WO2023279716A1

WO2023279716A1 - Device linkage method and apparatus, and device, storage medium, program product and computer program

Info

Publication number: WO2023279716A1
Application number: PCT/CN2022/076210
Authority: WO
Inventors: 李龙; 黄王爵; 刘高卫; 库博; 熊阅文
Original assignee: 上海商汤智能科技有限公司
Priority date: 2021-07-07
Filing date: 2022-02-14
Publication date: 2023-01-12
Also published as: TW202303399A; CN113486799A

Abstract

Provided in the embodiments of the present disclosure are a device linkage method and apparatus, and a device, a storage medium, a program product and a computer program. The method comprises: acquiring trigger data transmitted by a trigger device, and a linkage policy set for the trigger device, wherein the linkage policy at least comprises a preset abnormal event and a linkage device associated with the trigger device; on the basis of the preset abnormal event in the linkage policy, performing detection on the trigger data to obtain a detection result; in response to the detection result being that the abnormal event is detected, triggering the linkage device to acquire image data that comprises the abnormal event; and storing the image data that comprises the abnormal event.

Description

Device linkage method, device, device, storage medium, program product, and computer program

Cross References to Related Applications

This disclosure is based on the Chinese patent application with the application number 202110765584.1, the application date is July 07, 2021, and the application name is "equipment linkage method, device, equipment, storage medium and program product", and requires the priority of the Chinese patent application Right, the entire content of this Chinese patent application is hereby incorporated into this disclosure as a reference.

technical field

The present disclosure relates to but not limited to the field of information technology, and in particular relates to a device linkage method, device, device, storage medium, program product and computer program.

Background technique

With the development of information technology, there may be coordination and linkage between multiple devices. However, in the related art, the cooperation and linkage of devices can only be performed between devices of the same type, and the linkage mode between devices and the event that triggers the linkage are relatively simple, and the linkage between devices cannot be flexibly realized.

Contents of the invention

Embodiments of the present disclosure provide a device linkage method, device, device, storage medium, program product, and computer program.

The technical scheme of the embodiment of the present disclosure is realized in this way:

An embodiment of the present disclosure provides a device linkage method, the method including:

Acquiring the trigger data transmitted by the trigger device, and the linkage strategy set for the trigger device; the linkage strategy includes at least a preset abnormal event and a linkage device associated with the trigger device;

Detecting the trigger data based on the preset abnormal events in the linkage strategy to obtain a detection result;

In response to the detection result being the detection of the abnormal event, triggering the linkage device to acquire image data including the abnormal event;

The image data including the abnormal event is saved.

An embodiment of the present disclosure provides an equipment linkage device, which includes:

The first acquisition part is configured to acquire the trigger data transmitted by the trigger device, and the linkage strategy set for the trigger device; the linkage strategy includes at least a preset abnormal event and a linkage device associated with the trigger device;

The detection part is configured to detect the trigger data based on the abnormal event preset in the linkage strategy, and obtain a detection result;

A triggering part configured to trigger the linkage device to acquire image data including the abnormal event in response to the detection result being the detection of the abnormal event;

A saving section configured to save the image data including the abnormal event.

An embodiment of the present disclosure provides a computer device, including a memory and a processor, the memory stores a computer program that can run on the processor, and the processor implements some or all of the steps in the above method when executing the program.

An embodiment of the present disclosure provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, part or all of the steps in the above method are implemented.

An embodiment of the present disclosure provides a computer program, including computer readable codes. When the computer readable codes are run in a computer device, a processor in the computer device implements part or all of the steps in the above method.

An embodiment of the present disclosure provides a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program. When the computer program is read and executed by a computer, a part or part of the above method is implemented. All steps.

In the embodiment of the present disclosure, the trigger data transmitted by the trigger device and the linkage strategy set for the trigger device are obtained; the linkage strategy includes at least the preset abnormal event and the linkage device associated with the trigger device; based on the preset exception in the linkage strategy An event is used to detect the trigger data to obtain a detection result; in response to the detection result being an abnormal event detected, the linkage device is triggered to acquire image data including the abnormal event; and the image data including the abnormal event is saved. In this way, the trigger data can be detected based on the abnormal event preset in the linkage strategy, and when an abnormal event is detected, the linkage device associated with the trigger device preset in the linkage strategy can be triggered to obtain the image data including the abnormal event, And save the image data. In this way, the flexibility of device linkage can be improved by flexibly configuring the abnormal event and the linkage device associated with the trigger device in the linkage strategy, and the image data including the abnormal event can be accurately acquired and saved, which is convenient Playback and analysis of abnormal events.

Description of drawings

FIG. 1 is a schematic diagram of an implementation flow of a device linkage method provided by an embodiment of the present disclosure;

FIG. 2 is a schematic diagram of the implementation flow of a device linkage method provided by an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of the implementation flow of a device linkage method provided by an embodiment of the present disclosure;

FIG. 4 is a schematic flow diagram of an implementation process of a device linkage method provided by an embodiment of the present disclosure;

FIG. 5A is a schematic diagram of the implementation flow of a device linkage method provided by an embodiment of the present disclosure;

FIG. 5B is a schematic diagram of the implementation flow of a device linkage method provided by an embodiment of the present disclosure;

FIG. 5C is a schematic diagram of functional modules of a device linkage method provided by an embodiment of the present disclosure;

FIG. 5D is a schematic diagram of an interactive interface for creating a linkage device group provided by an embodiment of the present disclosure;

FIG. 5E is a schematic diagram of an interactive interface for selecting linked abnormal events provided by an embodiment of the present disclosure;

FIG. 5F is a schematic diagram of an interactive interface for setting a linkage cycle provided by an embodiment of the present disclosure;

FIG. 5G is a schematic diagram of a configuration interface of a custom timetable provided by an embodiment of the present disclosure;

FIG. 5H is a schematic diagram of an interactive interface for selecting a deep neural network model provided by an embodiment of the present disclosure;

FIG. 5I is a schematic diagram of a video playback interface of an abnormal event provided by an embodiment of the present disclosure;

FIG. 6 is a schematic diagram of the composition and structure of an equipment linkage device provided by an embodiment of the present disclosure;

FIG. 7 is a schematic diagram of a hardware entity of a computer device provided by an embodiment of the present disclosure.

detailed description

In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the technical solutions of the present disclosure will be further elaborated below in conjunction with the accompanying drawings and embodiments, and the described embodiments should not be regarded as limiting the present disclosure. All other embodiments obtained under the premise of no creative work belong to the protection scope of the present disclosure.

In the following description, references to "some embodiments" describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or a different subset of all possible embodiments, and Can be combined with each other without conflict.

If there is a similar description of "first/second" in the application documents, add the following explanation. In the following description, the terms "first/second/third" are only used to distinguish similar objects and do not mean With regard to the specific ordering of objects, it can be understood that "first/second/third" can be interchanged in specific order or sequential order if allowed, so that the embodiments of the present disclosure described here can operate in a performed in an order other than that shown or described.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. The terms used herein are for the purpose of describing the present disclosure only, and are not intended to limit the present disclosure.

An embodiment of the present disclosure provides a device linkage method, which can be applied to a platform server and executed by a processor of the platform server. Wherein, the platform server can be any suitable computer equipment, such as server, intelligent traffic device, camera capture machine, network camera, notebook computer, tablet computer, desktop computer, smart TV, set-top box, mobile device (such as mobile phone, portable video player) , personal digital assistants, dedicated messaging devices, portable game devices) and other devices with data processing capabilities. Fig. 1 is a schematic diagram of the implementation flow of a device linkage method provided by an embodiment of the present disclosure. As shown in Fig. 1, the method includes the following steps S101 to S104:

Step S101 , acquiring trigger data transmitted by a trigger device, and a linkage strategy set for the trigger device; the linkage strategy includes at least a preset abnormal event and a linkage device associated with the trigger device.

Here, the trigger data is any suitable data that can be used to determine whether to trigger device linkage, including but not limited to image data (such as captured images, collected video streams, etc.), audio data, device operation information, etc. or more. The trigger device can be any suitable device capable of obtaining trigger data, including but not limited to image acquisition devices (such as capture cameras, cameras, network cameras, etc.), audio collection devices (such as microphones, etc.), intelligent sensing devices (such as smart traffic devices , sensors for sensing the environment, infrared sensing equipment, etc.), signal detectors for equipment, etc., or one or more of them. During implementation, the platform server can obtain the trigger data collected by the trigger device and transmitted in real time, or the trigger device can save the collected trigger data, and then transmit the stored trigger data to the trigger device based on the data request of the platform server. limited.

The linkage strategy may be any appropriate strategy set for the trigger device, defining or restricting the linkage of the trigger device. The linkage strategy includes at least a preset abnormal event and a linkage device associated with the triggering device. Preset abnormal events are preset abnormal events used to trigger device linkage, for example, preset abnormal objects, abnormal behaviors, abnormal tracks, abnormal scenarios, device alarms, abnormal device operation, device power failure, environmental abnormalities, etc. . The linkage device associated with the trigger device is preset according to the actual scene, any suitable device that needs to be linked with the trigger device in the event of a preset abnormal event, including but not limited to image acquisition equipment, audio acquisition equipment One or more of , alarm device, server, etc. During implementation, different linkage strategies may be set for each trigger device, or the same linkage strategy may be set for two different trigger devices, which is not limited here.

It should be noted that, during implementation, the platform server can be deployed independently, or can be deployed together with the trigger device or linkage device. The triggering device and the linkage device can be the same device or different devices. In the case that the trigger device and the linkage device are not the same device, the trigger device and the linkage device may be installed in the same location area, or may be installed in different location areas, which is not limited here.

Step S102, based on the abnormal event preset in the linkage strategy, the trigger data is detected to obtain a detection result.

Here, according to the abnormal event preset in the linkage strategy, the trigger data may be detected in an appropriate manner to determine whether the abnormal event occurs and obtain the detection result. Detection results may include information indicative of whether an abnormal event has occurred. When an abnormal event occurs, the detection result may also include relevant information of the abnormal event, such as the start time, end time, and abnormal type of the abnormal event, which are not limited here.

For example, the preset abnormal event in the linkage strategy is the preset abnormal behavior, and the trigger data is the video stream collected by the passing equipment of the subway entrance channel. Based on the preset abnormal behavior, the collected video stream can be detected and detected. result. The detection result may include whether a preset abnormal behavior is recognized in the video stream. When a preset abnormal behavior is identified, the detection result may also include information such as the start time, end time, and associated objects of the abnormal behavior in the video stream.

As another example, the preset abnormal event in the linkage strategy is the preset abnormal operation of the equipment, and the trigger data is the operating data of the image acquisition equipment. Based on the preset abnormal operation of the equipment, the operating data of the image acquisition equipment can be detected to obtain the detected As a result, the detection result may include whether the image acquisition device is operating abnormally. If the device is operating abnormally, the detection result may also include information such as the start time, end time, and abnormal type of the image acquisition device.

Step S103, in response to the detection result being the detection of the abnormal event, triggering the linkage device to acquire image data including the abnormal event.

Here, when the detection result is that the abnormal event is detected, the platform server may trigger the linkage device to acquire image data including the abnormal event. The image data containing the abnormal event may include one or more image frames that can reflect the abnormal event, and may also include a video stream containing the occurrence process of the abnormal event. During implementation, the image data of the abnormal event may be obtained in an appropriate manner according to the actually detected abnormal event, which is not limited here. For example, if the abnormal event is a preset abnormal object, the linkage device may be triggered to capture one or more image frames containing the abnormal object. For another example, if the abnormal event is a preset abnormal behavior, the linked device may be triggered to record a video stream including the abnormal behavior based on the start time and end time of the abnormal behavior. For another example, if the abnormal event is that the triggering device is removed, the linkage device may be triggered to capture one or more image frames containing the object of the removed device.

Step S104, saving the image data including the abnormal event.

Here, the platform server may store the image data including abnormal events in any suitable manner, including but not limited to one or more stored locally on the platform server, in a database or in the cloud, which is not limited here.

In some embodiments, the linkage device in the linkage strategy includes at least one of the following: an image acquisition device, and a platform server.

In some embodiments, when the trigger data is at least one of online video streams, captured images, and device operation information, the linkage device is an image acquisition device.

Here, the online video stream may include a real-time video stream collected online by a trigger device, for example, a real-time video stream collected online by a network camera, a live video, and the like.

The captured image may be an image captured by the capture machine based on a specific capture strategy, for example, a captured image of a human face, a captured image of a license plate, and the like.

The device running information may include, but is not limited to, one or more of the triggering device's running time, power, processor temperature, memory, disk utilization, network connection status, and the like.

The image acquisition device may include, but not limited to, one or more of a video recording device, an image capture device, and the like. During implementation, when the trigger data is online video streams, captured images, or equipment operating information, it is necessary to obtain online image data including abnormal events corresponding to the online video streams, captured images, or equipment operating information. Therefore, in the linkage strategy The linkage device may be an image acquisition device.

For the case where the trigger data is an online video stream, the corresponding trigger device is a video capture device, such as a camera, etc., and the linkage device is an image capture device, which can include the video capture device as the trigger device, or other images different from the trigger device collection equipment.

For the case where the trigger data is a captured image, the corresponding trigger device is an image capture device, such as a traffic device with an image capture function, a capture electronic eye, etc., and the linkage device is an image capture device, which may include a video capture device as a trigger device, or Include other image acquisition devices than trigger devices.

For the case where the trigger data is device operation information, the corresponding trigger device can be any suitable electronic device, such as a network camera, a traffic device with image capture function, a capture electronic eye, etc., and the linkage device can be any suitable image acquisition device.

In some embodiments, when the trigger data is at least one of online video streams, captured images, and device operation information, triggering the linkage device described in step S103 to acquire images including the abnormal event Data, including the following steps S111 to S112:

Step S111, sending a recording instruction to the image acquisition device;

Step S112, receiving the image data including the abnormal event sent by the image acquisition device in response to the recording instruction. Here, the image acquisition device may record image data including abnormal events in response to the recording instruction, and send the recorded image data to the platform server. During implementation, the recording instruction may include any suitable information for instructing the image acquisition device to record image data, including but not limited to the start time and end time of the abnormal event, the pixels of the image data, the type of image data (such as video stream type, image type, etc.), etc.

In some embodiments, when the trigger data is a recorded video stream, the linkage device is the platform server; the triggering of the linkage device described in the above step S103 to obtain the information including the abnormal event The image data includes: step S121, intercepting the image data including the abnormal event from the recorded video stream. Here, after determining that the recorded video stream includes the image data of the abnormal event in any suitable manner, the image data including the abnormal event may be intercepted from the video stream. For example, the start time and end time of the abnormal event may be acquired, and image data including the abnormal event may be intercepted from the recorded video stream based on the start time and end time. For another example, the image data containing the abnormal event may be identified from the recorded video stream based on the characteristics of the abnormal event, so as to intercept the image data.

In some embodiments, the linkage strategy also includes a linkage period, and the method further includes the following step S131 or step S132:

Step S131, setting the working time of the trigger device as the linkage period.

Here, the linkage period is used to represent the validity period of the linkage strategy. By setting the working time of the trigger device as the linkage period, the trigger device only transmits the trigger data during the linkage period, so that the linkage strategy is only valid within the linkage period. During implementation, the linkage period may include, but not limited to, the date, time point, time period, etc. when the linkage strategy takes effect. In some embodiments, the linkage cycle can be the date, time point or period of time that is repeated periodically, for example, from the 1st to the 5th of each month, from Monday to Friday every day, at 8:00 am every day, and from 11:00 to 13:00 every day Wait. In some embodiments, the linkage period can also be a non-repeating date, time point, time period, etc., such as May 2021, June 1, 2021, and June 5, 2021 from 10:00 to 11:00, etc. In some embodiments, the linkage period may be a full period, that is, the linkage strategy is always valid.

Step S132, in response to the occurrence time of the trigger data being within the linkage period, the trigger data is detected based on the abnormal event preset in the linkage strategy.

In some embodiments, the method further includes: step S141 , discarding the trigger data in response to the occurrence time of the trigger data not within the linkage period. Here, for the trigger data whose occurrence time is not discarded within the linkage period, the platform server will not detect the abnormal event of the trigger data.

In the above embodiment, the linkage strategy also includes a linkage period used to characterize the validity period of the linkage strategy. In this way, the linkage strategy can only take effect within the linkage period, so that the linkage between the trigger device and the linkage device can be made more accurate, and It can improve the utilization rate of computing resources.

In some embodiments, the linkage device further includes an alarm device, and the method further includes the following step S151 or step S152:

Step S151, triggering the alarm device to output alarm information in response to the detection result being the detection of the abnormal event.

Here, the warning device may include, but is not limited to, a warning indicator light, an audible alarm, an electronic device with a function of receiving information or outputting voice, and the like. Alarm information may include, but not limited to, indicator light signals, alarm bell signals, alarm prompt information, alarm voices, and the like. During implementation, an appropriate alarm device may be determined according to the actual situation, and the alarm information may be output in an appropriate manner, which is not limited here.

Step S152, discarding the trigger data in response to the detection result being that the abnormal event is not detected. Here, for the trigger data that is discarded without detecting an abnormal event, the platform server will not trigger the linkage of the linkage device, that is, will not trigger the linkage device to acquire image data.

In some embodiments, when the trigger data is image data, the abnormal event includes at least one of the following: the object information contained in the image data does not match the preset object information; the first information contained in the image data Does not match the second information; the object information contained in the image data is associated with the preset abnormal attributes.

Here, the image data may include but not limited to one or more of the collected image information of the object, the collected image information of the ID card, the collected two-dimensional code image information, and the like. The object information contained in the image data may include but not limited to one or more of the object’s characteristic information, attribute information, identification information, etc., for example, the identity information, appearance characteristics, wearing accessories characteristics, etc. The object identity, identity type, object attributes, etc. contained in the QR code image information, the object identity, time information, object attributes, etc. contained in the QR code image information. The preset object information may be feature information, attribute information or identification information of the object preset by the user or defaulted by the system.

When the object information contained in the image data does not match the preset object information, it can be determined that an abnormal event has occurred, for example, the object identification information contained in the image data does not match the preset object identification information, and the image data contains The attribute information of the object does not match the preset attribute information, the identity type of the object contained in the image data does not match the preset identity type, and the time information contained in the QR code image information does not match the preset valid time range. match.

The image data may contain the first information and the second information for matching at the same time, wherein the first information and the second information may be any suitable information that needs to be matched in the image data determined according to the actual application scene, and may include but It is not limited to one or more of object attributes, object identifiers, ID card information, pass card identifiers, two-dimensional code information, license plate numbers, and vehicle features. In a case where the first information included in the image data does not match the second information, it may be determined that an abnormal event has occurred. For example, the first information and the second information may be the face information of the subject to be matched and the image information of the ID card respectively, and if the face information of the subject included in the image data does not match the image information of the ID card, it may be determined that an abnormal event has occurred . For another example, the first information and the second information may be the pass card number and the pass QR code to be matched respectively, and if the pass card identification contained in the image data does not match the pass QR code, it may be determined that an abnormal event has occurred. For another example, the first information and the second information may be the license plate number and vehicle features to be matched respectively, and if the license plate number contained in the image data does not match the vehicle features, it may be determined that an abnormal event has occurred.

In some embodiments, the first information and the second information included in the image data may also be two kinds of object information representing the collected object, namely the first object information and the second object information, for example, the first object information and the second object information. The two object information can be one of the collected image information of the object, the collected image information of the ID card, and the collected two-dimensional code image information, etc., and the image data contains the first object information and the second object information. In the case that the objects do not match, it can be determined that an abnormal event has occurred. For example, when the first object information and the second object information are the image information of the collected object and the image information of the ID card respectively, the image information of the object represented The object does not match the object represented by the image information of the ID card. When the first object information and the second object information are the image information of the collected object and the image information of the QR code respectively, the image information represented by the object The object does not match the object represented by the image information of the two-dimensional code. When the first object information and the second object information are the image information of the collected ID card and the image information of the two-dimensional code, the image of the ID card The object represented by the information does not match the object represented by the image information of the two-dimensional code.

The abnormal attribute may be a preset attribute that indicates an abnormality of the object, for example, the object does not wear a mask, the object has no access permission, and the object has abnormal health status. When the object information contained in the image data is associated with the preset abnormal attributes, it can be determined that an abnormal event has occurred. The wearing configuration feature of the object contained in the data indicates that the object is not wearing a mask, the object attribute represented by the two-dimensional code image information contained in the image data matches the preset abnormal attribute, and the time information contained in the two-dimensional code image information matches the preset abnormal attribute. The valid time range set does not match.

In some embodiments, when the trigger data is device operation information, the abnormal event includes at least one of the following: device hardware failure; device power supply abnormality; device network abnormality; device environment abnormality. Taking the trigger device as a pass-through device as an example, device hardware failures may include but are not limited to device removal, forced door opening, door contact timeout, etc. Device power failures may include but not limited to device power failure, device power shortage, Bluetooth module power shortage, etc. , Device network abnormalities may include but are not limited to offline devices, limited access to the device network, etc., and device environment abnormalities may include but are not limited to camera pollution of passing devices, device attacks, fire alarms in the device environment, etc.

An embodiment of the present disclosure provides a device linkage method, which can be executed by a platform server. As shown in Figure 2, the method includes the following steps S201 to S206:

Step S201, acquiring trigger data transmitted by a trigger device, and a linkage strategy set for the trigger device; the linkage strategy includes at least a preset abnormal event and a linkage device associated with the trigger device.

Step S202, based on the abnormal event preset in the linkage strategy, the trigger data is detected to obtain a detection result.

Step S203, in response to the detection result being the detection of the abnormal event, triggering the linkage device to acquire image data including the abnormal event.

Step S204, saving the image data including the abnormal event.

Here, the above-mentioned steps S201 to S204 correspond to the above-mentioned steps S101 to S104, and the specific implementation manners of the above-mentioned steps S101 to S104 can be referred to for implementation.

Step S205, in response to the configuration operation of the linkage strategy, present the first configuration interface; the first configuration interface is used to set the trigger device, associating the linkage device with the trigger device and setting the trigger device Set the abnormal events to be detected.

Here, the trigger device can be configured on the first configuration interface, such as adding a trigger device, updating an associated policy of the trigger device, and the like. During implementation, the user can configure a suitable trigger device according to the actual application scenario, and configure the associated linkage device and abnormal events to be detected for the trigger device.

Step S206, based on the setting operation for the trigger device and the linkage device in the first configuration interface, obtain a linkage policy for the trigger device; wherein, the quantitative relationship between the trigger device and the linkage device includes One of the following: one-to-one, one-to-many, many-to-one, many-to-many.

Here, the linkage policy of the trigger device includes preset abnormal events and linkage devices associated with the trigger device. Based on the setting operation for the trigger device and linkage device in the first configuration interface, the preset abnormal event and the linkage device associated with the trigger device can be obtained. , so that the linkage policy for the triggering device can be obtained.

In the embodiment of the present disclosure, in response to the configuration operation of the linkage policy, a first configuration interface for setting the trigger device, associating the linkage device with the trigger device, and setting the abnormal event to be detected for the trigger device is presented, based on the first The setting operation of the trigger device and the linkage device in the configuration interface can obtain the linkage strategy for the trigger device, where the quantity relationship between the trigger device and the linkage device includes one of the following: one-to-one, one-to-many, many-to-one, Many to many. In this way, users can flexibly set trigger devices on the first configuration interface according to actual business needs, and configure abnormal events for trigger devices and linkage devices associated with trigger devices, thereby further improving the flexibility of device linkage and better meeting business requirements. need.

An embodiment of the present disclosure provides a device linkage method, which can be executed by a platform server. As shown in Figure 3, the method includes the following steps S301 to S304:

Step S301, acquiring trigger data transmitted by a trigger device, and a linkage strategy set for the trigger device; the linkage strategy includes at least a preset abnormal event and a linkage device associated with the trigger device. Wherein, when the trigger data is a video stream, the abnormal event includes a preset abnormal scene.

Here, the above-mentioned step S301 corresponds to the above-mentioned step S101, and the specific implementation manner of the above-mentioned step S101 can be referred to for implementation.

Step S302, based on the abnormal scene preset in the linkage strategy, using a scene model matching the abnormal scene, to detect the video stream, and obtain a detection result indicating whether the abnormal scene is detected.

Here, the abnormal scene can be a preset abnormal scene, and a scene model matching the abnormal scene can be pre-configured for each abnormal scene, and the scene model can be an algorithm model customized for the abnormal scene in advance. The scene model can accurately detect abnormal scenes in the video stream, and obtain detection results indicating whether abnormal scenes are detected.

Step S303, in response to the detection result being the detection of the abnormal event, triggering the linkage device to acquire image data including the abnormal event.

Step S304, saving the image data including the abnormal event.

Here, the above-mentioned steps S303 to S304 correspond to the above-mentioned steps S103 to S104, and the specific implementation manners of the above-mentioned steps S103 to S104 can be referred to for implementation.

In the embodiment of the present disclosure, when the trigger data is a video stream, the abnormal event includes a preset abnormal scene, and based on the preset abnormal scene in the linkage strategy, the video stream is detected using a scene model that matches the abnormal scene , to obtain a detection result representing whether the abnormal scene is detected. In this way, abnormal scenes in the video stream can be detected more accurately, so that image data including abnormal events can be acquired and saved more accurately, which is convenient for playback and analysis of abnormal events.

An embodiment of the present disclosure provides a device linkage method, which can be executed by a platform server. As shown in Figure 4, the method includes the following steps S401 to S405:

Step S401, acquiring trigger data transmitted by a trigger device, and a linkage strategy set for the trigger device; the linkage strategy includes at least preset abnormal events and linkage devices associated with the trigger device.

Step S402, based on the abnormal events preset in the linkage strategy, the trigger data is detected to obtain a detection result.

Step S403, in response to the detection result being that the abnormal event is detected, the linkage device is triggered to acquire image data including the abnormal event.

Step S404, saving the image data including the abnormal event.

Here, the above-mentioned steps S401 to S104 correspond to the above-mentioned steps S101 to S104, and the specific implementation manners of the above-mentioned steps S101 to S104 can be referred to for implementation.

Step S405, outputting image data including the abnormal event in response to the playback operation on the abnormal event.

Here, the user can perform playback operations of abnormal events in the platform server. The image data including the abnormal event may be one or more image frames including the abnormal event, or may be a video stream including the abnormal event. During implementation, in response to the playback operation on the abnormal event, the image data including the abnormal event may be output in any suitable manner, for example, one or more image frames including the abnormal event may be displayed, or a video including the abnormal event may be played flow.

In the embodiment of the present disclosure, image data including the abnormal event may be output in response to a playback operation on the abnormal event. In this way, the user can conveniently look back at the image data including the abnormal event acquired by the linkage device after the abnormal event occurs, so as to facilitate the acquisition of on-site information of the abnormal event and facilitate further analysis of the abnormal event.

The following describes the application of the device linkage method provided by the embodiments of the present disclosure in actual scenarios. The cooperation and linkage of multiple devices can provide a combined Collaborative applications, through the alarm sent by a trigger device, link other devices to complete the linkage response, which can greatly improve the ability to capture abnormal events.

The interconnection and collaborative linkage of multiple devices is quite complicated, and it is necessary to uniformly manage different types of devices and configure corresponding linkage strategies and solutions. In the realization of multi-device interconnection and collaborative linkage, firstly, the independent operation status of the equipment cannot be affected, and the master-slave linkage mode needs to be configured, that is, the alarm trigger device and the linkage equipment; secondly, flexible configuration is required in the dimension of linkage time to determine The time for linkage between devices and the time for each to work independently; finally, it is necessary to classify and process abnormal events from different event dimensions to complete alarms and coordinated responses, thereby improving the accuracy and application value of equipment linkage.

The embodiment of the present disclosure provides a device linkage method, which can realize the following functions:

1) Use the deep learning model to predict and analyze abnormal events; among them, abnormal events can include abnormal object recognition, trajectory tracking, abnormal behavior recognition, etc., and can be modeled by using the powerful description ability of deep neural network to obtain a variety of abnormal events prediction and analysis models.

2) Fully open up the connection between different types of devices, such as the connection of traffic devices (also known as traffic panel machines, traffic terminals, etc.), capture machines, network cameras and other devices, and bind multiple devices as a collaborative linkage group. Multiple devices in the linkage group can automatically cooperate to complete the set tasks under the configured linkage cycle and abnormal events.

3) According to the linkage strategy, the trigger time of abnormal events and the recording time set by the system, the precise recording of abnormal events can be completed, and the real-time alarm of abnormal events can be realized, and the playback data can be viewed afterwards.

In some embodiments, the method can be applied to a platform server, and the platform server can connect and access protocols through Internet of Things devices (such as Open Network Video Interface Forum (Open Network Video Interface Forum, ONVIF), Real Time Streaming Protocol (Real Time Streaming Protocol, RTSP) etc.) to access the network camera (IP Camera, IPC), and unified management with the traffic device and the capture machine, the traffic device, the capture machine or the IPC can be set as the trigger device, and the IPC can also be set as linkage equipment.

In some embodiments, the prediction results of various face, human body and behavior algorithms can be used as trigger events, or the signal of the trigger device itself can be used as trigger events, such as device removal, camera pollution, etc. Create an abnormal event alarm, and trigger the linkage device bound to the trigger device to complete the recording task according to the linkage policy.

In some embodiments, the linkage policy can bind the trigger device with the linkage device through set rules. The quantity relationship between the mutually bound trigger devices and linkage devices may include one-to-one, one-to-many, many-to-one or many-to-many. In the process of setting the linkage strategy, the linkage period can also be set by setting a flexible linkage schedule, and the abnormal events to be detected and the alarm events of the equipment can be set. After the linkage policy is set, the detection result of the trigger data can be obtained based on the set linkage policy.

Fig. 5A is a schematic diagram of the implementation flow of a device linkage method provided by an embodiment of the present disclosure. As shown in Fig. 5A, the method includes the following steps S501 to S505:

In step S501, a video clip in a video stream is obtained from an IPC.

Step S502, use the neural network model to detect abnormal events in the acquired video clips, and obtain the detection results; wherein, the abnormal events are for various parts of scenes and objects (such as the face or body of an animal, such as human face, human body, vehicle, etc.). license plate number), the behavior of the object (behavior of the animal, the behavior of the vehicle), during implementation, according to the set abnormal event, the neural network model pair that matches the abnormal event can be selected from the preset algorithm warehouse Video clips for anomalous event detection.

Step S503, based on the detection result, it is judged whether there is an abnormal event in the video segment.

Step S504, when there is an abnormal event in the video clip, according to the linkage strategy of the IPC, trigger the video recording device to record the video, obtain the video data including the abnormal event, and link the alarm device to give an alarm; wherein, the linkage strategy can be Including the linked device associated with the IPC, the linked time, and the abnormal events that need to be linked.

Step S505, if there is no abnormal event in the video clip, discard the current video clip.

Fig. 5B is a schematic diagram of the implementation flow of a device linkage method provided by an embodiment of the present disclosure. As shown in Fig. 5B, the method includes the following steps S511 to S516:

Step S511, acquiring device operation information or images captured by the traffic device from the traffic device.

Step S512, judging whether there is an abnormal event in the equipment operation information or the captured image.

Step S513, if there is no abnormal event in the equipment operation information or the captured image, discard the equipment operation information or the captured image.

Step S514, when there is an abnormal event in the device operation information or the captured image, the linkage alarm device outputs alarm information, and judges whether to trigger the linkage strategy based on the linkage strategy of the passing device; during implementation, it can be based on the linkage strategy Including the linkage equipment associated with the traffic equipment, the linkage period, and the abnormal events that need to be linked, and determine whether to trigger the linkage strategy.

Step S515, if the linkage strategy is not triggered, the warning information is discarded;

Step S516, when the linkage strategy is triggered, cooperatively trigger the video recording device to perform video recording, and obtain the video data including the abnormal event.

In some embodiments, referring to FIG. 5C , a device linkage method provided by an embodiment of the present disclosure may include the following three functional modules: a linkage strategy configuration module 51, a deep neural network analysis module 52, and a recording and playback module 53, wherein, Based on the linkage strategy configuration module, users can set linkage strategies, including creating linkage device groups, setting linkage cycles, and selecting linkage abnormal events; the deep neural network analysis module can output intelligent analysis results based on the set linkage strategy; recording and The playback module can link the video recording device to record video data including the abnormal event when the intelligent analysis result indicates that there is an abnormal event.

The implementation of these three functional modules is described below:

1) Linkage strategy configuration module:

This module can provide an interactive interface for configuring linkage strategies. Users can configure linkage strategies on this interface, including:

a) Creating a linked device group: see FIG. 5D. FIG. 5D is a schematic diagram of an interactive interface for creating a linked device group provided by an embodiment of the present disclosure. As shown in FIG. 5D, the user can create a linked device group on the interactive interface, including Set the linkage strategy name in the linkage strategy name input box 521, select the traffic device in the traffic device input box 522, and select the recording device in the recording device input box 523, wherein the quantitative relationship between the traffic device and the recording device can be Determine according to the actual situation, such as multi-pass device to single recording device, single-pass device to multi-recording device, etc.

b) Selecting linked abnormal events: see FIG. 5E, which is a schematic diagram of an interactive interface for selecting linked abnormal events provided by an embodiment of the present disclosure. As shown in FIG. 5E, users can select The abnormal events that need to be linked, including the abnormal detection event 531 and the device alarm event 532, can be selected multiple or all. Detect abnormal events are abnormal events determined by detection of video stream data, such as mismatch of person ID, person card, person code, visitor not within the validity period, not within the timetable, invalid ID card, invalid card, invalid QR code, abnormal body temperature, not wearing a mask, no identity check, no health code check, etc. Device alarm events are abnormal events determined based on device operation information, such as device removal, forced door opening, door sensor timeout, password cracking, offline alarm, Bluetooth low power, abnormal connection of thermal imager, camera pollution, non-living attack, fire alarm , Face feature extraction failure, face capture abnormality, camera abnormality, etc.

c) Setting the linkage cycle: see FIG. 5F. FIG. 5F is a schematic diagram of an interactive interface for setting the linkage cycle provided by the embodiment of the present disclosure. As shown in FIG. 5F, the user can set the linkage cycle in the interactive interface, and support the selection of all periods 541 or a self-defined timetable 542 as the linkage period, wherein, the configuration interface of the self-defined timetable is shown in FIG.

2) Deep neural network analysis module:

This module can analyze the input video stream data, output algorithm analysis results to determine whether abnormal events occur, and trigger abnormal linkage event alarms in the event of abnormal events. Among the abnormal events that trigger linkage, in addition to the abnormal signals in the equipment operation information, the triggers of more abnormal events can be obtained by analyzing the video stream data. FIG. 5H is a schematic diagram of an interactive interface for selecting a deep neural network model provided by an embodiment of the present disclosure. As shown in FIG. 5H , the deep neural network analysis module can provide a large number of deep neural network models 561 for analyzing people in video stream , scenes, etc. for structured data analysis, such as face recognition, face clustering, image search, mask detection, expression analysis, age analysis, gender analysis, liveness detection, synthetic detection, traffic flow analysis, trajectory analysis, Queuing detection, direction of travel analysis, high-altitude parabolic detection, scene recognition, image review, environmental analysis, text recognition, license plate recognition, document recognition, bill recognition, voice recognition, etc.

3) Recording and playback module:

Based on the set linkage strategy, this module can link video recording equipment to record video data including abnormal events, and can support video playback of abnormal events. FIG. 5I is a schematic diagram of a video playback interface for an abnormal event provided by an embodiment of the present disclosure. As shown in FIG. 5I, the user can select a video segment 571 to be viewed on the video playback interface for playback, and can also enter the time 572, Information such as equipment 573 and abnormal event 574 is used to screen video clips, and video clips are selected from the screened video clips for playback.

In the embodiments of the present disclosure, the intelligent linkage strategy of multiple devices can be used to combine and configure different devices, and the linkage between multiple devices can be realized based on different abnormal events under a set linkage period. In addition, the multi-device intelligent linkage strategy can be used to analyze the characteristics of personnel, abnormal behaviors, scene categories, etc. in the video stream, and the multi-device intelligent linkage strategy can be used to complete device alarms and accurate recording, which is convenient for real-time attention to abnormal events Video records of the occurrence of events and accurate search for events afterwards.

Compared with the device linkage method in the related art, the device linkage method provided by the embodiment of the present disclosure includes at least the following improvements: 1) In the related art, the linkage task is only completed between devices of the same type. In the embodiment of the present disclosure, it can Comprehensive management and control of various types of equipment to achieve collaborative perception between various types of equipment; 2) In related technologies, the event alarm that is usually linked to a single master-slave equipment is completed. In the embodiment of the present disclosure, abnormal equipment operation information can be Events and abnormal events of video analysis are detected to trigger event linkage of flexible combination of multiple devices; 3) Devices in related technologies trigger linkage alarms based on a single event. Events are analyzed in parallel, so that linkage alarms can be completed based on multiple running deep neural network models among the same group of devices at the same time.

In the embodiment of the present disclosure, the intelligent linkage strategy of multiple devices is used to enable different devices and views to be managed through a unified platform, and it is no longer necessary to manage different devices through multiple platforms (such as the monitoring platform to manage cameras, the traffic center to manage traffic devices, etc.), Effectively improved the problem of interoperability between cross-platforms. In addition, in the embodiments of the present disclosure, deep learning is used to make the detection of various abnormal events and the triggering of corresponding linkage tasks more accurate, so that the information of abnormal events can be better comprehensively analyzed, and the information of abnormal events can be searched and reviewed more accurately. Video data related to abnormal events.

Fig. 6 is a schematic structural diagram of a device linkage device provided by an embodiment of the present disclosure. As shown in Fig. 6, the device linkage device 600 includes: a first acquisition part 610, a detection part 620, a trigger part 630 and a storage part 640, wherein :

The first acquisition part 610 is configured to acquire the trigger data transmitted by the trigger device, and the linkage strategy set for the trigger device; the linkage strategy includes at least a preset abnormal event and a linkage device associated with the trigger device ;

The detection part 620 is configured to detect the trigger data based on the abnormal event preset in the linkage strategy, and obtain a detection result;

The triggering part 630 is configured to trigger the linkage device to acquire image data including the abnormal event in response to the detection result being the detection of the abnormal event;

The saving part 640 is configured to save the image data including the abnormal event.

In some embodiments, when the trigger data is at least one of online video streams, captured images, and device operation information, the linkage device is an image acquisition device; the trigger part is further configured to: The image acquisition device sends a recording instruction; and the image data including the abnormal event sent by the image acquisition device in response to the recording instruction is received.

In some embodiments, when the trigger data is a recorded video stream, the linkage device is the platform server; the trigger part is further configured to: intercept the recorded video stream Image data including the abnormal event is included.

In some embodiments, the linkage strategy further includes a linkage period, and the apparatus further includes: a setting part configured to set the working time of the trigger device as the linkage period.

In some embodiments, the linkage strategy further includes a linkage period, and the detection part is further configured to: in response to the occurrence of the trigger data within the linkage period, based on the abnormality preset in the linkage strategy An event is used to detect the trigger data.

In some embodiments, the linkage strategy further includes a linkage period, and the detection part is further configured to: discard the trigger data in response to an occurrence time of the trigger data not within the linkage period.

In some embodiments, the linkage device further includes a warning device, and the apparatus further includes: a warning part configured to: trigger the warning device to output warning information in response to the detection result being that the abnormal event is detected ; or, discarding the trigger data in response to the detection result being that the abnormal event is not detected.

In some embodiments, the apparatus further includes: a presentation part configured to present the first configuration interface in response to the configuration operation on the linkage strategy; the first configuration interface is used to set the trigger device , associating a linkage device with the trigger device and setting an abnormal event to be detected for the trigger device; the second acquisition part is configured based on the settings for the trigger device and the linkage device in the first configuration interface The operation is to obtain a linkage strategy for the triggering device; wherein, the quantity relationship between the triggering device and the linkage device includes one of the following: one-to-one, one-to-many, many-to-one, and many-to-many.

In some embodiments, when the trigger data is image data, the abnormal event includes at least one of the following: the object information contained in the image data does not match the preset object information; the first object contained in the image data The information does not match the object represented by the second object information; the object information contained in the image data is associated with preset abnormal attributes.

In some embodiments, when the trigger data is device operation information, the abnormal event includes at least one of the following: device hardware failure; device power supply abnormality; device network abnormality; device environment abnormality.

In some embodiments, when the trigger data is a video stream, the abnormal event includes a preset abnormal scene; the detection part is further configured to: based on the preset abnormal scene in the linkage strategy, use The scene model matched with the abnormal scene detects the video stream, and obtains a detection result representing whether the abnormal scene is detected.

In some embodiments, the apparatus further includes: an output section configured to output image data including the abnormal event in response to a playback operation on the abnormal event.

The description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device embodiments of the present disclosure, please refer to the description of the method embodiments of the present disclosure for understanding.

In the embodiments of the present disclosure and other embodiments, a "part" may be a part of a circuit, a part of a processor, a part of a program or software, etc., of course it may also be a unit, a module or a non-modular one.

It should be noted that, in the embodiment of the present disclosure, if the above device linkage method is implemented in the form of software function modules and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of the embodiments of the present disclosure or the part that contributes to the related technology can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to make a A computer device (which may be a personal computer, a server, or a network device, etc.) executes all or part of the methods described in various embodiments of the present disclosure. The aforementioned storage medium includes: various media that can store program codes such as U disk, mobile hard disk, read-only memory (Read Only Memory, ROM), magnetic disk or optical disk. As such, embodiments of the present disclosure are not limited to any specific combination of hardware and software.

An embodiment of the present disclosure provides a computer device, including a memory and a processor, the memory stores a computer program that can run on the processor, and the processor implements the steps in the above method when executing the program.

An embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above method are implemented. The computer readable storage medium may be transitory or non-transitory.

An embodiment of the present disclosure provides a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program. When the computer program is read and executed by a computer, a part or part of the above method is implemented. All steps. The computer program product can be specifically realized by means of hardware, software or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK) etc. Wait.

It should be pointed out here that: the above descriptions of the storage medium, computer program, computer program product, and device embodiments are similar to the descriptions of the above method embodiments, and have similar beneficial effects to those of the method embodiments. For technical details not disclosed in the storage medium, computer program product, and device embodiments of the present disclosure, please refer to the description of the method embodiments of the present disclosure for understanding.

It should be noted that FIG. 7 is a schematic diagram of a hardware entity of a computer device in an embodiment of the present disclosure. As shown in FIG. 7 , the hardware entity of the computer device 700 includes: a processor 701, a communication interface 702, and a memory 703, wherein:

Processor 701 generally controls the overall operation of computer device 700 .

The communication interface 702 enables the computer device to communicate with other terminals or servers through the network.

The memory 703 is configured to store instructions and applications executable by the processor 701, and can also cache data to be processed or processed by the processor 701 and various modules in the computer device 700 (for example, image data, audio data, voice communication data and Video communication data) can be realized by flash memory (FLASH) or random access memory (Random Access Memory, RAM). Data transmission may be performed between the processor 701 , the communication interface 702 and the memory 703 through the bus 704 .

It should be understood that reference throughout the specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic related to the embodiment is included in at least one embodiment of the present disclosure. Thus, appearances of "in one embodiment" or "in an embodiment" in various places throughout the specification are not necessarily referring to the same embodiment. Furthermore, the particular features, structures or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that in various embodiments of the present disclosure, the sequence numbers of the above-mentioned processes do not mean the order of execution, and the execution order of the processes should be determined by their functions and internal logic, rather than by the embodiments of the present disclosure. The implementation process constitutes any limitation. The serial numbers of the above-mentioned embodiments of the present disclosure are for description only, and do not represent the advantages and disadvantages of the embodiments.

It should be noted that, in this document, the term "comprising", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising that element.

In the several embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods may be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or May be integrated into another system, or some features may be ignored, or not implemented. In addition, the coupling, or direct coupling, or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be electrical, mechanical or other forms of.

The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed to multiple network units; Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may be used as a single unit, or two or more units may be integrated into one unit; the above-mentioned integration The unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

Those of ordinary skill in the art can understand that all or part of the steps to realize the above method embodiments can be completed by hardware related to program instructions, and the aforementioned programs can be stored in computer-readable storage media. When the program is executed, the execution includes The steps of the foregoing method embodiments; and the foregoing storage media include: removable storage devices, read-only memory (Read Only Memory, ROM), magnetic disks or optical disks and other media that can store program codes.

Alternatively, if the above-mentioned integrated units of the present disclosure are realized in the form of software function modules and sold or used as independent products, they may also be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of the present disclosure or the part that contributes to related technologies can be embodied in the form of software products, the computer software products are stored in a storage medium, and include several instructions to make a A computer device (which may be a personal computer, a server, or a network device, etc.) executes all or part of the methods described in various embodiments of the present disclosure. The aforementioned storage medium includes various media capable of storing program codes such as removable storage devices, ROMs, magnetic disks or optical disks.

The above is only the embodiment of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Anyone skilled in the art can easily think of changes or substitutions within the technical scope of the present disclosure, and should within the protection scope of the present disclosure.

Industrial Applicability

Embodiments of the present disclosure provide a device linkage method, device, device, storage medium, program product, and computer program, wherein the method includes: acquiring trigger data transmitted by a trigger device, and setting a linkage for the trigger device strategy; the linkage strategy includes at least a preset abnormal event and a linkage device associated with the trigger device; based on the preset abnormal event in the linkage strategy, the trigger data is detected to obtain a detection result; in response to The detection result is that the abnormal event is detected, triggering the linkage device to acquire image data including the abnormal event; and saving the image data including the abnormal event. In the embodiment of the present disclosure, the flexibility of device linkage can be improved by flexibly configuring the abnormal event and the linkage device associated with the triggering device in the linkage strategy, and the image data including the abnormal event can be accurately acquired and saved, which facilitates the abnormal event playback and analysis.

Claims

A device linkage method applied to a platform server, the method comprising:

Acquiring the trigger data transmitted by the trigger device, and the linkage strategy set for the trigger device; the linkage strategy includes at least a preset abnormal event and a linkage device associated with the trigger device;

Detecting the trigger data based on the preset abnormal events in the linkage strategy to obtain a detection result;

In response to the detection result being the detection of the abnormal event, triggering the linkage device to acquire image data including the abnormal event;

The image data including the abnormal event is saved.
The method according to claim 1, wherein the linkage device in the linkage strategy includes at least one of the following: an image acquisition device, and a platform server.
The method according to claim 2, wherein, when the trigger data is at least one of online video streams, snapshot images, and device operation information, the linkage device is an image acquisition device;

The triggering the linkage device to acquire the image data including the abnormal event includes:

sending a recording instruction to the image acquisition device;

receiving the image data including the abnormal event sent by the image acquisition device in response to the recording instruction.
The method according to claim 2 or 3, wherein, when the trigger data is a recorded video stream, the linkage device is the platform server;

The triggering the linkage device to acquire the image data including the abnormal event includes:

Image data including the abnormal event is intercepted from the recorded video stream.
The method according to any one of claims 1 to 4, wherein the linkage strategy further includes a linkage period, and the method further includes one of the following:

Setting the working time of the trigger device as the linkage cycle;

In response to the occurrence time of the trigger data being within the linkage period, the trigger data is detected based on an abnormal event preset in the linkage strategy.
The method according to claim 5, further comprising: discarding the trigger data in response to the occurrence time of the trigger data not within the linkage period.
The method according to any one of claims 2 to 6, wherein the linkage device further includes an alarm device, and the method further includes one of the following:

triggering the alarm device to output alarm information in response to the detection result being the detection of the abnormal event;

In response to the detection result being that the abnormal event is not detected, the trigger data is discarded.
The method according to any one of claims 1 to 7, further comprising:

In response to the configuration operation of the linkage policy, the first configuration interface is presented; the first configuration interface is used to set the trigger device, associate the trigger device with a linkage device and set the trigger device to be detected abnormal events;

Acquiring a linkage strategy for the trigger device based on the setting operation for the trigger device and the linkage device in the first configuration interface;

Wherein, the quantitative relationship between the triggering device and the linkage device includes one of the following: one-to-one, one-to-many, many-to-one, and many-to-many.
The method according to any one of claims 1 to 8, wherein, when the trigger data is image data, the abnormal event includes at least one of the following:

The object information contained in the image data does not match the preset object information;

The first information contained in the image data does not match the second information;

The object information contained in the image data is associated with preset abnormal attributes;

In the case where the trigger data is equipment operation information, the abnormal event includes at least one of the following:

equipment hardware failure;

The power supply of the equipment is abnormal;

The device network is abnormal;

The environment of the device is abnormal.
The method according to any one of claims 1 to 9, wherein, when the trigger data is a video stream, the abnormal event includes a preset abnormal scene;

The detection of the trigger data based on the preset abnormal events in the linkage strategy to obtain a detection result includes:

Based on the abnormal scene preset in the linkage strategy, the video stream is detected by using a scene model matching the abnormal scene, and a detection result indicating whether the abnormal scene is detected is obtained.
The method according to any one of claims 1 to 10, further comprising:

Image data including the abnormal event is output in response to a playback operation of the abnormal event.
A device linkage device, comprising:

The first acquisition part is configured to acquire the trigger data transmitted by the trigger device, and the linkage strategy set for the trigger device; the linkage strategy includes at least a preset abnormal event and a linkage device associated with the trigger device;

The detection part is configured to detect the trigger data based on the abnormal event preset in the linkage strategy, and obtain a detection result;

A triggering part configured to trigger the linkage device to acquire image data including the abnormal event in response to the detection result being the detection of the abnormal event;

A saving section configured to save the image data including the abnormal event.
The apparatus according to claim 12, wherein the linkage device in the linkage strategy includes at least one of the following: an image acquisition device, and a platform server.
The device according to claim 13, wherein, when the trigger data is at least one of online video streams, snapped images, and device operation information, the linkage device is an image acquisition device; the trigger part is further It is configured to: send a recording instruction to the image acquisition device; receive image data including the abnormal event sent by the image acquisition device in response to the recording instruction.
The device according to claim 13 or 14, wherein, when the trigger data is a recorded video stream, the linkage device is the platform server; the trigger part is further configured to: from the Image data including the abnormal event is intercepted from the recorded video stream.
The device according to any one of claims 12 to 15, wherein the linkage strategy further includes a linkage period, and the detection part is further configured to: respond to the trigger data occurring within the linkage period , detecting the trigger data based on an abnormal event preset in the linkage strategy; or, the device further includes: a setting part configured to set the working time of the trigger device as the linkage period.
The device according to claim 16, wherein the detection part is further configured to: discard the trigger data in response to the occurrence time of the trigger data not within the linkage period.
The device according to any one of claims 13 to 17, wherein the linkage device further comprises an alarm device, and the device further comprises: an alarm part configured to: detect the An abnormal event, triggering the alarm device to output alarm information; or, in response to the detection result that the abnormal event is not detected, discarding the trigger data.
The device according to any one of claims 12 to 18, wherein the device further comprises: a presentation part configured to present the first configuration interface in response to a configuration operation on the linkage strategy; the The first configuration interface is used to set the trigger device, associate the trigger device with a linkage device and set the abnormal event to be detected for the trigger device; the second acquisition part is configured based on the first configuration interface The setting operation of the trigger device and the linkage device obtains a linkage strategy for the trigger device; wherein, the quantitative relationship between the trigger device and the linkage device includes one of the following: one-to-one, one-to-many, Many-to-one, many-to-many.
The device according to any one of claims 12 to 19, wherein, when the trigger data is image data, the abnormal event includes at least one of the following: object information contained in image data and preset object information The information does not match; the first object information contained in the image data does not match the object represented by the second object information; the object information contained in the image data is associated with preset abnormal attributes;

When the trigger data is device operation information, the abnormal event includes at least one of the following: device hardware failure; device power supply abnormality; device network abnormality; device environment abnormality.
The device according to any one of claims 12 to 20, wherein when the trigger data is a video stream, the abnormal event includes a preset abnormal scene; the detection part is further configured to: based on the The abnormal scene preset in the linkage strategy is used, and the scene model matching the abnormal scene is used to detect the video stream, and a detection result representing whether the abnormal scene is detected is obtained.
The apparatus according to any one of claims 12 to 21, wherein the apparatus further comprises an output section configured to output image data including the abnormal event in response to a playback operation of the abnormal event.
A computer device, comprising a memory and a processor, the memory stores a computer program that can run on the processor, and the processor implements the method described in any one of claims 1 to 11 when executing the computer program step.
A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the method of any one of claims 1 to 11 are realized.
A computer program product, the computer program product comprising a non-transitory computer-readable storage medium storing a computer program, when the computer program is read and executed by a computer, it realizes any one of claims 1 to 11 steps in the method.
A computer program, comprising computer readable code, when the computer readable code is run in a computer device, a processor in the computer device implements the method in any one of claims 1 to 11 step.