Event determination method and apparatus, storage medium, and electronic device

Abstract

The embodiment of the application provides a kind of event determination method and device, storage medium, electronic equipment, the method comprises: in the case where target object carries target device and enters target area, the target object feature of target object and the target device feature of target device are acquired;In the similarity of target object feature and the first object feature stored in first feature library is less than first threshold value, and the similarity of target device feature and the first device feature in first feature library is less than second threshold value, the target similarity of target device feature and other device features stored in second feature library is determined;In the case where target similarity is greater than or equal to second threshold value, it is determined that there is predetermined class device enters the event of target area.The application solves the problem of low efficiency in determining the event of predetermined class device entering the target area in the related art, and achieves the effect of efficiently determining the event of predetermined class device entering the target area.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more specifically, to a method and apparatus for determining an event, a storage medium, and an electronic device. Background Technology

[0002] When the early warning system performs various detection services, some detection targets have a large activity range but a small detection range. Using conventional detection methods may result in low detection efficiency. How to improve detection efficiency is an urgent problem to be solved.

[0003] For example, with the increasing popularity of electric bicycles, the safety hazards of bringing electric bicycle batteries into elevators are becoming increasingly prominent, especially in residential areas. Electric bicycle batteries may spontaneously combust inside elevators due to overheating, short circuits, or other unexpected factors, seriously threatening passenger safety and the normal operation of the elevator. Related early warning systems mainly rely on two detection methods: one is to install positioning and communication modules on the electric bicycle to track the battery's location in real time, and take immediate action once a battery is detected inside the elevator. The other technical solution is to continuously capture images of targets in the elevator waiting area and use image recognition technology to determine whether someone has brought an electric bicycle battery into the elevator. However, both methods have limitations such as high investment costs, low recognition efficiency, and low accuracy.

[0004] Therefore, there is a technical problem in the related technology of low efficiency in determining the entry of predetermined type of equipment into the target area. Summary of the Invention

[0005] This application provides an event determination method and apparatus, storage medium, and electronic device to at least solve the problem of low efficiency in determining events of predetermined types of devices entering a target area in related technologies.

[0006] According to one embodiment of this application, a method for determining an event is provided, comprising: when it is determined that a target object carries a target device into a target area, acquiring target object features of the target object and target device features of the target device, wherein the target area is an area where predetermined types of devices are prohibited from entering; when the similarity between the target object features and first object features stored in a first feature library is less than a first threshold, and the similarity between the target device features and first device features stored in the first feature library is less than a second threshold, determining the target similarity between the target device features and other device features stored in a second feature library, wherein the first object features are acquired after it is determined that the first object performs a target operation on a first device within a first area. The features of the first object stored in the first feature library, the features of the first device being acquired and stored in the first feature library and the second feature library after determining that the first object performs the target operation on the first device in the first region, the first storage time limit of the features in the first feature library is less than the second storage time limit of the features in the second feature library, the first device being the predetermined type of device, and the other device features including device features deleted from the first feature library after the storage time exceeds the first storage time limit and device features pre-stored in the second feature library; when the target similarity is greater than or equal to the second threshold, it is determined that there is an event of the predetermined type of device entering the target region.

[0007] In an exemplary embodiment, before acquiring the target object features of the target object and the target device features of the target device when it is determined that the target object carries the target device into the target area, the method further includes: detecting whether the first object performs the target operation on the first device in the first area; if it is determined that the first object performs the target operation, acquiring object video data of the first object and device video data of the first device, and determining the acquisition time; acquiring the first object features from the object video data and the first device features from the device video data; storing the first object features, the first device features, and the acquisition time in the first feature library, and storing the first device features in the second feature library.

[0008] In an exemplary embodiment, detecting whether the first object performs the target operation on the first device in the first region includes: detecting whether the first object performs a first operation on a first component, wherein the first component is used to store a second device, and the first operation is used to open the first component; if it is determined that the first object performs the first operation, detecting whether the first object performs a second operation on the second device stored in the first component, wherein the second operation is used to remove the second device; if it is determined that the first object performs the second operation, detecting whether the second device is the first device; if it is determined that the second device is the first device, detecting whether the first object performs a third operation on the first component, wherein the third operation is used to close the first component; and if it is determined that the first object performs the third operation, determining that the first object performs the target operation.

[0009] In an exemplary embodiment, before determining the target similarity between the target device feature and other device features stored in the second feature library, the method further includes: determining whether the first feature library stores object features and device features; if the first feature library stores object features and device features, determining the similarity between the target object feature and the first object feature, and the similarity between the target device feature and the first device feature, wherein the object feature includes the first object feature, and the device feature includes the first device feature; if the first feature library does not store object features and device features, determining the target similarity; and if the target similarity is greater than or equal to the second threshold, determining that an event has occurred where the predetermined type of device enters the target area.

[0010] In an exemplary embodiment, after determining the similarity between the target object feature and the first object feature, and the similarity between the target device feature and the first device feature, the method further includes: determining that an event exists where the predetermined type of device enters the target area when the similarity between the target object feature and the first object feature is greater than or equal to the first threshold and the similarity between the target device feature and the first device feature is greater than or equal to the second threshold.

[0011] In an exemplary embodiment, after determining that an event has occurred where the predetermined type of device has entered the target area when the target similarity is greater than or equal to the second threshold, the method further includes: triggering a first target alarm mechanism; after determining that an event has occurred where the target object feature is greater than or equal to the first object feature and the target device feature is greater than or equal to the second threshold, the method further includes: triggering a second target alarm mechanism; wherein the alarm level of the second target alarm mechanism is greater than the alarm level of the first target alarm mechanism.

[0012] In an exemplary embodiment, after storing the first object feature, the first device feature, and the acquisition time in the first feature library, the method further includes: deleting the first object feature, the first device feature, and the acquisition time from the first feature library if the storage time of the first object feature and the first device feature in the first feature library exceeds the first storage time limit.

[0013] According to another embodiment of this application, an event determination apparatus is provided, comprising: a first acquisition module, configured to acquire target object features of the target object and target device features of the target device when it is determined that a target object carries a target device into a target area, wherein the target area is an area where predetermined types of devices are prohibited from entering; and a first determination module, configured to determine the target similarity between the target device features and other device features stored in a second feature library when the similarity between the target object features and first object features stored in a first feature library is less than a first threshold, and the similarity between the target device features and first device features stored in the first feature library is less than a second threshold, wherein the first object features are determined after it is determined that the first object performs a target operation on a first device in a first area. The features of the first object acquired and stored in the first feature library, the features of the first device acquired and stored in the first feature library and the second feature library after determining that the first object performs the target operation on the first device in the first region, the first storage time limit of the features in the first feature library is less than the second storage time limit of the features in the second feature library, the first device is the predetermined type of device, and the other device features include device features deleted from the first feature library after the storage time exceeds the first storage time limit and device features pre-stored in the second feature library; the second determining module is used to determine that there is an event that the predetermined type of device enters the target region when the target similarity is greater than or equal to the second threshold.

[0014] In one exemplary embodiment, the apparatus further includes: a first detection module, configured to detect whether the first object performs the target operation on the first device in the first area before acquiring the target object feature of the target object and the target device feature of the target device, when it is determined that the target object carries the target device into the target area; a second acquisition module, configured to acquire object video data of the first object and device video data of the first device, and determine the acquisition time, when it is determined that the first object performs the target operation; a third acquisition module, configured to acquire the first object feature from the object video data and the first device feature from the device video data; and a first storage module, configured to store the first object feature, the first device feature, and the acquisition time in the first feature library and store the first device feature in the second feature library.

[0015] In an exemplary embodiment, the first detection module includes: a first detection submodule, configured to detect whether the first object performs a first operation on a first component, wherein the first component is used to store a second device, and the first operation is used to open the first component; a second detection submodule, configured to, if it is determined that the first object performs the first operation, detect whether the first object performs a second operation on the second device stored in the first component, wherein the second operation is used to remove the second device; a third detection submodule, configured to, if it is determined that the first object performs the second operation, detect whether the second device is the first device; a fourth detection submodule, configured to, if it is determined that the second device is the first device, detect whether the first object performs a third operation on the first component, wherein the third operation is used to close the first component; and a first determination submodule, configured to, if it is determined that the first object performs the third operation, determine that the first object performs the target operation.

[0016] In an exemplary embodiment, the apparatus further includes: a third determining module, configured to determine whether object features and device features are stored in the first feature library before determining the target similarity between the target device feature and other device features stored in the second feature library; a fourth determining module, configured to determine the similarity between the target object feature and the first object feature, and the similarity between the target device feature and the first device feature, if the object feature and the device feature are stored in the first feature library, wherein the object feature includes the first object feature and the device feature includes the first device feature; a fifth determining module, configured to determine the target similarity if the object feature and the device feature are not stored in the first feature library; and a sixth determining module, configured to determine that an event exists where the predetermined type of device enters the target area if the target similarity is greater than or equal to the second threshold.

[0017] In an exemplary embodiment, the apparatus further includes a seventh determining module, configured to determine, after determining the similarity between the target object feature and the first object feature, and the similarity between the target device feature and the first device feature, an event in which the predetermined type of device enters the target area occurs if the similarity between the target object feature and the first object feature is greater than or equal to the first threshold, and the similarity between the target device feature and the first device feature is greater than or equal to the second threshold.

[0018] In one exemplary embodiment, the apparatus further includes: a first triggering module, configured to trigger a first target alarm mechanism after determining that an event has occurred where the target similarity is greater than or equal to the second threshold; and after determining that an event has occurred where the predetermined type of device has entered the target area, the method further includes: a second triggering module, configured to trigger a second target alarm mechanism; wherein the alarm level of the second target alarm mechanism is greater than the alarm level of the first target alarm mechanism.

[0019] In an exemplary embodiment, the apparatus further includes a first deletion module, configured to delete the first object feature, the first device feature, and the acquisition time from the first feature library after storing the first object feature, the first device feature, and the acquisition time in the first feature library for a period exceeding the first storage time limit.

[0020] According to another embodiment of this application, a computer program product is also provided, including a computer program configured to have a processor perform the steps in any of the above method embodiments.

[0021] According to yet another embodiment of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, and the computer program is configured to execute the steps in any of the above method embodiments by a processor.

[0022] According to yet another embodiment of this application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to execute the computer program to perform the steps in any of the above method embodiments.

[0023] This application, by establishing a first feature library and a second retrieval library, can differentiate feature comparison needs at different time scales. The second retrieval library stores long-term valid device features, while the first feature library stores short-term object and device features with a shorter initial storage period. This allows for comparison with the most recent features stored in the first feature library when processing events of predetermined types of devices entering a target area. If no match is found in the first feature library, then a comparison is made with the second retrieval library. Due to the short storage time and relatively small size of the first feature library, this quick comparison strategy significantly improves comparison efficiency for events occurring within a short period. Simultaneously, the second retrieval library includes historically detected device features and pre-stored device features, increasing the comprehensiveness and accuracy of the comparison. Furthermore, the comparison process considers not only device features but also the features of the object carrying the device, avoiding false positives and false negatives that may occur when relying solely on device features for identification. Therefore, this solves the problem of low efficiency in determining events of predetermined types of devices entering a target area in related technologies, achieving the effect of efficiently determining such events. Attached Figure Description

[0024] Figure 1 This is a hardware structure block diagram of a mobile terminal for an event determination method according to an embodiment of this application.

[0025] Figure 2 This is a flowchart of an event determination method according to an embodiment of this application;

[0026] Figure 3 This is a schematic diagram of a method for determining an event according to a specific embodiment of this application;

[0027] Figure 4 This is a flowchart of an event determination method according to a specific embodiment of this application. Figure 1 ;

[0028] Figure 5 This is a flowchart of an event determination method according to a specific embodiment of this application. Figure 2 ;

[0029] Figure 6 This is a flowchart of an event determination method according to a specific embodiment of this application. Figure 3 ;

[0030] Figure 7 This is a structural block diagram of an event determination device according to an embodiment of this application. Detailed Implementation

[0031] The embodiments of this application will be described in detail below with reference to the accompanying drawings and examples.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0033] The methods and embodiments provided in this application can be executed on a mobile terminal, a computer terminal, or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for an event determination method according to an embodiment of this application. For example... Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0034] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to an event determination method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thus implementing the aforementioned method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0035] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0036] This embodiment provides a method for determining an event. Figure 2 This is a flowchart of an event determination method according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps:

[0037] Step S202: If it is determined that the target object carries the target device into the target area, the target object characteristics of the target object and the target device characteristics of the target device are obtained, wherein the target area is an area where predetermined types of devices are prohibited from entering.

[0038] Optionally, the target object refers to an individual identified by the system as carrying a specific device in the monitored environment, usually a person. For example, in an early warning method for an electric bicycle battery entering an elevator, the target object refers to the person who brought the battery into the elevator.

[0039] Optionally, the target object features include, but are not limited to, facial features: extracting feature points of the target object's face through facial recognition technology, such as the position and size of the eyes, nose, and mouth, as well as the facial contours, etc.; and body features: including the target object's body shape, walking posture, clothing style, etc.

[0040] Optionally, the target device refers to a specific device that is monitored by the system and enters the target area, including but not limited to living equipment, office equipment, medical equipment, and building equipment.

[0041] Optionally, the target area refers to a specific area set by the system that needs to be monitored and protected. The target area corresponds to a predetermined type of equipment and is an area where the predetermined type of equipment is prohibited from entering, such as batteries and elevators.

[0042] Step S204: If the similarity between the target object feature and the first object feature stored in the first feature library is less than a first threshold, and the similarity between the target device feature and the first device feature stored in the first feature library is less than a second threshold, determine the target similarity between the target device feature and other device features stored in the second feature library. The first object feature is the feature of the first object acquired and stored in the first feature library after determining that the first object performs the target operation on the first device in the first region. The first device feature is the feature of the first device acquired and stored in both the first feature library and the second feature library after determining that the first object performs the target operation on the first device in the first region. The first storage time limit of the features in the first feature library is less than the second storage time limit of the features in the second feature library. The first device is the predetermined type of device. The other device features include device features deleted from the first feature library after their storage time exceeds the first storage time limit and device features pre-stored in the second feature library.

[0043] Optionally, the first feature library refers to a database in the system used for short-term storage of object and device features, typically with a short storage period, designed to match recent events. The second feature library refers to a database in the system used for long-term storage of device features, with a longer storage period.

[0044] Optionally, the first storage time limit refers to the storage time of features in the first feature library, which is relatively short, generally set to a few hours to a few days, and is used to match the features of recently active objects and devices. The second storage time limit refers to the storage time of features in the second feature library, which is relatively long, possibly covering weeks, months or even years, and is used for long-term accumulation and maintenance of the device feature library, so that a certain recognition capability can be maintained even if the device is updated.

[0045] Optionally, the first zone can be any physical space that needs to be monitored or controlled, typically a place with strict requirements for security, compliance, or operational procedures. For example, an electric scooter parking area: In an electric scooter battery warning system, the area where electric scooters are parked is considered the first zone, used to monitor battery retrieval behavior. An airport security checkpoint: In this scenario, the first zone might be a baggage checkpoint, where the system needs to identify any suspicious baggage or prohibited items.

[0046] Optionally, a target operation refers to an action performed on a specific target device within a first area that may trigger subsequent monitoring or warning responses. These operations are typically closely related to safety, compliance, or management requirements. For example, a battery removal operation: in a battery warning scenario for electric bicycles, the target operation is to remove the battery from the electric bicycle.

[0047] Step S206: If the target similarity is greater than or equal to the second threshold, it is determined that there is an event where the predetermined type of device enters the target area.

[0048] In this embodiment, the entity executing the above steps can be a terminal, a server, a specific processor set in the terminal or server, or a processor or processing device set relatively independently of the terminal or server, but is not limited thereto.

[0049] Through the above steps, by establishing a first feature library and a second retrieval library, feature comparison needs at different time scales can be distinguished. The second retrieval library stores long-term valid device features, while the first feature library stores short-term object and device features with a shorter initial storage period. This allows for comparison with the most recent features stored in the first feature library when processing events of predetermined types of devices entering a target area. If no match is found in the first feature library, then a comparison with the second retrieval library is performed. Due to the short storage time and relatively small size of the first feature library, this strategy of quick comparison significantly improves comparison efficiency for events occurring within a short period. Simultaneously, the second retrieval library includes historically detected device features and pre-stored device features, increasing the comprehensiveness and accuracy of the comparison. Furthermore, the comparison process considers not only the device features but also the features of the object carrying the device, avoiding false positives and false negatives that may occur when relying solely on device features for identification. Therefore, this solves the problem of low efficiency in determining events of predetermined types of devices entering a target area in related technologies, achieving the effect of efficiently determining such events.

[0050] In an exemplary embodiment, before acquiring the target object features of the target object and the target device features of the target device when it is determined that the target object carries the target device into the target area, the method further includes: detecting whether the first object performs the target operation on the first device in the first area; if it is determined that the first object performs the target operation, acquiring object video data of the first object and device video data of the first device, and determining the acquisition time; acquiring the first object features from the object video data and the first device features from the device video data; storing the first object features, the first device features, and the acquisition time in the first feature library, and storing the first device features in the second feature library.

[0051] Optionally, detecting whether a first object performs a target operation on a first device within a first area involves identifying and determining specific behaviors occurring within a specific area. The system first monitors the first area (such as a battery parking lot, laboratory, or vault) using video surveillance or sensors. Then, it analyzes the video data using computer vision algorithms and deep learning models to detect whether a target operation has occurred. The target operation can be various behaviors, such as retrieving a battery, opening a safe, or touching hazardous materials. For example, in a school library, the first area might be the book lending area, and the target operation might be a student illegally taking valuable books without registering. The system uses a camera to capture video streams from the lending area and analyzes the student's actions (such as picking up a book and leaving quickly without lingering at the registration desk) to determine if the target operation has occurred. Similarly, to detect whether a battery has entered an elevator, the first area could be a battery parking area, and the target operation might be a user retrieving a battery. The system uses a camera to capture video streams from the battery parking area and analyzes the user's actions to determine if the target operation has occurred.

[0052] Optionally, when the system detects a target operation, it records relevant video data, including video clips of the first object and the first device during the event. Simultaneously, the system accurately records the timestamp of acquiring this video data, which is crucial for subsequent feature extraction and event backtracking.

[0053] Optionally, features of a first object are obtained from the object video data, and features of a first device are obtained from the device video data. In this step, the system performs deep analysis on the acquired video data to extract features of the first object and the first device. For the first object, these features may include facial features, body contours, clothing styles, gait, etc.; while for the first device, features may include size, shape, color, markings, etc. These features are then compared with existing information in the feature library.

[0054] Optionally, the system stores the extracted first object features and first device features, along with the event occurrence time, in a first feature library for rapid comparison of short-term events. The first device features are also additionally stored in a second feature library, which has a longer retention period to accumulate and maintain long-term device feature information, facilitating the identification and matching of devices across different time spans. The features in the second feature library include not only device features extracted from the first region detection but also pre-stored device features obtained from other sources, thus encompassing a broader range of device features.

[0055] This embodiment ensures accurate early warning by determining whether the target object has performed a target operation on the first device within the first area before detecting the target object carrying the target device entering the target area. Simultaneously, the first object's characteristics and the first device's characteristics are stored in a first feature library, while the first device's characteristics are stored separately in a second feature library. This dual-library management mechanism increases the flexibility of feature comparison. The first feature library has a shorter storage period, suitable for rapid response to recent events, while the second feature library preserves device characteristics long-term, maintaining strong identification capabilities even after device upgrades, thus reducing maintenance costs.

[0056] In an exemplary embodiment, detecting whether the first object performs the target operation on the first device in the first region includes: detecting whether the first object performs a first operation on a first component, wherein the first component is used to store a second device, and the first operation is used to open the first component; if it is determined that the first object performs the first operation, detecting whether the first object performs a second operation on the second device stored in the first component, wherein the second operation is used to remove the second device; if it is determined that the first object performs the second operation, detecting whether the second device is the first device; if it is determined that the second device is the first device, detecting whether the first object performs a third operation on the first component, wherein the third operation is used to close the first component; and if it is determined that the first object performs the third operation, determining that the first object performs the target operation.

[0057] Optionally, the first object can be the target object. The first operation refers to the action of opening the first component. This operation is the first step of the target operation and is also the basis for the system to judge subsequent events. For example, opening the battery compartment cover of an electric bicycle.

[0058] Optionally, the first component includes, but is not limited to, components for storing batteries such as the vehicle seat and foot pedals, and the second device includes, but is not limited to, batteries and non-battery devices. The step of determining whether the second device is the same as the first device involves confirming whether the removed device matches the expected device; for example, whether what was removed is indeed a battery and not some other object.

[0059] This embodiment uses a multi-level detection mechanism to decompose the target operation, thereby achieving the goal of accurately determining the target operation.

[0060] In an exemplary embodiment, before determining the target similarity between the target device feature and other device features stored in the second feature library, the method further includes: determining whether the first feature library stores object features and device features; if the first feature library stores object features and device features, determining the similarity between the target object feature and the first object feature, and the similarity between the target device feature and the first device feature, wherein the object feature includes the first object feature, and the device feature includes the first device feature; if the first feature library does not store object features and device features, determining the target similarity; and if the target similarity is greater than or equal to the second threshold, determining that an event has occurred where the predetermined type of device enters the target area.

[0061] In an exemplary embodiment, after determining the similarity between the target object feature and the first object feature, and the similarity between the target device feature and the first device feature, the method further includes: determining that an event exists where the predetermined type of device enters the target area when the similarity between the target object feature and the first object feature is greater than or equal to the first threshold and the similarity between the target device feature and the first device feature is greater than or equal to the second threshold.

[0062] Optionally, if the number of features stored in the first feature library is less than the number of features stored in the second feature library, the similarity comparison between the target object features and the target device features and the first object features and the first device features stored in the first feature library is performed first, thereby improving the comparison efficiency.

[0063] Optionally, if the first feature library does not include any features, the similarity between the target device features and other device features stored in the second feature library can be determined to determine whether there is an event where a specific type of device enters the target area.

[0064] This embodiment first checks a first feature database to quickly confirm whether a specific type of device has entered the target area. Even if there is no record in the first feature database, it can switch to a second feature database for comparison. The second feature database stores long-accumulated device features and can support the identification of a wider range of device types. Through this dual-checking mechanism of the feature databases, the goal of more accurate and efficient event identification is achieved.

[0065] In an exemplary embodiment, after determining that an event has occurred where the predetermined type of device has entered the target area when the target similarity is greater than or equal to the second threshold, the method further includes: triggering a first target alarm mechanism; after determining that an event has occurred where the target object feature is greater than or equal to the first object feature and the target device feature is greater than or equal to the second threshold, the method further includes: triggering a second target alarm mechanism; wherein the alarm level of the second target alarm mechanism is greater than the alarm level of the first target alarm mechanism.

[0066] Optionally, the first target alarm mechanism is a lower-level alarm response process, including but not limited to recording the event, visual or audible warnings, and sending notifications to the monitoring center, aiming to initially alert relevant personnel to potential safety issues. The second target alarm mechanism is a higher-level alarm response process, including but not limited to automatically locking the target area and activating the emergency response team. For example, when detecting whether someone has brought a battery into the elevator, the first target alarm mechanism is triggered: if the similarity of the target object's characteristics exceeds a first threshold, but the similarity of the target device's characteristics is low or does not exceed a second threshold, the system initially confirms that a battery entry event may have occurred, but is not entirely certain. In this case, the system will activate the first target alarm mechanism, which may include: sending a warning message to the property management personnel's mobile phone or the monitoring center, prompting "Suspected battery brought into the elevator, please pay attention to monitoring," and displaying a warning message on the elevator display screen, reminding residents "Do not bring batteries into the elevator." The second target alarm mechanism is triggered when the similarity between the target object's features and the first object's features is greater than or equal to the first threshold, and the similarity between the target device's features and the first device's features is greater than or equal to the second threshold. The system is certain that an event has occurred where a battery has entered the elevator. At this time, a higher-level second target alarm mechanism will be activated to automatically lock the elevator, prevent the elevator from operating, and prevent the battery from entering the elevator interior further.

[0067] This embodiment introduces an alarm level difference between the first and second target alarm mechanisms, enabling appropriate response measures to be taken based on the severity and credibility of the event, avoiding excessive resource consumption and unnecessary human interference. This mechanism not only improves the accuracy and timeliness of early warnings, but also enhances flexibility and efficiency.

[0068] In an exemplary embodiment, after storing the first object feature, the first device feature, and the acquisition time in the first feature library, the method further includes: deleting the first object feature, the first device feature, and the acquisition time from the first feature library if the storage time of the first object feature and the first device feature in the first feature library exceeds the first storage time limit.

[0069] The present invention will now be described in conjunction with specific embodiments:

[0070] Let's take the example of detecting an electric bicycle battery entering an elevator to illustrate this. Figure 3 As shown, the front-end camera captures images of the community's electric vehicle parking area and uploads them to the large-scale cloud platform. The cloud platform analyzes the people and their behavior in the images to determine if anyone is attempting to retrieve a battery. If so, it records the time of the incident, the person's image and characteristics, and the battery's image and characteristics. This information is then deployed to elevator cameras to analyze the characteristics of passengers and their objects. If an elevator is detected entering, a warning or alarm is triggered. Specific steps are as follows... Figure 4 As shown, it includes the following steps:

[0071] S402, people appeared at the electric vehicle parking area.

[0072] S404: Determine if there is a battery removal operation. If yes, proceed to S406; otherwise, proceed to S410.

[0073] S406 captures one or more photos of people, one or more photos of batteries, and obtains the capture time.

[0074] S408, obtain personnel characteristics and obtain battery characteristics.

[0075] S410 stores one or more images of people, one or more images of batteries, personnel characteristics, battery characteristics, and capture time in a temporary retrieval database; stores battery characteristics in a battery retrieval database. Features in the temporary retrieval database exist for a limited time; if the time period (e.g., 4 hours) is exceeded, they are deleted.

[0076] S412, deploy a temporary search database and a battery search database for the elevator camera footage. In addition to deploying the battery search database for the elevator camera footage after determining that a person has taken a battery, it is also necessary to deploy the battery search database for the elevator camera footage when the battery search database is updated with battery characteristics obtained from other means. Other means include, but are not limited to, the network and other parking areas.

[0077] S414, End.

[0078] Determine the battery removal action, such as Figure 5 As shown, it includes the following steps:

[0079] S502, determine the battery removal action.

[0080] S504, determine whether there is an opening action (i.e., first operation) on the seat and foot pedal (i.e., first component). If yes, proceed to S506; otherwise, proceed to S514 to determine that there is no battery removal action.

[0081] S506, determine if there is an operation to retrieve an item; if yes, proceed to S508; otherwise, proceed to S514 to confirm that there is no operation to retrieve the battery.

[0082] S508, determine whether the object in hand is a battery. If yes, proceed to S510; otherwise, proceed to S514 to confirm that there is no battery removal action.

[0083] S510, determine whether there is a cover closing action; if yes, proceed to S512; otherwise, proceed to S514 to determine that there is no battery removal action.

[0084] S512, triggering a battery removal warning.

[0085] S514, End.

[0086] Methods for detecting the presence of batteries in elevators using temporary search databases and battery search databases, such as... Figure 6 As shown, it includes the following steps:

[0087] S602, people appeared in the elevator lobby.

[0088] S604, determine if the person is holding an object; if so, proceed to S606; otherwise, proceed to S626 to confirm that no person is carrying an elevator in the elevator lobby.

[0089] S606, determine if a temporary search database exists; if yes, proceed to S608; otherwise, proceed to S620.

[0090] S608, Compare with the temporary search database.

[0091] S610, comparison of features between the held object and the battery, and comparison of features between personnel.

[0092] S612, determine whether the similarity exceeds the set threshold. If yes, proceed to S614; otherwise, proceed to S616.

[0093] S614, advanced alarm triggered, elevator operation stopped.

[0094] S616, if the similarity between the battery or the person exceeds the threshold, proceed to S618: if the similarity between the person or the object being held exceeds the set threshold, it may be that the person has placed the battery in a bag or other packaging and the battery characteristics cannot be confirmed, or that someone else has carried the battery into the elevator; otherwise, proceed to S620.

[0095] S618 triggered a medium-level alarm, with a voice reminder to people in the elevator: "Please do not bring batteries into the elevator."

[0096] S620, compares the features of the handheld item with the elevator search database.

[0097] S622, determine if the similarity exceeds the set threshold, if so, proceed to S624, otherwise proceed to S626 to determine if no person is present in the elevator room with the elevator.

[0098] S624, triggering a low-level alarm, voice prompt.

[0099] S626, End.

[0100] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0101] This embodiment also provides an event determination device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the systems described in the following embodiments are preferably implemented in software, hardware implementations, or a combination of software and hardware, are also possible and contemplated.

[0102] Figure 7 This is a structural block diagram of an event determination device according to an embodiment of this application, such as... Figure 7 As shown, the device includes:

[0103] The first acquisition module 702 is used to acquire the target object characteristics of the target object and the target device characteristics of the target device when it is determined that the target object carries the target device into the target area, wherein the target area is an area where predetermined types of devices are prohibited from entering.

[0104] The first determining module 704 is configured to determine the target similarity between the target device feature and other device features stored in the second feature library when the similarity between the target object feature and the first object feature stored in the first feature library is less than a first threshold, and the similarity between the target device feature and the first device feature stored in the first feature library is less than a second threshold. The first object feature is the feature of the first object acquired and stored in the first feature library after determining that the first object performs the target operation on the first device in the first region. The first device feature is the feature of the first device acquired and stored in both the first feature library and the second feature library after determining that the first object performs the target operation on the first device in the first region. The first storage time limit of the features in the first feature library is less than the second storage time limit of the features in the second feature library. The first device is the predetermined type of device. The other device features are device features deleted from the first feature library after their storage time exceeds the first storage time limit.

[0105] The second determining module 706 is used to determine, when the target similarity is greater than or equal to the second threshold, that there is an event where the predetermined type of device enters the target area.

[0106] In one exemplary embodiment, the apparatus further includes: a first detection module, configured to detect whether the first object performs the target operation on the first device in the first area before acquiring the target object feature of the target object and the target device feature of the target device, when it is determined that the target object carries the target device into the target area; a second acquisition module, configured to acquire object video data of the first object and device video data of the first device, and determine the acquisition time, when it is determined that the first object performs the target operation; a third acquisition module, configured to acquire the first object feature from the object video data and the first device feature from the device video data; and a first storage module, configured to store the first object feature, the first device feature, and the acquisition time in the first feature library and store the first device feature in the second feature library.

[0107] In an exemplary embodiment, the first detection module includes: a first detection submodule, configured to detect whether the first object performs a first operation on a first component, wherein the first component is used to store a second device, and the first operation is used to open the first component; a second detection submodule, configured to, if it is determined that the first object performs the first operation, detect whether the first object performs a second operation on the second device stored in the first component, wherein the second operation is used to remove the second device; a third detection submodule, configured to, if it is determined that the first object performs the second operation, detect whether the second device is the first device; a fourth detection submodule, configured to, if it is determined that the second device is the first device, detect whether the first object performs a third operation on the first component, wherein the third operation is used to close the first component; and a first determination submodule, configured to, if it is determined that the first object performs the third operation, determine that the first object performs the target operation.

[0108] In an exemplary embodiment, the apparatus further includes: a third determining module, configured to determine whether object features and device features are stored in the first feature library before determining the target similarity between the target device feature and other device features stored in the second feature library; a fourth determining module, configured to determine the similarity between the target object feature and the first object feature, and the similarity between the target device feature and the first device feature, if the object feature and the device feature are stored in the first feature library, wherein the object feature includes the first object feature and the device feature includes the first device feature; a fifth determining module, configured to determine the target similarity if the object feature and the device feature are not stored in the first feature library; and a sixth determining module, configured to determine that an event exists where the predetermined type of device enters the target area if the target similarity is greater than or equal to the second threshold.

[0109] In an exemplary embodiment, the apparatus further includes a seventh determining module, configured to determine, after determining the similarity between the target object feature and the first object feature, and the similarity between the target device feature and the first device feature, an event in which the predetermined type of device enters the target area occurs if the similarity between the target object feature and the first object feature is greater than or equal to the first threshold, and the similarity between the target device feature and the first device feature is greater than or equal to the second threshold.

[0110] In one exemplary embodiment, the apparatus further includes: a first triggering module, configured to trigger a first target alarm mechanism after determining that an event has occurred where the target similarity is greater than or equal to the second threshold; and after determining that an event has occurred where the predetermined type of device has entered the target area, the method further includes: a second triggering module, configured to trigger a second target alarm mechanism; wherein the alarm level of the second target alarm mechanism is greater than the alarm level of the first target alarm mechanism.

[0111] In an exemplary embodiment, the apparatus further includes a first deletion module, configured to delete the first object feature, the first device feature, and the acquisition time from the first feature library after storing the first object feature, the first device feature, and the acquisition time in the first feature library for a period exceeding the first storage time limit.

[0112] Embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0113] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when run.

[0114] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0115] Embodiments of this application also provide an electronic device, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0116] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0117] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0118] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular hardware and software combination.

[0119] The above are merely preferred embodiments of this application and are not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any updates, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A method for determining an event, characterized in that, include: If it is determined that a target object carries a target device into a target area, the target object characteristics of the target object and the target device characteristics of the target device are obtained, wherein the target area is an area where predetermined types of devices are prohibited from entering; If the similarity between the target object feature and the first object feature stored in the first feature library is less than a first threshold, and the similarity between the target device feature and the first device feature stored in the first feature library is less than a second threshold, then the target similarity between the target device feature and other device features stored in the second feature library is determined. The first object feature is the feature of the first object acquired and stored in the first feature library after determining that the first object performs a target operation on the first device in the first region. The first device feature is the feature of the first device acquired and stored in both the first feature library and the second feature library after determining that the first object performs the target operation on the first device in the first region. The first storage time limit of the features in the first feature library is less than the second storage time limit of the features in the second feature library. The first device is the predetermined type of device. The other device features include device features deleted from the first feature library after their storage time exceeds the first storage time limit and device features pre-stored in the second feature library. If the target similarity is greater than or equal to the second threshold, it is determined that an event has occurred where the predetermined type of device has entered the target area.

2. The method according to claim 1, characterized in that, If it is determined that a target object is carrying a target device into a target area, before acquiring the target object characteristics of the target object and the target device characteristics of the target device, the method further includes: Detect whether the first object performs the target operation on the first device within the first area; If it is determined that the first object performs the target operation, the object video data of the first object and the device video data of the first device are acquired, and the acquisition time is determined. Obtain the first object feature from the object video data, and obtain the first device feature from the device video data; The first object features, the first device features, and the acquisition time are stored in the first feature library, and the first device features are stored in the second feature library.

3. The method according to claim 2, characterized in that, Detecting whether the first object performs the target operation on the first device within the first area includes: Detect whether the first object performs a first operation on the first component, wherein the first component is used to store the second device, and the first operation is used to open the first component; If it is determined that the first object performs the first operation, it is detected whether the first object performs a second operation on the second device stored in the first component, wherein the second operation is used to retrieve the second device; If it is determined that the first object is performing the second operation, it is detected whether the second device is the first device; If the second device is determined to be the first device, it is detected whether the first object performs a third operation on the first component, wherein the third operation is used to shut down the first component; If it is determined that the first object performs the third operation, then it is determined that the first object performs the target operation.

4. The method according to claim 1, characterized in that, Before determining the target similarity between the target device features and other device features stored in the second feature library, the method further includes: Determine whether the first feature library stores object features and device features; When the object features and the device features are stored in the first feature library, the similarity between the target object features and the first object features, and the similarity between the target device features and the first device features are determined, wherein the object features include the first object features, and the device features include the first device features; If the object features and the device features are not stored in the first feature library, the target similarity is determined. If the target similarity is greater than or equal to the second threshold, it is determined that an event has occurred where the predetermined type of device has entered the target area.

5. The method according to claim 4, characterized in that, After determining the similarity between the target object features and the first object features, and the similarity between the target device features and the first device features, the method further includes: If the similarity between the target object feature and the first object feature is greater than or equal to the first threshold, and the similarity between the target device feature and the first device feature is greater than or equal to the second threshold, an event is determined that the predetermined type of device has entered the target area.

6. The method according to claim 4, characterized in that, After determining that an event has occurred where the target similarity is greater than or equal to the second threshold, the method further includes: triggering a first target alarm mechanism; After determining that an event has occurred where the similarity between the target object feature and the first object feature is greater than or equal to the first threshold, and the similarity between the target device feature and the first device feature is greater than or equal to the second threshold, the method further includes: triggering a second target alarm mechanism. The alarm level of the second target alarm mechanism is greater than the alarm level of the first target alarm mechanism.

7. The method according to claim 2, characterized in that, After storing the first object features, the first device features, and the acquisition time into the first feature library, the method further includes: If the storage time of the first object feature and the first device feature in the first feature library exceeds the first storage time limit, the first object feature, the first device feature, and the acquisition time shall be deleted from the first feature library.

8. An event determination device, characterized in that, include: The first acquisition module is used to acquire the target object characteristics of the target object and the target device characteristics of the target device when it is determined that the target object carries the target device into the target area, wherein the target area is an area where predetermined types of devices are prohibited from entering; A first determining module is configured to determine the target similarity between the target device feature and other device features stored in a second feature library when the similarity between the target object feature and the first object feature stored in the first feature library is less than a first threshold, and the similarity between the target device feature and the first device feature stored in the first feature library is less than a second threshold. The first object feature is the feature of the first object acquired and stored in the first feature library after determining that the first object performs a target operation on a first device within a first region. The first device feature is the feature of the first device acquired and stored in both the first feature library and the second feature library after determining that the first object performs the target operation on the first device within the first region. The first storage time limit of the features in the first feature library is less than the second storage time limit of the features in the second feature library. The first device is the predetermined type of device. The other device features include device features deleted from the first feature library after their storage time exceeds the first storage time limit and device features pre-stored in the second feature library. The second determining module is used to determine, when the target similarity is greater than or equal to the second threshold, that there is an event that the predetermined type of device has entered the target area.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the method described in any one of claims 1 to 7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 7.

Images