Configuration method and device for monitoring equipment in multiple scenes

Abstract

The invention discloses a configuration method and device for monitoring equipment in multiple scenes, and relates to the field of artificial intelligence and big data, and the method comprises the steps: obtaining K business scenes of target monitoring equipment, and determining a monitoring demand for each business scene; determining a to-be-configured target algorithm based on the monitoring requirement of the target monitoring equipment in each business scene, and configuring algorithm parameters and an algorithm analysis mode for the target algorithm; determining an alarm triggering rule based on the algorithm parameters; and generating an algorithm analysis task based on the business scene, the monitoring demand, the target algorithm, the algorithm parameter, the algorithm analysis mode and the alarm triggering rule, and issuing the algorithm analysis task to the target monitoring device. According to the method and the device, the technical problem of low reuse rate of a mode of performing single algorithm configuration on the monitoring equipment in related technologies is solved.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence and big data, and in particular, to a method and device for configuring monitoring devices in multiple scenarios. Background Art

[0002] Mid-high point video monitoring is a video monitoring technology that uses cameras installed at mid-high positions for remote and large-area monitoring. This monitoring method is usually applied to scenarios such as open areas, urban areas, nature reserves, public facilities, and traffic arteries. Its core advantage lies in being able to cover a wider monitoring area, capture more monitoring details, and at the same time reduce monitoring blind spots caused by obstacles such as buildings and terrain.

[0003] With the rapid development of artificial intelligence and cloud computing technologies, mid-high point video monitoring systems have gradually initiated a profound transformation in the fields of technology and application. This monitoring mode, with its wide coverage, comprehensive perspective, and strong data processing capabilities, is being widely applied in many fields such as urban management, environmental protection, traffic safety, emergency response, and natural resource monitoring. However, with the progress of technology and the in-depth application, mid-high point video monitoring systems are also facing challenges in meeting the needs of multiple customers and multiple scenarios: First, the diversity of the needs of multiple customers. In application scenarios such as smart cities, smart parks, forest and grassland fire prevention, the video monitoring needs of different customers are not the same. For example, urban management departments may be more concerned about public safety, traffic conditions, and crowd behavior analysis; environmental protection agencies may need to monitor air quality, water pollution, and wildlife activities; while the forest and grassland field may focus on fire warning and illegal intrusion detection. This diversity of needs requires mid-high point video monitoring systems to be able to provide highly customizable monitoring services to meet the specific needs of different customers. Second, the complexity of monitoring in multiple scenarios. Even for the same customer, the monitoring needs may change in different scenarios or time points. For example, a scenic area may require high-frequency pedestrian flow statistics and security monitoring during the day, while at night, the focus may shift to fire prevention and wildlife protection. This rapid switching between scenarios and changing needs pose higher requirements for the flexibility and response speed of mid-high point video monitoring systems, and the system needs to be able to quickly adapt to different scenarios and accurately adjust monitoring strategies.

[0004] In the related art, the method of configuring a single algorithm for monitoring devices has the problem of low reuse rate, making it difficult to meet the needs of multiple users and multiple scenarios, and also difficult to adapt to the development needs of artificial intelligence and cloud computing in the current environment.

[0005] In response to the above problems, no effective solution has been proposed yet. Summary of the Invention

[0006] An embodiment of the present invention provides a configuration method and device for monitoring devices in multiple scenarios, so as to at least solve the technical problem of low reuse rate in the related art of configuring a single algorithm for monitoring devices.

[0007] According to one aspect of the embodiments of the present invention, a configuration method for monitoring devices in multiple scenarios is provided, including: obtaining K service scenarios of a target monitoring device, and determining monitoring requirements for each of the service scenarios, where K is a positive integer; determining a target algorithm to be configured based on the monitoring requirements of the target monitoring device in each of the service scenarios, and configuring algorithm parameters and an algorithm analysis method for the target algorithm; determining an alarm trigger rule based on the algorithm parameters; generating an algorithm analysis task based on the service scenario, the monitoring requirements, the target algorithm, the algorithm parameters, the algorithm analysis method, and the alarm trigger rule, and sending the algorithm analysis task to the target monitoring device.

[0008] Further, the types of the algorithm parameters at least include: algorithm parameters based on tripwire judgment, algorithm parameters based on target duration, algorithm parameters based on target classification, algorithm parameters based on quantity threshold, algorithm parameters based on percentage, and algorithm parameters based on feature recognition. The configuration method for monitoring devices in multiple scenarios further includes: for a target algorithm, selecting M types of algorithm parameters for combined configuration, where M is a positive integer.

[0009] Further, the algorithm analysis methods at least include: picture analysis method and real-time stream analysis method. The step of configuring algorithm parameters and an algorithm analysis method for the target algorithm includes: when at least one of the types of algorithm parameters configured for the target algorithm is the algorithm parameter based on tripwire judgment and the algorithm parameter based on target duration, determining the algorithm analysis method of the target algorithm as the real-time stream analysis method; when at least one of the types of algorithm parameters configured for the target algorithm is the algorithm parameter based on target classification, the algorithm parameter based on quantity threshold, the algorithm parameter based on percentage, and the algorithm parameter based on feature recognition, determining the algorithm analysis method of the target algorithm as the picture analysis method, where for a target algorithm configured with multiple types of algorithm parameters, the priority of the real-time stream analysis method is defined to be higher than the priority of the picture analysis method.

[0010] Further, the step of determining an alarm trigger rule based on the algorithm parameters includes: in the case where the type of the algorithm parameter is the algorithm parameter based on tripwire judgment, setting a warning reference line and a trigger direction; determining the tripwire alarm trigger rule based on the warning reference line and the trigger direction as: triggering a tripwire alarm when it is detected that a target object crosses the warning reference line along the trigger direction.

[0011] Further, the steps of determining the alarm trigger rule based on the algorithm parameters include: when the type of the algorithm parameters is the algorithm parameters based on the target duration, setting the monitoring area and the target stay duration threshold; determining the duration alarm trigger rule based on the monitoring area and the target stay duration as: triggering a duration alarm when it is monitored that the stay duration of the target object in the monitoring area is greater than the target stay duration threshold.

[0012] Further, the steps of determining the alarm trigger rule based on the algorithm parameters include: when the type of the algorithm parameters is the algorithm parameters based on the target classification, setting the monitoring target category; generating a dictionary value based on the monitoring target category and storing the dictionary value in a dictionary, wherein when generating an algorithm analysis task, selecting N dictionary values as monitoring targets based on the monitoring requirements, and N is a positive integer; determining the classification alarm rule based on the monitoring target category and the dictionary value as: classifying the monitored target object and generating a dictionary value, and triggering a classification alarm when the generated dictionary value belongs to the selected monitoring targets.

[0013] Further, the steps of determining the alarm trigger rule based on the algorithm parameters include: when the type of the algorithm parameters is the algorithm parameters based on the quantity threshold, setting the target quantity threshold and generating a threshold determination condition based on the target quantity threshold; determining the quantity alarm rule based on the target quantity threshold and the threshold determination condition as: triggering a quantity alarm when it is monitored that the quantity of the target object meets the threshold determination condition.

[0014] Further, the steps of determining the alarm trigger rule based on the algorithm parameters include: when the type of the algorithm parameters is the algorithm parameters based on the percentage, setting the percentage value and generating a percentage determination condition based on the percentage value; determining the quantity alarm rule based on the percentage value and the percentage determination condition as: triggering a percentage alarm when it is monitored that the proportion of the target object meets the percentage determination condition.

[0015] Further, the steps of determining the alarm trigger rule based on the algorithm parameters include: when the type of the algorithm parameters is the algorithm parameters based on feature recognition, setting the target recognition feature; determining the quantity alarm rule based on the target recognition feature as: triggering a feature alarm when the target recognition feature is monitored.

[0016] According to another aspect of the embodiments of the present invention, there is also provided a configuration device for a monitoring device in multiple scenarios, including: an acquisition unit, configured to acquire K service scenarios of a target monitoring device, and determine monitoring requirements for each of the service scenarios, where K is a positive integer; a configuration unit, configured to determine a target algorithm to be configured based on the monitoring requirements of the target monitoring device in each of the service scenarios, and configure algorithm parameters and an algorithm analysis method for the target algorithm; a determination unit, configured to determine an alarm trigger rule based on the algorithm parameters; a generation unit, configured to generate an algorithm analysis task based on the service scenario, the monitoring requirements, the target algorithm, the algorithm parameters, the algorithm analysis method, and the alarm trigger rule, and send the algorithm analysis task to the target monitoring device.

[0017] Further, the types of the algorithm parameters at least include: algorithm parameters based on tripwire judgment, algorithm parameters based on target duration, algorithm parameters based on target classification, algorithm parameters based on quantity threshold, algorithm parameters based on percentage, and algorithm parameters based on feature recognition. The configuration device for the monitoring device in multiple scenarios further includes: a first configuration module, configured to, for a target algorithm, select M types of algorithm parameters for combined configuration, where M is a positive integer.

[0018] Further, the algorithm analysis methods at least include: a picture analysis method and a real-time stream analysis method. The configuration unit includes: a first determination module, configured to, when at least one of the types of the algorithm parameters configured for the target algorithm is an algorithm parameter based on tripwire judgment and an algorithm parameter based on target duration, determine that the algorithm analysis method of the target algorithm is the real-time stream analysis method; a second determination module, configured to, when at least one of the types of the algorithm parameters configured for the target algorithm is an algorithm parameter based on target classification, an algorithm parameter based on quantity threshold, an algorithm parameter based on percentage, and an algorithm parameter based on feature recognition, determine that the algorithm analysis method of the target algorithm is the picture analysis method, where, for a target algorithm configured with multiple types of algorithm parameters, it is defined that the priority of the real-time stream analysis method is higher than the priority of the picture analysis method.

[0019] Further, the determination unit includes: a first setting module, configured to, when the type of the algorithm parameters is an algorithm parameter based on tripwire judgment, set a warning reference line and a trigger direction; a third determination module, configured to determine, based on the warning reference line and the trigger direction, that the tripwire alarm trigger rule is: trigger a tripwire alarm when it is detected that a target object crosses the warning reference line along the trigger direction.

[0020] Further, the determining unit further includes: a second setting module, configured to set a monitoring area and a target residence duration threshold when the type of the algorithm parameter is an algorithm parameter based on a target duration; a fourth determining module, configured to determine, based on the monitoring area and the target residence duration, that the duration alarm trigger rule is: triggering a duration alarm when it is monitored that the residence duration of the target object in the monitoring area is greater than the target residence duration threshold.

[0021] Further, the determining unit further includes: a third setting module, configured to set a monitoring target category when the type of the algorithm parameter is an algorithm parameter based on a target classification; a first generating module, configured to generate a dictionary value based on the monitoring target category and store the dictionary value in a dictionary, wherein when generating an algorithm analysis task, N dictionary values are selected as monitoring targets based on monitoring requirements, and N is a positive integer; a fifth determining module, configured to determine, based on the monitoring target category and the dictionary value, that the classification alarm rule is: triggering a classification alarm when the monitoring result indicates the existence of the selected monitoring target.

[0022] Further, the determining unit further includes: a fourth setting module, configured to set a target quantity threshold when the type of the algorithm parameter is an algorithm parameter based on a quantity threshold, and generate a threshold determination condition based on the target quantity threshold; a sixth determining module, configured to determine, based on the monitoring target category and the dictionary value, that the classification alarm rule is: classifying the monitored target object and generating a dictionary value, and triggering a classification alarm when the generated dictionary value belongs to the selected monitoring target.

[0023] Further, the determining unit further includes: a fifth setting module, configured to set a percentage value when the type of the algorithm parameter is an algorithm parameter based on a percentage, and generate a percentage determination condition based on the percentage value; a seventh determining module, configured to determine, based on the percentage value and the percentage determination condition, that the quantity alarm rule is: triggering a percentage alarm when it is monitored that the ratio of the target object meets the percentage determination condition.

[0024] Further, the determining unit further includes: a sixth setting module, configured to set a target recognition feature when the type of the algorithm parameter is an algorithm parameter based on feature recognition; an eighth determining module, configured to determine, based on the target recognition feature, that the quantity alarm rule is: triggering a feature alarm when the target recognition feature is monitored.

[0025] In this application, the corresponding algorithms are configured for monitoring devices in multiple scenarios through the following steps: obtaining K service scenarios of the target monitoring device, determining the monitoring requirements for each service scenario, where K is a positive integer; determining the target algorithms to be configured based on the monitoring requirements of the target monitoring device in each service scenario, and configuring algorithm parameters and algorithm analysis methods for the target algorithms; determining the alarm trigger rules based on the algorithm parameters; generating algorithm analysis tasks based on the service scenarios, monitoring requirements, target algorithms, algorithm parameters, algorithm analysis methods, and alarm trigger rules, and sending the algorithm analysis tasks to the target monitoring device.

[0026] In this application, the monitoring requirements are determined based on the service scenarios used by the monitoring device, and appropriate algorithms are selected based on the monitoring requirements. The analysis methods and algorithm parameters are configured for the selected algorithms, and the alarm trigger rules corresponding to the algorithms are determined to generate algorithm analysis tasks, thereby associating the service scenarios with specific algorithm analysis tasks, meeting the monitoring requirements of multiple users and multiple scenarios, achieving the purpose of reusing the same monitoring device, and obtaining the technical effect of improving the reuse rate of the monitoring device. Furthermore, it solves the technical problem of low reuse rate in the related art where a single algorithm configuration method is used for monitoring devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings described herein are used to provide a further understanding of the present invention, form a part of this application, and the schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0028] Figure 1 A hardware structure block diagram of a computer terminal (or mobile device) for implementing a configuration method of a monitoring device in multiple scenarios is shown;

[0029] Figure 2 It is a flowchart of an optional configuration method of a monitoring device in multiple scenarios according to an embodiment of the present invention;

[0030] Figure 3 It is a schematic diagram of an optional configuration process of a monitoring device in multiple scenarios according to an embodiment of the present invention;

[0031] Figure 4 It is an example diagram of an algorithm configuration of a monitoring device in multiple scenarios according to an embodiment of the present invention;

[0032] Figure 5 It is a schematic diagram of an optional configuration device of a monitoring device in multiple scenarios according to an embodiment of the present invention;

[0033] Figure 6 It is a hardware structure block diagram of an electronic device (or mobile device) for executing a configuration method of a monitoring device in multiple scenarios according to an embodiment of the present invention. Detailed implementation manners

[0034] In order to enable those skilled in the art of the present technology to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0035] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0036] To facilitate the understanding of the present invention by those skilled in the art, some terms or nouns involved in the embodiments of the present invention are explained below:

[0037] URL address, the full name is Uniform Resource Locator, which is an address used to identify and locate resources (such as web pages, images, files, etc.) on the Internet. In the field of video surveillance, the URL address is mainly used for real-time stream (video) analysis. That is, a camera or a video server will provide a URL, which points to the real-time source of the video stream, and an algorithm or a monitoring system can pull and analyze the video data in real time through this URL address.

[0038] It should be noted that the configuration method and device of the monitoring device in multiple scenarios in the present application can be used in the field of blockchain technology when configuring algorithm tasks for the monitoring device in multiple scenarios, and can also be used in any field other than the field of blockchain technology when configuring algorithm tasks for the monitoring device in multiple scenarios. The application field of the configuration method and device of the monitoring device in multiple scenarios in the present application is not limited.

[0039] It should be noted that the information collected in this application (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) are information and data that have been authorized by the user or fully authorized by all parties. Moreover, for the processing of relevant data such as collection, storage, use, processing, transmission, provision, disclosure, and application, all comply with relevant laws, regulations, and standards, adopt necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse. For example, there are interfaces set between this system and relevant users or institutions to provide corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0040] The following embodiments of the present invention can be applied to the configuration systems / applications / devices of monitoring devices in various multi-scenario environments. The present invention proposes an algorithm configuration method for multi-scenario and multi-parameter video monitoring, providing a personalized parameter configuration method combined with the actual needs of customers, flexibly meeting the needs of different customers, making the monitoring effect more accurate, and effectively meeting the monitoring needs of different customers in different scenarios.

[0041] The present invention will be described in detail below in conjunction with each embodiment.

[0042] Embodiment 1

[0043] According to an embodiment of the present invention, an embodiment of a method for configuring a monitoring device in a multi-scenario environment 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 the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0044] The method embodiment provided by the first embodiment of this application can be executed on a mobile terminal, a computer terminal, or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal (or mobile device) for implementing the method for configuring a monitoring device in a multi-scenario environment is shown. As Figure 1 shown, the computer terminal 10 (or mobile device) may include one or more (shown as 102a, 102b,..., 102n in the figure) 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 device 106 for communication functions. In addition, it may further 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. Those of ordinary skill in the art can understand, Figure 1The structure shown is only schematic and does not limit the structure of the above-mentioned electronic device. For example, the computer terminal 10 may further include more or fewer components than those shown in Figure 1 or have a configuration different from that shown in Figure 1 .

[0045] It should be noted that one or more of the above-mentioned processors 102 and / or other data processing circuits can generally be referred to as "data processing circuits" herein. The data processing circuit can be embodied in software, hardware, firmware or any combination thereof, in whole or in part. In addition, the data processing circuit can be a single independent processing module, or be incorporated in whole or in part into any one of other elements in the computer terminal 10 (or mobile device). As involved in the embodiments of the present application, the data processing circuit is a kind of processor control (such as the selection of a variable resistor terminal path connected to an interface).

[0046] 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 configuration method of the monitoring device in multiple scenarios in the embodiments 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, implements the configuration method of the monitoring device in multiple scenarios. 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 memories, or other non-volatile solid-state memories. In some instances, the memory 104 may further include a memory remotely provided with respect to the processor 102, and these remote memories can be connected to the computer terminal 10 through a network. Examples of the above-mentioned network include but are not limited to the Internet, enterprise intranets, local area networks, mobile communication networks and their combinations.

[0047] The transmission device 106 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wireless network provided by the communication provider of the computer terminal 10. In one instance, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station and thus can communicate with the Internet. In one instance, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0048] The display can be, for example, a touch-screen liquid crystal display (LCD), which enables a user to interact with the user interface of the computer terminal 10 (or mobile device).

[0049] Under the above operating environment, the present application provides as Figure 2The configuration method of the monitoring device in multiple scenarios as shown, and the implementation entity of this method is the configuration system of the monitoring device in multiple scenarios. The embodiments of the present invention can implement a monitoring device to configure multiple algorithms, and an algorithm to configure multiple parameters. Different customers can reuse the monitoring device and algorithms to meet the monitoring requirements of multiple scenarios, effectively saving costs through the reuse of the monitoring device and algorithms.

[0050] Figure 2 It is a flowchart of an optional configuration method of the monitoring device in multiple scenarios according to an embodiment of the present invention. As Figure 2 shown, the method includes the following steps:

[0051] Step S201, obtain K business scenarios of the target monitoring device, and determine the monitoring requirements for each business scenario.

[0052] In the above step S201, the target monitoring device can be a specific camera used for medium and high point video monitoring, installed at a high point position overlooking a large area, or other monitoring cameras facing multiple users and multiple scenarios. Specifically, the monitoring range of medium and high point video monitoring is large, and the monitored content is also relatively large, which can meet the multiple monitoring requirements of multiple users. In addition, in the field of cloud computing, a monitoring device can also be rented by multiple users and used at different times to achieve the monitoring of different targets. The business scenario refers to the specific application occasion that the target monitoring device serves, such as urban traffic monitoring, forest wildlife monitoring, etc. The K business scenarios indicate that the target monitoring device faces a multi-scenario monitoring environment, and K is a positive integer. The monitoring requirement refers to the functional requirements and performance indicators expected by the user for the monitoring device in a certain business scenario, including but not limited to target recognition, alarm mechanism, monitoring period, etc.

[0053] In the embodiments of the present invention, by carefully collecting and analyzing the business scenarios of the monitoring device and the customer monitoring requirements, it provides clear guidance and basis for a series of operations such as subsequent algorithm configuration, task generation, and task distribution, thereby ensuring the efficient, intelligent, and low-cost operation of the video monitoring system in multiple customers and multiple scenarios.

[0054] Step S202, determine the target algorithm to be configured based on the monitoring requirements of the target monitoring device in each business scenario, and configure algorithm parameters and algorithm analysis methods for the target algorithm.

[0055] In the above step S202, after determining the monitoring requirements of the target monitoring device, for the monitoring requirements in each business scenario, the system will screen and determine the most suitable "target algorithm" from the pre-constructed algorithm library. The selection of the target algorithm is related to the user's monitoring scenario requirements, monitoring target requirements, monitoring effect requirements, user resource constraint requirements, user system compatibility requirements, etc. The resource constraint requirements include computing power resources, network bandwidth, storage capacity, etc. The above algorithm library contains a variety of intelligent algorithms optimized for different monitoring scenarios, such as tripwire intrusion detection, vehicle recognition and classification, pedestrian flow statistics, fire warning, water surface floating object recognition, etc. The selection of the target algorithm is crucial, which directly determines whether the video monitoring system can achieve the expected monitoring effect in this scenario.

[0056] For each selected target algorithm, the system will configure specific "algorithm parameters" according to the analysis method of the algorithm, the corresponding parameter types, and the user's specific monitoring requirements. One or more types of algorithm parameters can be selected for personalized settings according to the user's specific monitoring requirements. The purpose of parameter configuration is to refine the operation logic of the algorithm to ensure that it can accurately identify the target and generate alarms in a specific scenario.

[0057] According to the type of the configured algorithm parameters, determine the analysis method of the algorithm, including picture analysis and real-time stream analysis. This configuration is based on the reasonable utilization of computing power resources and the consideration of real-time requirements.

[0058] Furthermore, the types of algorithm parameters at least include: algorithm parameters based on tripwire judgment, algorithm parameters based on target duration, algorithm parameters based on target classification, algorithm parameters based on quantity threshold, algorithm parameters based on percentage, algorithm parameters based on feature recognition. The configuration method of the monitoring device in multiple scenarios also includes: for one target algorithm, select M types of algorithm parameters for combined configuration, where M is a positive integer.

[0059] In the embodiment of the present invention, for the determined target algorithm, the types of algorithm parameters at least include six types: algorithm parameters based on tripwire judgment, algorithm parameters based on target duration, algorithm parameters based on target classification, algorithm parameters based on quantity threshold, algorithm parameters based on percentage, algorithm parameters based on feature recognition. Each type of parameter specifically includes: parameter name, parameter code, parameter minimum value, parameter maximum value, parameter default value. When configuring the parameters of the target algorithm, M types of algorithm parameters can be selected for combined configuration according to the monitoring requirements. For example, for the personnel intrusion algorithm, an alarm is generated when the number of people crossing the tripwire is greater than 3, then the algorithm parameters include two types: tripwire judgment and quantity threshold. Where M (M is a positive integer) represents the number of parameter types that can be selected when configuring a single target algorithm, which provides a high degree of flexibility and customization ability for the configuration of the monitoring device.

[0060] Through the above embodiments, different types of algorithm parameter combinations can provide more personalized and targeted services for monitoring in specific scenarios, reduce the false alarm rate, improve the monitoring efficiency, and at the same time make it possible to share monitoring resources among multiple customers, reducing equipment and operation and maintenance costs.

[0061] Furthermore, the algorithm analysis methods at least include: picture analysis method, real-time stream analysis method. The steps of configuring algorithm parameters and algorithm analysis methods for the target algorithm include: when the type of algorithm parameters configured for the target algorithm is at least one of the algorithm parameters based on tripwire judgment and the algorithm parameters based on target duration, determining that the algorithm analysis method of the target algorithm is the real-time stream analysis method; when the type of algorithm parameters configured for the target algorithm is at least one of the algorithm parameters based on target classification, the algorithm parameters based on quantity threshold, the algorithm parameters based on percentage, and the algorithm parameters based on feature recognition, determining that the algorithm analysis method of the target algorithm is the picture analysis method, wherein, for the target algorithm configured with multiple types of algorithm parameters, the priority of the real-time stream analysis method is defined to be higher than the priority of the picture analysis method.

[0062] Specifically, on the premise of meeting the user's requirement of receiving analysis results in real time, the embodiments of the present invention consider saving computing power resources and divide the algorithm analysis methods into picture analysis and real-time stream (video) analysis. Among them, picture analysis provides the pictures required for algorithm analysis by video frame extraction, and real-time stream analysis provides the camera video stream URL address for the algorithm to perform real-time pulling stream analysis. When the requirements of algorithm analysis are equally met, picture analysis saves more computing power resources than real-time stream analysis.

[0063] On the premise of saving computing power costs, according to the real-time requirements and implementation logic of algorithm analysis, the analysis methods and scenarios are matched. When the type of algorithm parameters configured for the target algorithm is the algorithm parameters based on tripwire judgment or the algorithm parameters based on target duration, the implementation scenarios corresponding to these two types of algorithm parameters usually require the system to have high real-time response capabilities and continuous monitoring capabilities. Therefore, in these cases, the analysis method of the target algorithm will be set to the real-time stream analysis method. This means that the algorithm will directly obtain the continuous video stream from the camera and perform real-time analysis on it to quickly identify and respond to the targets crossing the line or staying for a long time, reducing false alarms or missed alarms caused by delays.

[0064] For business scenarios that focus on identifying specific types of targets (based on target classification), monitoring changes in the number of targets (based on quantity thresholds), checking the proportion of targets within the monitored area (based on percentages), or searching for objects with specific characteristics (based on feature recognition), the real-time requirement is relatively low, but there are certain requirements for the accuracy and efficiency of the algorithm in processing images. In this case, the analysis method of the target algorithm will be set to the picture analysis method. That is, the algorithm extracts key-frame pictures from the video for analysis instead of continuously analyzing the video stream. This method can more effectively utilize computing power resources and reduce the system operation cost while meeting the monitoring requirements, especially when dealing with a large amount of historical video data or in resource-constrained environments.

[0065] Furthermore, for the same algorithm configured with multiple types of algorithm parameters, define the priority of the real-time stream analysis method to be higher than that of the picture analysis method. That is, for the same algorithm, the parameters for different scenarios can be combined and set. In a complex scenario that simultaneously includes parameter types of the real-time stream analysis method and the picture analysis method, the algorithm analysis method adopts real-time stream analysis to ensure that the monitoring requirements of users can be met.

[0066] Step S203, determine the alarm trigger rule based on the algorithm parameters.

[0067] In the above step S203, after configuring the algorithm parameters for the target algorithm, define the specific alarm trigger rule according to the algorithm parameters to ensure that the monitoring device can accurately identify the preset abnormal situations and issue alarms in a timely manner when specific conditions are met, thereby improving the response speed and monitoring efficiency of the system.

[0068] Furthermore, the step of determining the alarm trigger rule based on the algorithm parameters includes: when the type of the algorithm parameters is the algorithm parameters based on tripwire judgment, set the warning reference line and the trigger direction; determine the tripwire alarm trigger rule based on the warning reference line and the trigger direction as: trigger the tripwire alarm when it is detected that the target object crosses the warning reference line along the trigger direction.

[0069] Specifically, when the type of the algorithm parameters is the algorithm parameters based on tripwire judgment, it is necessary to set the warning reference line and the trigger direction for identifying tripwire behavior. The warning reference line will be placed on the boundary where the moving target needs to be monitored. In addition, a trigger direction needs to be defined, which is the direction that the target object must face or move along to trigger the tripwire alarm mechanism. The trigger direction is perpendicular to the warning reference line, ensuring that the system can accurately judge whether the target has truly crossed the warning line and trigger an alarm accordingly.

[0070] Based on this, for the target algorithm that determines to execute the monitoring task based on tripwire judgment, its alarm trigger rule is expressed as: a tripwire alarm is triggered when it is detected that the target object crosses the warning reference line along the trigger direction. It is also possible to combine the maximum parameter value of the tripwire judgment to generate an alarm message when the number of people reaching the maximum is determined. For example, in the real-time passenger flow monitoring algorithm used in scenic spots, the warning reference line and trigger direction are delimited by a tripwire at the scenic spot entrance to calculate the number of people entering and leaving the scenic spot; in the real-time vehicle flow monitoring in forest areas, setting a tripwire is used to delimit the warning reference line and trigger direction in key areas to identify the entry and exit of vehicles.

[0071] Furthermore, the steps for determining the alarm trigger rule based on algorithm parameters include: when the type of algorithm parameter is an algorithm parameter based on target duration, setting the monitoring area and the target stay duration threshold; based on the monitoring area and the target stay duration, determining the duration alarm trigger rule as: a duration alarm is triggered when it is detected that the stay duration of the target object in the monitoring area is greater than the target stay duration threshold.

[0072] It should be noted that when the type of algorithm parameter is an algorithm parameter based on target duration, it is necessary to set the monitoring area for identifying specific behaviors and the target stay duration threshold. The monitoring area may be a specific part of the video screen, such as a parking space in a parking lot, a sensitive operation area in a factory, or an exit in a shopping mall, etc. The target stay duration threshold can be determined according to the maximum parameter value or the minimum parameter value, specifically based on the business scenario and requirements. For example, in vehicle illegal parking monitoring, the threshold may be the minimum parameter value of 3 minutes; in the parking lot monitoring scenario, the threshold may be the maximum parameter value of 30 minutes. The setting of the target stay duration threshold ensures that the system can distinguish normal behaviors and abnormal stays, reducing the false alarm rate.

[0073] Based on this, for the target algorithm that executes the monitoring task based on target duration, its alarm trigger rule is expressed as: a duration alarm is triggered when it is detected that the stay duration of the target object in the monitoring area is greater than the target stay duration threshold.

[0074] Furthermore, the steps for determining the alarm trigger rule based on algorithm parameters include: when the type of algorithm parameter is an algorithm parameter based on target classification, setting the monitoring target category; generating a dictionary value based on the monitoring target category and storing the dictionary value in the dictionary. Among them, when generating the algorithm analysis task, N dictionary values are selected as the monitoring targets based on the monitoring requirements, where N is a positive integer; based on the monitoring target category and the dictionary value, determining the classification alarm rule as: classifying the monitored target object and generating a dictionary value, and triggering a classification alarm when the generated dictionary value belongs to the selected monitoring target.

[0075] In some optional embodiments, when the type of algorithm parameter is an algorithm parameter based on target classification, a monitoring target, a monitoring target category are set, and a dictionary value is generated. The monitoring target may include one or more targets. For example, in a vehicle recognition algorithm, it can be classified into cars, buses, bicycles, motorcycles, tricycles, trucks, and other vehicles. When configuring the algorithm parameters of the target algorithm, all classifications can be selected or a part of them can be selected. The recognition targets in the horizontal floating object recognition algorithm can be classified into plastic bags, wrapping papers, bottles, barrels, cans, cardboard boxes, plastic boxes, foam boxes or boards, branches, wooden blocks, fallen leaves, and others. When configuring the algorithm parameters, part or all of them can be selected according to the management rules of floating objects. When the selected target object appears, an alarm is generated after algorithm analysis, and the customer can handle the floating object according to the alarm.

[0076] In addition, in the scenario of monitoring target classification, the system stores all possible monitoring target types (such as pedestrians, cars, bicycles, etc.) in a dictionary, and each target type has a unique identifier (dictionary key). When the user configures an algorithm analysis task and selects the target types to be monitored, the system will obtain the corresponding identifiers (dictionary values) from the dictionary according to the user's selection. These dictionary values will then be used as part of the algorithm parameters to indicate which types of targets the algorithm should focus on during analysis.

[0077] Based on this, for a target algorithm that performs a monitoring task based on target classification, the corresponding classification alarm trigger rule is: classify the recognized target object and generate a dictionary value for this category. When the generated dictionary value belongs to the selected monitoring target, the classification alarm rule is triggered.

[0078] Furthermore, the steps for determining the alarm trigger rule based on algorithm parameters include: when the type of algorithm parameter is an algorithm parameter based on a quantity threshold, set a target quantity threshold and generate a threshold determination condition based on the target quantity threshold; determine the quantity alarm rule based on the target quantity threshold and the threshold determination condition as: trigger a quantity alarm when the quantity of the monitored target object meets the threshold determination condition.

[0079] In some optional embodiments, in the scenario of quantity threshold judgment, set the target quantity threshold in the monitored area. When the set target quantity threshold is exceeded (greater than or equal to), a quantity alarm is triggered, and the monitored target quantity threshold is a positive number. For example, in a real-time pedestrian flow algorithm, an alarm can be generated when the detected target of people exceeds 5; in a traffic congestion recognition algorithm, it can be determined that there is congestion when the number of vehicles exceeds 8, and the algorithm generates an alarm only when the threshold determination condition is met.

[0080] Further, the steps of determining the alarm trigger rule based on the algorithm parameters include: when the type of the algorithm parameter is a percentage-based algorithm parameter, setting a percentage value and generating a percentage determination condition based on the percentage value; determining the quantity alarm rule based on the percentage value and the percentage determination condition as: triggering a percentage alarm when it is monitored that the proportion of the target object meets the percentage determination condition.

[0081] In some optional embodiments, in the percentage setting scenario, set the percentage of the detection target in the monitored area in the overall area, and trigger an alarm when it exceeds (is greater than or equal to) the set percentage. The percentage supports setting two decimal places.

[0082] Further, the steps of determining the alarm trigger rule based on the algorithm parameters include: when the type of the algorithm parameter is a feature recognition-based algorithm parameter, setting the target recognition feature; determining the quantity alarm rule based on the target recognition feature as: triggering a feature alarm when the target recognition feature is monitored.

[0083] In some optional embodiments, in the feature recognition scenario, set the feature parameter (i.e., the target recognition feature), directly analyze the content of the monitored video by the algorithm, and generate an alarm when relevant features are found, such as smoke, thick fog, fishing, etc. For example, in the smoke recognition algorithm, an alarm is generated as long as smoke is found, and in the illegal fishing recognition algorithm, an alarm is generated as long as it is monitored that someone is fishing.

[0084] Step S204, generate an algorithm analysis task based on the business scenario, monitoring requirements, target algorithm, algorithm parameters, algorithm analysis method, and alarm trigger rule, and send the algorithm analysis task to the target monitoring device.

[0085] In the above step S204, generate an algorithm analysis task according to the business scenario, monitoring requirements, selected target algorithm, set algorithm parameters, algorithm analysis method, and alarm trigger rule, so as to bind the business scenario and monitoring requirements with a specific analysis algorithm and alarm rule, and send the algorithm analysis task to the target monitoring device. Subsequently, as long as the relevant algorithm analysis task is called according to the business scenario and monitoring requirements selected by the user, the corresponding target algorithm can be executed to achieve accurate target monitoring and monitoring alarm, and realize the reuse of monitoring devices in multiple user and multiple scenario situations.

[0086] In some optional embodiments, after sending the algorithm analysis task to the target monitoring device, it further includes: receiving a monitoring request sent by the user terminal, determining the business scenario and monitoring requirements based on the monitoring request; selecting the corresponding target algorithm analysis task based on the monitoring requirements, and controlling the target monitoring device to execute the target algorithm to monitor and analyze the target object.

[0087] In practical applications, various algorithm analysis tasks are configured in the target monitoring device. The device receives monitoring requests sent by the user terminal, parses the monitoring requests to determine the business scenarios to be monitored and the monitoring requirements of the user, automatically selects the corresponding algorithm analysis task according to the monitoring requirements, and executes the target algorithm in the algorithm analysis task to monitor and alarm the target.

[0088] Through the above steps, K business scenarios of the target monitoring device are obtained. For each business scenario, the monitoring requirements are determined, where K is a positive integer. Based on the monitoring requirements of the target monitoring device in each business scenario, the target algorithm to be configured is determined, and algorithm parameters and algorithm analysis methods are configured for the target algorithm. Based on the algorithm parameters, the alarm trigger rule is determined. Based on the business scenario, monitoring requirements, target algorithm, algorithm parameters, algorithm analysis method, and alarm trigger rule, an algorithm analysis task is generated and sent to the target monitoring device.

[0089] In this embodiment, the monitoring requirements are determined based on the business scenarios used by the monitoring device, and appropriate algorithms are selected based on the monitoring requirements. Analysis methods and algorithm parameters are configured for the selected algorithms, and the alarm trigger rules corresponding to the algorithms are determined to generate algorithm analysis tasks, thereby associating the business scenarios with specific algorithm analysis tasks, meeting the monitoring requirements of multiple users and multiple scenarios, achieving the purpose of reusing the same monitoring device, obtaining the technical effect of improving the reuse rate of the monitoring device, and further solving the technical problem of low reuse rate in the related art where a single algorithm configuration method is used for the monitoring device.

[0090] The following is a detailed description in combination with another optional specific implementation manner.

[0091] Figure 3 It is a schematic diagram of a configuration process of a monitoring device in multiple scenarios according to an embodiment of the present invention. As Figure 3 shown, the configuration process of the monitoring device in multiple scenarios includes:

[0092] Step 1: Clarify the monitoring requirements according to the business scenarios monitored by the camera and determine the algorithms to be configured. A monitoring device can select multiple algorithms according to requirements, and a monitoring device can be shared by multiple customers.

[0093] Step 2: Configure the algorithm analysis tasks according to the analysis methods, corresponding parameter types, and specific parameter configuration rules of different algorithms, and integrate the algorithm analysis tasks according to the algorithm dimension.

[0094] Step 3: Send different algorithm analysis tasks to the corresponding algorithms. The algorithms receive the tasks for analysis and report the results that meet the parameter conditions.

[0095] Figure 4It is an exemplary diagram of algorithm configuration for a monitoring device in multiple scenarios according to an embodiment of the present invention. As Figure 4 shown, first, select the target algorithms to be configured for the monitoring device under various business scenarios and monitoring requirements. The target algorithms are obtained from an algorithm library, which integrates existing monitoring algorithms. Then, configure the analysis methods for the target algorithms, namely real-time stream analysis method and image analysis method.

[0096] The setting of algorithm parameters is related to the scenario. Scenario 1 is a monitoring scenario based on tripwire judgment, and it is necessary to configure an alarm trigger rule 1 for tripwire judgment. For Rule 1, in the tripwire judgment scenario, the tripwire serves as a trigger for algorithm-assisted analysis. It is necessary to set a warning reference line and a trigger direction, and the trigger direction is perpendicular to the warning reference line. Multiple tripwires are supported to be set in the same algorithm analysis task. Therefore, it is supported to set one or more groups of parameters including the warning reference line and the trigger direction. When the detected target crosses the warning reference line along the set direction (the center point of the target object crosses the warning line), the algorithm generates an alarm and reports the result. For example, in the real-time pedestrian flow monitoring algorithm used in scenic spots, a warning line and direction are defined by a tripwire at the entrance to calculate the number of people entering and leaving the scenic spot; in the real-time vehicle flow monitoring in forest areas, a warning line and direction are set by a tripwire in key areas to identify the entry and exit of vehicles.

[0097] Scenario 2 is a monitoring scenario based on the target duration, and it is necessary to configure a duration alarm trigger rule based on the target duration, that is, Rule 2. In the monitoring target duration scenario, set the duration for which the monitoring target stays in the monitoring area according to the requirements. When the stay duration exceeds (is greater than or equal to) the set stay duration threshold, an alarm is triggered, where the stay duration is a positive number. For example, the vehicle illegal parking algorithm can set the stay duration to 3 minutes, that is, when the vehicle stays for more than 3 minutes, the algorithm generates an alarm and reports it. The personnel off-duty recognition algorithm can set different off-duty durations according to management requirements. For example, when a person leaves for more than 30 minutes, the algorithm generates an alarm and determines that the person is off-duty.

[0098] Scenario 3 is a monitoring scenario based on target classification, and it is necessary to configure a classification alarm trigger rule based on target classification, that is, Rule 3. In the monitoring target classification scenario, classify the target objects to be monitored and generate dictionary values, and select one or more detection targets when setting the algorithm analysis task. For example, in the vehicle recognition algorithm, it can be classified as cars, buses, bicycles, motorcycles, tricycles, trucks, and other vehicles. When setting the algorithm analysis task, all classifications can be selected or a part of them can be selected. The recognition target objects in the horizontal floating object recognition algorithm can be classified as plastic bags, wrapping papers, bottles, barrels, cans, cartons, plastic boxes, foam boxes or boards, branches, wooden blocks, fallen leaves, and others. You can select some or all of them according to your own management rules for floating objects. When the selected target objects appear, the algorithm generates an alarm after analysis, and the customer can handle the floating objects according to the alarm.

[0099] Scenario 4 is a monitoring scenario based on a quantity threshold, and a quantity alarm trigger rule based on the quantity threshold, i.e., Rule 4, needs to be configured for it. In the quantity threshold judgment scenario, set the target quantity threshold within the monitoring area. When the detected target quantity exceeds (is greater than or equal to) the set quantity threshold, an alarm is triggered, and the monitored target quantity threshold is a positive number. For example, in the real-time pedestrian flow algorithm, an alarm can be generated when the detected number of people exceeds 5; in the traffic congestion recognition algorithm, it is only recognized as congested when the number of vehicles exceeds 8, and the algorithm generates an alarm only when the condition is met.

[0100] Scenario 5 is a monitoring scenario based on a percentage, and a percentage alarm trigger rule based on the percentage value, i.e., Rule 5, needs to be configured for it. In the percentage monitoring scenario, set the percentage of the detected target in the overall area within the monitoring area. When it exceeds (is greater than or equal to) the set value, an alarm is triggered, and the percentage supports setting two decimal places.

[0101] Scenario 6 is a monitoring scenario based on feature recognition, and a feature alarm trigger rule based on target feature recognition, i.e., Rule 6, needs to be configured for it. In the feature recognition scenario, set the target features to be recognized, that is, the algorithm performs feature recognition and direct analysis on the content of the monitoring screen, and generates an alarm when relevant features are found, such as smoke, thick fog, fishing, etc. For example, in the smoke recognition algorithm, an alarm is generated as long as smoke is found.

[0102] Based on different business scenarios, different types of algorithm parameters can be selected, and specific parameter values and alarm rules can be set according to the user's monitoring requirements, thereby generating algorithm analysis tasks, and finally integrating the algorithm analysis tasks according to the set analysis types and parameters.

[0103] The embodiment of the present invention proposes an algorithm configuration method for multi-scenario and multi-parameter video monitoring, which provides a personalized parameter configuration method in combination with the actual needs of customers, flexibly meets the needs of different customers, makes the monitoring effect more accurate, and can effectively meet the monitoring needs of different customers in different scenarios.

[0104] The following is a detailed description in combination with another embodiment.

[0105] Embodiment 2

[0106] A configuration device for a monitoring device in multiple scenarios provided in this embodiment includes multiple implementation units, and each implementation unit corresponds to each implementation step in the first embodiment above. Its specific implementation manner and beneficial effects can be referred to the foregoing method embodiment, and will not be elaborated here.

[0107] Figure 5 It is a schematic diagram of an optional configuration device for a monitoring device in multiple scenarios according to an embodiment of the present invention, asFigure 5 As shown in Figure 5 , the configuration device for the monitoring device in multiple scenarios may include: an acquisition unit 51, a configuration unit 52, a determination unit 53, and a generation unit 54. Among them,

[0108] The acquisition unit 51 is configured to acquire K service scenarios of the target monitoring device, and determine monitoring requirements for each service scenario, where K is a positive integer;

[0109] The configuration unit 52 is configured to determine a target algorithm to be configured based on the monitoring requirements of the target monitoring device in each service scenario, and configure algorithm parameters and algorithm analysis methods for the target algorithm;

[0110] The determination unit 53 is configured to determine an alarm trigger rule based on the algorithm parameters;

[0111] The generation unit 54 is configured to generate an algorithm analysis task based on the service scenario, monitoring requirements, target algorithm, algorithm parameters, algorithm analysis method, and alarm trigger rule, and send the algorithm analysis task to the target monitoring device.

[0112] For the above configuration device for the monitoring device in multiple scenarios, the acquisition unit 51 acquires K service scenarios of the target monitoring device, and determines monitoring requirements for each service scenario, where K is a positive integer; the configuration unit 52 determines a target algorithm to be configured based on the monitoring requirements of the target monitoring device in each service scenario, and configures algorithm parameters and algorithm analysis methods for the target algorithm; the determination unit 53 determines an alarm trigger rule based on the algorithm parameters; the generation unit 54 generates an algorithm analysis task based on the service scenario, monitoring requirements, target algorithm, algorithm parameters, algorithm analysis method, and alarm trigger rule, and sends the algorithm analysis task to the target monitoring device.

[0113] In this embodiment, the monitoring requirements are determined based on the service scenarios used by the monitoring device, and a suitable algorithm is selected based on the monitoring requirements. The analysis method and algorithm parameters are configured for the selected algorithm, and the alarm trigger rule corresponding to the algorithm is determined to generate an algorithm analysis task, so as to associate the service scenario with a specific algorithm analysis task, meet the monitoring requirements of multiple users and multiple scenarios, achieve the purpose of reusing the same monitoring device, and obtain the technical effect of improving the reuse rate of the monitoring device. Furthermore, it solves the technical problem of low reuse rate in the related art where a single algorithm configuration method is used for the monitoring device.

[0114] Further, the types of algorithm parameters at least include: algorithm parameters based on tripwire judgment, algorithm parameters based on target duration, algorithm parameters based on target classification, algorithm parameters based on quantity threshold, algorithm parameters based on percentage, and algorithm parameters based on feature recognition. The configuration device for monitoring devices in multiple scenarios further includes: a first configuration module, configured to, for a target algorithm, select M types of algorithm parameters for combined configuration, where M is a positive integer.

[0115] Further, the algorithm analysis methods at least include: picture analysis method, real-time stream analysis method. The configuration unit includes: a first determination module, configured to, when the type of algorithm parameters configured for the target algorithm is at least one of the algorithm parameters based on tripwire judgment and the algorithm parameters based on target duration, determine that the algorithm analysis method of the target algorithm is the real-time stream analysis method; a second determination module, configured to, when the type of algorithm parameters configured for the target algorithm is at least one of the algorithm parameters based on target classification, the algorithm parameters based on quantity threshold, the algorithm parameters based on percentage, and the algorithm parameters based on feature recognition, determine that the algorithm analysis method of the target algorithm is the picture analysis method, where, for a target algorithm configured with multiple types of algorithm parameters, it is defined that the priority of the real-time stream analysis method is higher than that of the picture analysis method.

[0116] Further, the determination unit includes: a first setting module, configured to, when the type of algorithm parameters is the algorithm parameters based on tripwire judgment, set a warning baseline and a trigger direction; a third determination module, configured to determine the tripwire alarm trigger rule based on the warning baseline and the trigger direction as: triggering a tripwire alarm when it is detected that the target object crosses the warning baseline along the trigger direction.

[0117] Further, the determination unit further includes: a second setting module, configured to, when the type of algorithm parameters is the algorithm parameters based on target duration, set a monitoring area and a target stay duration threshold; a fourth determination module, configured to determine the duration alarm trigger rule based on the monitoring area and the target stay duration as: triggering a duration alarm when it is detected that the stay duration of the target object in the monitoring area is greater than the target stay duration threshold.

[0118] Further, the determination unit further includes: a third setting module, configured to, when the type of algorithm parameters is the algorithm parameters based on target classification, set a monitoring target category; a first generation module, configured to generate a dictionary value based on the monitoring target category and store the dictionary value in the dictionary, where, when generating an algorithm analysis task, N dictionary values are selected as monitoring targets based on monitoring requirements, and N is a positive integer; a fifth determination module, configured to determine the classification alarm rule based on the monitoring target category and the dictionary value as: triggering a classification alarm when the monitoring result indicates the existence of the selected monitoring target.

[0119] Further, the determining unit further includes: a fourth setting module, configured to set a target quantity threshold when the type of the algorithm parameter is an algorithm parameter based on a quantity threshold, and generate a threshold determination condition based on the target quantity threshold; a sixth determining module, configured to determine that the classification warning rule is: classifying the monitored target object and generating a dictionary value, and triggering a classification warning when the generated dictionary value belongs to the selected monitored target.

[0120] Further, the determining unit further includes: a fifth setting module, configured to set a percentage value when the type of the algorithm parameter is an algorithm parameter based on a percentage, and generate a percentage determination condition based on the percentage value; a seventh determining module, configured to determine that the quantity warning rule is: triggering a percentage warning when the ratio of the monitored target object meets the percentage determination condition based on the percentage value and the percentage determination condition.

[0121] Further, the determining unit further includes: a sixth setting module, configured to set a target recognition feature when the type of the algorithm parameter is an algorithm parameter based on feature recognition; an eighth determining module, configured to determine that the quantity warning rule is: triggering a feature warning when the target recognition feature is monitored based on the target recognition feature.

[0122] It should be noted here that the above-mentioned obtaining unit 51, configuration unit 52, determining unit 53, and generating unit 54 correspond to steps S201 to S204 in Embodiment 1. The examples and application scenarios implemented by the above units and the corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1 above. It should be noted that the above modules or units may be hardware components or software components stored in a memory (for example, memory 104) and processed by one or more processors (for example, processors 102a, 102b,..., 102n). The above modules or units may also be part of a device and may run in the computer terminal 10 provided in Embodiment 1.

[0123] The present invention will be described below in conjunction with another alternative embodiment.

[0124] Embodiment 3

[0125] The embodiment of the present invention may further provide an electronic device. Figure 6 It is a hardware structure block diagram of an electronic device (or mobile device) that optionally executes the configuration method of the monitoring device in multiple scenarios according to the embodiment of the present invention, as Figure 6 shown. The electronic device may include: one or more ( Figure 6 only one is shown in the figure) processors 602, a memory 604, a storage controller, and a peripheral interface. The peripheral interface is connected to a radio frequency module, an audio module, and a display.

[0126] Among them, the memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and devices in the embodiments of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, implements the above-mentioned methods. The memory 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 memories, or other non-volatile solid-state memories. In some instances, the memory may further include a memory remotely disposed relative to the processor, and these remote memories may be connected to the terminal through a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0127] The processor can call the information and application programs stored in the memory through the transmission device to execute the following steps: obtain K service scenarios of the target monitoring device, and determine the monitoring requirements for each service scenario, where K is a positive integer; determine the target algorithm to be configured based on the monitoring requirements of the target monitoring device in each service scenario, and configure algorithm parameters and algorithm analysis methods for the target algorithm; determine the alarm trigger rule based on the algorithm parameters; generate an algorithm analysis task based on the service scenario, monitoring requirements, target algorithm, algorithm parameters, algorithm analysis method, and alarm trigger rule, and send the algorithm analysis task to the target monitoring device.

[0128] The processor can also call the information and application programs stored in the memory through the transmission device to execute the following steps: The types of algorithm parameters at least include: algorithm parameters based on tripwire judgment, algorithm parameters based on target duration, algorithm parameters based on target classification, algorithm parameters based on quantity threshold, algorithm parameters based on percentage, algorithm parameters based on feature recognition. The configuration method of the monitoring device in multiple scenarios further includes: for a target algorithm, select M types of algorithm parameters for combined configuration, where M is a positive integer.

[0129] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: The algorithm analysis methods at least include: picture analysis method, real-time stream analysis method. The steps of configuring algorithm parameters and algorithm analysis methods for the target algorithm include: when the type of algorithm parameters configured for the target algorithm is at least one of the algorithm parameters based on tripwire judgment and the algorithm parameters based on target duration, determining that the algorithm analysis method of the target algorithm is the real-time stream analysis method; when the type of algorithm parameters configured for the target algorithm is at least one of the algorithm parameters based on target classification, the algorithm parameters based on quantity threshold, the algorithm parameters based on percentage, and the algorithm parameters based on feature recognition, determining that the algorithm analysis method of the target algorithm is the picture analysis method. Among them, for the target algorithm configured with multiple types of algorithm parameters, the priority of the real-time stream analysis method is defined to be higher than that of the picture analysis method.

[0130] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: The steps of determining the alarm trigger rule based on the algorithm parameters include: in the case where the type of algorithm parameters is the algorithm parameters based on tripwire judgment, setting the warning baseline and the trigger direction; determining the tripwire alarm trigger rule based on the warning baseline and the trigger direction as: triggering the tripwire alarm when it is detected that the target object crosses the warning baseline along the trigger direction.

[0131] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: The steps of determining the alarm trigger rule based on the algorithm parameters include: in the case where the type of algorithm parameters is the algorithm parameters based on target duration, setting the monitoring area and the target stay duration threshold; determining the duration alarm trigger rule based on the monitoring area and the target stay duration as: triggering the duration alarm when it is detected that the stay duration of the target object in the monitoring area is greater than the target stay duration threshold.

[0132] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: The steps of determining the alarm trigger rule based on the algorithm parameters include: The steps of determining the alarm trigger rule based on the algorithm parameters include: in the case where the type of algorithm parameters is the algorithm parameters based on target classification, setting the monitoring target category; generating a dictionary value based on the monitoring target category and storing the dictionary value in the dictionary. Among them, when generating the algorithm analysis task, selecting N dictionary values as the monitoring targets based on the monitoring requirements, N is a positive integer; determining the classification alarm rule based on the monitoring target category and the dictionary value as: classifying the monitored target object and generating a dictionary value, and triggering the classification alarm when the generated dictionary value belongs to the selected monitoring targets.

[0133] The processor can also call the information and application programs stored in the memory through the transmission device to execute the following steps: The steps for determining the alarm trigger rule based on the algorithm parameters include: The steps for determining the alarm trigger rule based on the algorithm parameters include: In the case where the type of the algorithm parameters is the algorithm parameters based on the quantity threshold, set the target quantity threshold, and generate a threshold determination condition based on the target quantity threshold; Determine the quantity alarm rule based on the target quantity threshold and the threshold determination condition as: Trigger a quantity alarm when it is monitored that the quantity of the target object meets the threshold determination condition.

[0134] The processor can also call the information and application programs stored in the memory through the transmission device to execute the following steps: The steps for determining the alarm trigger rule based on the algorithm parameters include: The steps for determining the alarm trigger rule based on the algorithm parameters include: In the case where the type of the algorithm parameters is the algorithm parameters based on the percentage, set the percentage value, and generate a percentage determination condition based on the percentage value; Determine the quantity alarm rule based on the percentage value and the percentage determination condition as: Trigger a percentage alarm when it is monitored that the proportion of the target object meets the percentage determination condition.

[0135] The processor can also call the information and application programs stored in the memory through the transmission device to execute the following steps: The steps for determining the alarm trigger rule based on the algorithm parameters include: The steps for determining the alarm trigger rule based on the algorithm parameters include: In the case where the type of the algorithm parameters is the algorithm parameters based on feature recognition, set the target recognition feature; Determine the quantity alarm rule based on the target recognition feature as: Trigger a feature alarm when the target recognition feature is monitored.

[0136] By adopting the embodiment of the present invention, a configuration method for a monitoring device in multiple scenarios is provided. Determine the monitoring requirements through the business scenarios used by the monitoring device, select a suitable algorithm based on the monitoring requirements, configure the analysis method and algorithm parameters for the selected algorithm, and determine the alarm trigger rule corresponding to the algorithm, and generate an algorithm analysis task, so as to associate the business scenario with a specific algorithm analysis task, meet the monitoring requirements of multiple users and multiple scenarios, achieve the purpose of reusing the same monitoring device, obtain the technical effect of improving the reuse rate of the monitoring device, and further solve the technical problem of low reuse rate in the related art where a single algorithm configuration is performed on the monitoring device.

[0137] Those of ordinary skill in the art can understand that Figure 6 The structure shown is only schematic, and the electronic device can also be a terminal device such as a smart phone, a tablet computer, a personal digital assistant, and mobile Internet devices (MID), PAD, etc. Figure 6 It does not limit the structure of the above-mentioned electronic device. For example, the electronic device may further include more Figure 6more or fewer components (such as network interfaces, display devices, etc.) shown therein, or having a configuration different from that shown in Figure 6 that shown.

[0138] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by a program instructing the hardware related to the terminal device, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disc, etc.

[0139] The present invention will be described below in conjunction with another alternative embodiment.

[0140] Embodiment 4

[0141] The embodiment of the present invention also provides a computer-readable storage medium. Optionally, in the embodiment of the present invention, the above computer-readable storage medium can be used to store the program code executed by the configuration method of the monitoring device in multiple scenarios provided in the first embodiment above.

[0142] Optionally, in the embodiment of the present invention, the above storage medium can be located in any one of the computer terminals in the computer terminal group in the computer network, or in any one of the mobile terminals in the mobile terminal group.

[0143] The embodiment of the present invention also provides a computer program product, which, when executed on a data processing device, is adapted to execute a program for the steps of the configuration method of the monitoring device in multiple scenarios: obtaining K service scenarios of the target monitoring device, determining monitoring requirements for each service scenario, where K is a positive integer; determining a target algorithm to be configured based on the monitoring requirements of the target monitoring device in each service scenario, and configuring algorithm parameters and algorithm analysis methods for the target algorithm; determining an alarm trigger rule based on the algorithm parameters; generating an algorithm analysis task based on the service scenario, monitoring requirements, target algorithm, algorithm parameters, algorithm analysis method, and alarm trigger rule, and sending the algorithm analysis task to the target monitoring device.

[0144] The above serial numbers of the embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments.

[0145] In the above embodiments of the present invention, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0146] In several embodiments provided by the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of the units can be a logical function division. In actual implementation, there can be other division methods. 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 couplings or direct couplings or communication connections shown or discussed with each other can be through some interfaces. The indirect couplings or communication connections of units or modules can be in electrical or other forms.

[0147] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0148] In addition, in each embodiment of the present invention, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0149] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention. The foregoing storage medium includes: USB flash drives, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), mobile hard disks, magnetic disks, or optical discs and other various media that can store program codes.

[0150] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for configuring monitoring equipment in multiple scenarios, characterized in that: include: Obtain K business scenarios of the target monitoring device, and determine the monitoring requirements for each of the business scenarios, where K is a positive integer; Determine the target algorithm to be configured based on the monitoring requirements of the target monitoring device in each of the business scenarios, and configure algorithm parameters and algorithm analysis methods for the target algorithm; Determining an alarm triggering rule based on the algorithm parameters; An algorithm analysis task is generated based on the business scenario, the monitoring requirements, the target algorithm, the algorithm parameters, the algorithm analysis method and the alarm triggering rules, and the algorithm analysis task is sent to the target monitoring device.

2. The method according to claim 1, characterized in that The types of the algorithm parameters include at least: algorithm parameters based on tripwire judgment, algorithm parameters based on target duration, algorithm parameters based on target classification, algorithm parameters based on quantity threshold, algorithm parameters based on percentage, and algorithm parameters based on feature recognition. The configuration method of the monitoring device in multiple scenarios also includes: For a target algorithm, M types of algorithm parameters are selected for combined configuration, where M is a positive integer.

3. The method according to claim 2, characterized in that The algorithm analysis method at least includes: an image analysis method and a real-time stream analysis method. The steps of configuring algorithm parameters and the algorithm analysis method for the target algorithm include: When the type of the algorithm parameter configured for the target algorithm is at least one of an algorithm parameter based on tripwire judgment and an algorithm parameter based on target duration, determining that the algorithm analysis mode of the target algorithm is a real-time stream analysis mode; When the type of the algorithm parameters configured for the target algorithm is at least one of an algorithm parameter based on target classification, an algorithm parameter based on a quantity threshold, an algorithm parameter based on a percentage, and an algorithm parameter based on feature recognition, determining that the algorithm analysis mode of the target algorithm is an image analysis mode; Among them, for a target algorithm configured with multiple types of algorithm parameters, it is defined that the priority of the real-time stream analysis method is higher than the priority of the image analysis method.

4. The method according to claim 2, characterized in that: The step of determining the alarm triggering rule based on the algorithm parameters comprises: In the case where the type of the algorithm parameter is an algorithm parameter based on tripwire judgment, setting a warning baseline and a trigger direction; The tripwire alarm triggering rule is determined based on the warning baseline and the triggering direction: the tripwire alarm is triggered when it is monitored that the target object crosses the warning baseline along the triggering direction.

5. The method according to claim 2, characterized in that: The step of determining the alarm triggering rule based on the algorithm parameters comprises: When the type of the algorithm parameter is an algorithm parameter based on target duration, setting a monitoring area and a target stay duration threshold; The duration alarm triggering rule is determined based on the monitoring area and the target stay duration: triggering the duration alarm when it is monitored that the stay duration of the target object in the monitoring area is greater than the target stay duration threshold.

6. The method according to claim 2, characterized in that The step of determining the alarm triggering rule based on the algorithm parameters comprises: In the case where the type of the algorithm parameter is an algorithm parameter based on target classification, setting a monitoring target category; Generate dictionary values ​​based on the monitoring target category, and store the dictionary values ​​in the dictionary, wherein, when generating an algorithm analysis task, select N dictionary values ​​as monitoring targets based on monitoring requirements, where N is a positive integer; The classification alarm rule is determined based on the monitoring target category and the dictionary value: the monitored target object is classified and a dictionary value is generated, and a classification alarm is triggered when the generated dictionary value belongs to the selected monitoring target.

7. The method according to claim 2, characterized in that The step of determining the alarm triggering rule based on the algorithm parameters comprises: In the case where the type of the algorithm parameter is an algorithm parameter based on a quantity threshold, setting a target quantity threshold, and generating a threshold determination condition based on the target quantity threshold; The quantity alarm rule is determined based on the target quantity threshold and the threshold determination condition: triggering a quantity alarm when the quantity of the monitored target objects meets the threshold determination condition.

8. The method according to claim 2, characterized in that: The step of determining the alarm triggering rule based on the algorithm parameters comprises: In the case where the type of the algorithm parameter is an algorithm parameter based on percentage, setting a percentage value, and generating a percentage determination condition based on the percentage value; The quantity alarm rule is determined based on the percentage value and the percentage determination condition: triggering a percentage alarm when the proportion of the monitored target objects meets the percentage determination condition.

9. The method according to claim 2, characterized in that: The step of determining the alarm triggering rule based on the algorithm parameters comprises: In the case where the type of the algorithm parameter is an algorithm parameter based on feature recognition, setting a target recognition feature; The quantity alarm rule is determined based on the target identification feature: triggering a feature alarm when the target identification feature is detected.

10. A configuration device for monitoring equipment in multiple scenarios, characterized in that: include: An acquisition unit, configured to acquire K business scenarios of a target monitoring device and determine a monitoring requirement for each business scenario, wherein K is a positive integer; A configuration unit, configured to determine a target algorithm to be configured based on the monitoring requirements of the target monitoring device in each of the business scenarios, and configure algorithm parameters and an algorithm analysis method for the target algorithm; A determination unit, configured to determine an alarm triggering rule based on the algorithm parameters; A generation unit is used to generate an algorithm analysis task based on the business scenario, the monitoring requirements, the target algorithm, the algorithm parameters, the algorithm analysis method and the alarm triggering rules, and send the algorithm analysis task to the target monitoring device.

Images