain log data associated with the target object; after preprocessing the log data, the target object behavior indicators and target object hardware indicators in the preprocessed log data as well as the scene information and camera information associated with the target object are extracted; based on the target object behavior indicators, target object hardware indicators, scene information and camera information, the target object attribute information is determined.

[0094] The first determination module 304 is used to determine a behavior feature portrait based on the target object attribute information, wherein the behavior feature portrait is used to represent the attribute distribution of different behavior features of the target object.

[0095] The first determination module 304 is also used to cluster the target object behavior indicators in the target object attribute information to obtain multiple behavior feature sets, wherein each behavior feature set includes a behavior feature and a target object classified into the behavior feature; determine the attribute distribution of each behavior feature set, wherein the attribute distribution is used to represent the probability distribution of the attributes of each behavior feature in the corresponding behavior feature set; and determine the behavior feature portrait based on the behavior feature set and the attribute distribution of the behavior feature set.

[0096] The second determination module 306 is used to determine the target audience portrait based on the target object attribute information and the behavior feature portrait, wherein the target audience portrait is used to represent the association between the behavior feature of the target object and the camera that collects the behavior feature.

[0097] The second determination module 306 is also used to obtain the target object hardware indicators in the target object attribute information and the scene information and camera information associated with the target object; associate the behavior feature portrait with the target object hardware indicators, the scene information and camera information associated with the target object, and determine the hardware requirements for each behavior feature set in the behavior feature portrait, wherein the hardware requirements are used to indicate the hardware resource usage and camera location of the target object under the corresponding behavior characteristics; determine the target audience portrait based on the hardware requirements.

[0098] The third determination module 308 is used to determine the location of the camera based on the target audience portrait.

[0099] The third determination module 308 is also used to determine the first behavior feature set corresponding to the first target object in the behavior feature portrait, wherein the first target object is any target object; determine the first hardware requirement corresponding to the first behavior feature set in the target audience portrait; and determine the location of the camera based on the first hardware requirement.

[0100] The third determination module 308 is also used to determine the transmission nodes corresponding to the overlapping data of multiple cameras in the monitoring scenes when there is overlap between the monitoring scenes corresponding to multiple cameras; two adjacent transmission nodes are determined as a main node, and the main node manages the transmission data of the cameras corresponding to the two adjacent transmission nodes.

[0101] The third determination module 308 is also used to obtain the target file stored in the database, wherein the target file is a file used to store target object attribute information; after identifying that the target file has been tampered with, determine the attack path corresponding to the target file; mark the file overlapping with the attack path as an isolated file, and mark the file that does not overlap with the attack path as a non-isolated file; delete the isolated file, and feed back the processing result to the terminal.

[0102] It should be noted that Figure 3 The camera position determination device shown is used to perform Figure 2 The camera position is determined by Figure 2 The relevant explanations in the method for determining the camera position in also apply to the device for determining the camera position, and will not be repeated here.

[0103] It should be noted that the various modules in the above-mentioned camera position determination device can be program modules (for example, a set of program instructions that implement a certain specific function) or hardware modules. For the latter, it can be expressed in the following forms, but is not limited to this: the expression form of each of the above-mentioned modules is a processor, or the functions of each of the above-mentioned modules are implemented by a processor.

[0104] The embodiment of the present application also provides a non-volatile storage medium, the non-volatile storage medium includes a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the above method for determining the position of the camera. For example, the target object attribute information within a preset range is obtained, wherein the target object attribute information at least includes a target object behavior indicator and a target object hardware indicator, the target object behavior indicator is used to indicate the behavior information associated with the target object, and the target object hardware indicator is used to indicate the hardware information associated with the target object during the data transmission process; based on the target object attribute information, a behavior feature portrait is determined, wherein the behavior feature portrait is used to represent the attribute distribution of different behavior features of the target object; based on the target object attribute information and the behavior feature portrait, a target audience portrait is determined, wherein the target audience portrait is used to represent the association between the behavior features of the target object and the camera that collects the behavior features; based on the target audience portrait, the camera location is determined.

[0105] The embodiment of the present application also provides an electronic device, the electronic device includes a processor, the processor is used to run a program, wherein the above method for determining the position of a camera is executed when the program is running. For example, the target object attribute information within a preset range is obtained, wherein the target object attribute information at least includes a target object behavior indicator and a target object hardware indicator, the target object behavior indicator is used to indicate the behavior information associated with the target object, and the target object hardware indicator is used to indicate the hardware information associated with the target object during data transmission; based on the target object attribute information, a behavior feature portrait is determined, wherein the behavior feature portrait is used to represent the attribute distribution of different behavior features of the target object; based on the target object attribute information and the behavior feature portrait, a target audience portrait is determined, wherein the target audience portrait is used to represent the association between the behavior features of the target object and the camera that collects the behavior features; based on the target audience portrait, the camera location is determined.

[0106] According to another aspect of the embodiment of the present application, a computer program product is also provided, including a computer program, which implements the above method for determining the position of a camera when executed by a processor. For example, the target object attribute information within a preset range is obtained, wherein the target object attribute information at least includes a target object behavior indicator and a target object hardware indicator, the target object behavior indicator is used to indicate the behavior information associated with the target object, and the target object hardware indicator is used to indicate the hardware information associated with the target object during data transmission; based on the target object attribute information, a behavior feature portrait is determined, wherein the behavior feature portrait is used to represent the attribute distribution of different behavior features of the target object; based on the target object attribute information and the behavior feature portrait, a target audience portrait is determined, wherein the target audience portrait is used to represent the association between the behavior features of the target object and the camera that collects the behavior features; based on the target audience portrait, the camera location is determined.

[0107] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0108] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, 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, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0109] The units described 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 units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0110] 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.

[0111] If the 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 storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the relevant technology or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0112] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for determining a camera position, characterized in that: include: Acquire target object attribute information within a preset range, wherein the target object attribute information at least includes a target object behavior indicator and a target object hardware indicator, the target object behavior indicator is used to indicate behavior information associated with the target object, and the target object hardware indicator is used to indicate hardware information associated with the target object during data transmission; Determining a behavior feature portrait based on the target object attribute information, wherein the behavior feature portrait is used to represent the attribute distribution of different behavior features of the target object; Determining a target audience portrait based on the target object attribute information and the behavior characteristic portrait, wherein the target audience portrait is used to represent the association between the behavior characteristics of the target object and the camera that collects the behavior characteristics; The location of the camera is determined based on the target audience portrait.

2. The method according to claim 1, characterized in that Before obtaining the target object attribute information within a preset range, the method further includes: Acquire all data within the preset range, wherein all data includes attribute information of the target object; Determine the level to which all the data belongs; All the data are clustered with each level as the cluster center to determine the target data collected at each level.

3. The method according to claim 1, characterized in that Get the target object attribute information within the preset range, including: Obtaining log data associated with the target object; After preprocessing the log data, extracting the target object behavior indicator and the target object hardware indicator, as well as the scene information and camera information associated with the target object from the preprocessed log data; The target object attribute information is determined according to the target object behavior indicator, the target object hardware indicator, the scene information and the camera information.

4. The method according to claim 1, characterized in that Determining a behavior feature profile based on the target object attribute information includes: Clustering the target object behavior indicators in the target object attribute information to obtain a plurality of behavior feature sets, wherein each behavior feature set includes a behavior feature and a target object classified into the behavior feature; Determine the attribute distribution of each behavior feature set, wherein the attribute distribution is used to represent the probability distribution of the attribute of each behavior feature in the corresponding behavior feature set; The behavior feature profile is determined based on the behavior feature set and the attribute distribution of the behavior feature set.

5. The method according to claim 3, characterized in that: Determining a target audience portrait based on the target object attribute information and the behavior characteristic portrait includes: Acquire the target object hardware indicators in the target object attribute information and the scene information and camera information associated with the target object; Associating the behavior feature portrait with the hardware indicators of the target object, the scene information associated with the target object, and the camera information, and determining the hardware requirements of each behavior feature set in the behavior feature portrait, wherein the hardware requirements are used to indicate the hardware resource usage and camera location of the target object under the corresponding behavior feature; The target audience profile is determined based on the hardware requirements.

6. The method according to claim 1, characterized in that Determining the location of the camera based on the target audience portrait includes: Determine a first behavior feature set corresponding to a first target object in the behavior feature portrait, wherein the first target object is any one of the target objects; Determine a first hardware requirement corresponding to the first behavior feature set in the target audience portrait; The location of the camera is determined based on the first hardware requirement.

7. The method according to claim 1, characterized in that The method further comprises: In the case where the monitoring scenes corresponding to the multiple cameras overlap, determining the transmission nodes corresponding to the overlapping data of the multiple cameras in the monitoring scenes; Two adjacent transmission nodes are determined as a master node, and the master node manages the transmission data of the cameras corresponding to the two adjacent transmission nodes.

8. The method according to claim 1, characterized in that The method further comprises: Acquire a target file stored in a database, wherein the target file is a file used to store attribute information of the target object; After identifying that the target file has been tampered with, determining an attack path corresponding to the target file; Marking files that overlap with the attack path as isolated files, and marking files that do not overlap with the attack path as non-isolated files; The isolated file is deleted, and the processing result is fed back to the terminal.

9. A device for determining a camera position, characterized in that: include: an acquisition module, configured to acquire target object attribute information within a preset range, wherein the target object attribute information at least includes a target object behavior indicator and a target object hardware indicator, wherein the target object behavior indicator is used to indicate behavior information associated with the target object, and the target object hardware indicator is used to indicate hardware information associated with the target object during data transmission; A first determination module, configured to determine a behavior feature portrait based on the target object attribute information, wherein the behavior feature portrait is used to represent the attribute distribution of different behavior features of the target object; A second determination module is used to determine a target audience portrait based on the target object attribute information and the behavior characteristic portrait, wherein the target audience portrait is used to represent the association between the behavior characteristics of the target object and the camera that collects the behavior characteristics; The third determination module is used to determine the location of the camera based on the target audience portrait.

10. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the method for determining the camera position as described in any one of claims 1 to 8.

11. An electronic device, characterized in that: include: A memory and a processor, wherein the processor is used to run a program stored in the memory, wherein the method for determining the camera position described in any one of claims 1 to 8 is executed when the program is run.

12. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the method for determining the camera position described in any one of claims 1 to 8 is implemented.

Images