CN114296073A - Abnormity warning method and system based on millimeter wave radar and electronic device - Google Patents

Abstract

The present application relates to an abnormality warning method, system, electronic device and storage medium based on a millimeter-wave radar. The method includes: acquiring observation events detected by a millimeter-wave radar in a preset monitoring scene; The reported events reported locally by any target of From a variety of warning devices, select the warning device that matches the danger level for warning processing. Through the present application, the problem of low accuracy of alarming abnormal events in the related art is solved, and the technical effect of improving the accuracy of alarming abnormal events is achieved.

Description

Anomaly warning method, system and electronic device based on millimeter wave radar

technical field

The present application relates to the technical field of target detection, and in particular, to an abnormality warning method, system, electronic device and storage medium based on millimeter wave radar.

Background technique

With the continuous development and application of smart cities, smart homes and smart buildings, it is very important to ensure the safety of users. Due to various reasons, the elderly or patients are prone to accidents such as falls and sudden illnesses, and lose the ability to seek help after the accident. When such an abnormal situation occurs, if it is not detected and treated in time, it will lead to serious consequences.

Nursing institutions (nursing homes, hospitals, etc.) conduct regular ward rounds through nurses, nurses, etc. to check for abnormal conditions. However, the number and energy of nursing staff are limited after all. Accurately and efficiently providing assistance to the elderly or patients is a difficult problem that nursing institutions need to face. On the other hand, the problem of home-based care is even more difficult. It is impossible to conduct regular rounds of wards by full-time staff, and can only rely on relatives and friends to take care of them. In recent years, the elderly living alone have suffered a fall or sudden cardiovascular disease and no one is rescued. Happened, and even passed away for a long time still undiscovered. Therefore, how to accurately and efficiently realize the abnormal warning of indoor targets is a major problem that needs to be solved urgently.

At present, there are many methods in the related art that can be used to warn indoor targets of abnormality. For example, users can carry a one-button warning device, manually pull the wire or press the warning button when an accident occurs, and trigger the sound and light signal of the warning device to warn ; Or by setting up a radar warning integrated machine, when an abnormal event occurs in the radar monitoring area, the sound and light signal is triggered for warning and so on. However, in this type of technical solution, the one-button warning device requires the user to have certain behavioral capabilities, and cannot serve as a warning to users who have fallen or become incapacitated due to other circumstances. The next problem is that the false alarm rate is high and the false alarm rate is high.

At present, no effective solution has been proposed for the problem of low accuracy of alerting abnormal events in the related art.

SUMMARY OF THE INVENTION

Embodiments of the present application provide an abnormality warning method, system, electronic device, and storage medium based on a millimeter-wave radar, so as to at least solve the problem of low accuracy of warning of abnormal events in the related art.

In a first aspect, an embodiment of the present application provides an abnormality warning method based on a millimeter-wave radar. The method includes: acquiring observation events detected by a millimeter-wave radar in a preset monitoring scene; The reporting event reported locally by any target of the For the danger level of the monitoring scene, an alerting device matching the danger level is selected from a variety of preset alerting devices to perform alerting processing.

In some of the embodiments, determining the risk level of the monitoring scenario according to the feature information of the observed event and the reported event, and the correlation between the observed event and the reported event includes: according to the Observing the feature information of the event to determine whether there is abnormal behavior in the monitoring scene, wherein the abnormal behavior includes the target falling behavior and the abnormal breathing behavior of the target; in the case of abnormal behavior in the monitoring scene, according to the observation The characteristic information of the event is used to determine the risk level of the monitoring scene; when the number of the reported events is greater than zero, the risk level of the monitoring scene is determined according to the characteristic information of the reported event; in the monitoring scene In the case where there is abnormal behavior and the number of the reported events is greater than zero, determine the Monitor the danger level of the scene.

In some of the embodiments, determining the risk level of the monitoring scene according to the characteristic information of the observation event includes: determining the number of normal targets other than abnormal targets in the monitoring scene according to the characteristic information of the observation event , wherein the abnormal target corresponds to the abnormal behavior; according to the characteristic information of the observation event, it is determined whether the abnormal behavior disappears; according to the number of the normal targets in the monitoring scene, and the abnormal behavior The existence status of the monitoring scene is determined, and the danger level of the monitoring scene is determined.

In some of the embodiments, determining the risk level of the monitoring scenario according to the feature information of the reported event includes: determining, according to the feature information of the reported event, the risk of the reported event within a preset first time period Occurrence frequency; according to the occurrence frequency of the reported event within the first time period, determine the risk level of the monitoring scenario.

In some of the embodiments, determining the risk level of the monitoring scenario according to the feature information of the observed event and the reported event, and the correlation between the observed event and the reported event includes: according to the Observing the characteristic information of the event, and determining the number of normal targets other than the abnormal target in the monitoring scene, wherein the abnormal target corresponds to the abnormal behavior; according to the characteristic information of the observation event, determining whether the abnormal behavior is not according to the feature information of the reported event, determine the frequency of occurrence of the reported event within a preset first time period; according to the observed event and the feature information of the reported event, determine the abnormal behavior and all The occurrence time interval of the reported event in the preset second time period; in the case of whether the occurrence time interval between the abnormal behavior and the reported event in the second time period is less than the preset fifth threshold , determine that there is a correlation between the abnormal behavior and the reported event; according to the number of the normal targets in the monitoring scene, the existence state of the abnormal behavior, the reported event is in the first time period The occurrence frequency of the monitoring scene and the correlation between the abnormal behavior and the reported event are used to determine the risk level of the monitoring scene.

In some of these embodiments, the risk level includes a low risk level, a medium risk level and a high risk level; according to the number of the normal targets in the monitoring scene, the existence state of the abnormal behavior, the reporting event The frequency of occurrence in the first time period and the correlation between the abnormal behavior and the reported event, and determining the risk level of the monitoring scenario includes: according to the number of the normal targets in the monitoring scenario , the existence state of the abnormal behavior, the frequency of occurrence of the reported event within the first time period, and the correlation between the abnormal behavior and the reported event, to determine the risk score of the monitoring scenario; When the risk score of the monitoring scene is less than or equal to a preset first threshold, it is determined that the monitoring scene has a low risk level; or when the risk score of the monitoring scene is greater than the first threshold and less than or When it is equal to the preset second threshold, it is determined that the monitoring scene is at a medium risk level; or when the risk score of the monitoring scene is greater than the second threshold, it is determined that the monitoring scene is at a high risk level.

In some of these embodiments, according to the number of the normal targets in the monitoring scenario, the existence state of the abnormal behavior, the occurrence frequency of the reported event within the first time period, and the abnormal behavior and The correlation between the reported events, and determining the risk score of the monitoring scenario includes: when there is abnormal behavior in the monitoring scenario and/or the number of reported events is greater than zero, determining the risk of the monitoring scenario The risk score is a preset first score; when the number of the normal targets is greater than a preset third threshold, it is determined that the risk score is reduced by a preset second score; When the frequency of occurrence in the first time period is greater than a preset fourth threshold, it is determined that the risk score is increased by a preset third score; when there is a correlation between the abnormal behavior and the reported event, it is determined that the The risk score is a preset fourth score; when the abnormal behavior disappears, it is determined that the risk score is reduced by a preset fifth score.

In a second aspect, an embodiment of the present application provides an abnormality warning system based on a millimeter-wave radar. The system includes: an event observation device, a local reporting device, and a warning device; wherein the event observation device includes a millimeter-wave radar and a processing The processor is connected in communication with the millimeter-wave radar, the local reporting device and the warning device, and the millimeter-wave radar is used to detect observation events that occur in a preset monitoring scenario; the local The reporting device is used to collect reporting events manually reported locally by any target; the processor is configured to execute the millimeter-wave radar-based abnormal warning method as described in the first aspect above; the warning device includes a local warning device and a remote warning device and a designated warning device, the warning device is configured to be controlled by the processor to perform a corresponding warning action.

In a third aspect, an embodiment of the present application further provides an electronic device, including a memory and a processor, where a computer program is stored in the memory, and the processor is configured to run the computer program to execute the above-mentioned first aspect The described abnormality warning method based on millimeter wave radar.

In a fourth aspect, an embodiment of the present application further provides a storage medium, where a computer program is stored in the storage medium, wherein, when the computer program is executed by a processor, the millimeter-wave radar based on the above-mentioned first aspect is implemented exception warning method.

Compared with the related art, the abnormal warning method, system, electronic device and storage medium based on the millimeter-wave radar provided by the embodiments of the present application obtain the observation events detected by the millimeter-wave radar in the preset monitoring scene; The reporting event reported locally by any target collected by the local reporting device; according to the feature information of the observed event and the reported event, and the correlation between the observed event and the reported event, the risk level of the monitoring scene is determined; according to the risk level of the monitoring scene, Select the warning device that matches the danger level from the preset various warning devices to perform the warning processing. The problem of low accuracy of warning for abnormal events in the related art is solved, and the technical effect of improving the accuracy of warning of abnormal events is achieved.

The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below in order to make other features, objects and advantages of the application more apparent.

Description of drawings

The drawings described herein are used to provide further understanding of the present application and constitute a part of the present application. The schematic embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation of the present application. In the attached image:

1 is a structural block diagram of an abnormality warning system based on a millimeter wave radar according to an embodiment of the present application;

2 is a flowchart of an abnormality warning method based on a millimeter wave radar according to an embodiment of the present application;

FIG. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application. In addition, it will also be appreciated that while such development efforts may be complex and lengthy, for those of ordinary skill in the art to which the present disclosure pertains, the techniques disclosed in this application Some changes in design, manufacture or production based on the content are only conventional technical means, and it should not be understood that the content disclosed in this application is not sufficient.

Reference in this application to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor a separate or alternative embodiment that is mutually exclusive of other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

Unless otherwise defined, the technical or scientific terms involved in this application shall have the usual meanings understood by those with ordinary skill in the technical field to which this application belongs. Words such as "a", "an", "an", "the" and the like mentioned in this application do not denote a quantitative limitation, and may denote the singular or the plural. The terms "comprising", "comprising", "having" and any of their variants referred to in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product or process comprising a series of steps or modules (units) The apparatus is not limited to the steps or units listed, but may further include steps or units not listed, or may further include other steps or units inherent to the process, method, product or apparatus. Words like "connected," "connected," "coupled," and the like referred to in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "plurality" referred to in this application means greater than or equal to two. "And/or" describes the association relationship between associated objects, indicating that there can be three kinds of relationships. For example, "A and/or B" can mean that A exists alone, A and B exist at the same time, and B exists alone. The terms "first", "second", "third", etc. involved in this application are only to distinguish similar objects, and do not represent a specific order for the objects.

This embodiment provides an abnormality warning system based on a millimeter wave radar. FIG. 1 is a structural block diagram of an abnormality warning system based on a millimeter wave radar according to an embodiment of the present application. As shown in FIG. 1 , the system includes: an event observation device 10. The local reporting device 11 and the warning device 12; wherein, the event observation device 10 includes a millimeter-wave radar 101 and a processor 102, and the processor 102 is connected to the millimeter-wave radar 101, the local reporting device 11 and the warning device 12. The radar 101 is used to detect observation events that occur in a preset monitoring scenario; the local reporting device 11 is used to collect the reporting events manually reported locally by any target; the processor 102 is used to execute an abnormality warning based on the millimeter wave radar 101 The method; the warning device 12 includes a local warning device 121 , a remote warning device 122 and a designated warning device 123 , and the warning device 12 is controlled by the processor 102 to execute a corresponding warning action.

In this embodiment, the millimeter-wave radar 101 is used for real-time monitoring of various observation events in the monitoring scene, such as: target entry event, target departure event, target fall event, target posture height change event, target breathing abnormal event, Target bed-in events and target-out-of-bed events, etc.

In this embodiment, the local reporting device 11 can use a button-type reporting device and/or a pull-line reporting device. After any target finds an abnormal situation, it can choose to press the button or pull the cable. When the button-type reporting device or the cable-pulling reporting device After being triggered, a report event is generated, and the report event can be sent to the processor 102 through the local wireless network module in the form of a message.

In this embodiment, the local warning device 121 may include sound and light equipment and a ringing device, the processor 102 may send a control command to the local warning device 121 through the local wireless network module, and the local warning device 121 may be controlled by the control command to emit sound Optical signal or ringing warning; the remote warning device 122 may include application software installed on the mobile terminal, and the processor 102 may send first warning information to the remote warning device 122 through the public mobile network module, and the first warning information may include corresponding The corresponding alarm operation is completed by the corresponding application software; the designated alarm device 123 may include the communication equipment corresponding to the designated communication address, and the processor 102 may send a second alarm to the designated alarm device 123 through the public telephone network module information, the second warning information may be a warning recording including the corresponding abnormal event information, and when the corresponding communication device answers the call, the warning recording will be played.

In the above embodiment, the millimeter wave includes electromagnetic waves with a wavelength of millimeter level. The millimeter wave radar 101 may be a radar system with a wavelength of emitting electromagnetic waves greater than 0.1 mm and less than 0.2 mm and a frequency between 20 GHz and 300 GHz. The radar 101 mainly uses a transmission frequency band such as 24GHz, 60GHz or 77GHz.

In the above embodiment, the processor 102 may have built-in fall detection algorithms, breathing detection algorithms, target detection algorithms, etc., the event observation device 10 can effectively identify various human postures in a single target scene, and the millimeter-wave radar 101 has good detection capabilities. Accuracy and sensitivity can effectively eliminate the interference of daily actions and static environmental disturbances on event observation.

In this embodiment, the fall detection algorithm can effectively identify various types of fall postures in a single-target scenario, wherein the dependent parameters of the fall detection algorithm to determine the fall state of the target mainly include: dynamic number of people, that is, the fall detection algorithm can In the scene, fall behavior detection is performed; for height, when the height of the target from the ground is less than the height threshold preset by the algorithm, a fall judgment is triggered; the duration of falling to the ground, when the duration of the target falling to the ground is greater than the preset falling time threshold of the algorithm, Trigger fall judgment; recovery standing time, when the duration of the target's recovery after falling to the ground is less than the standing time threshold preset by the algorithm, maintain the fall judgment; confidence level, when the target is suspected of falling to the ground The confidence level is higher than the algorithm preset confidence When the temperature threshold is reached, a fall judgment is triggered.

In this embodiment, the target detection algorithm can detect the number of targets in the monitoring scene through the clustering algorithm, so as to provide auxiliary judgment for whether to trigger the warning operation after the abnormal event is sent. In the scene, the single target has a fall event), if the target detection algorithm detects more than one person in the monitoring scene in real time, the local warning and remote warning will not be triggered.

In this embodiment, the breathing detection algorithm can be implemented by relying on frequency-modulated continuous wave radar, which can automatically locate the target position and detect the breathing information of the target, wherein the breathing information includes breathing frequency, average breathing interval, average breathing time, etc. , and can warn abnormal conditions such as respiratory arrest and shortness of breath. The breath detection algorithm adopts the optimized Kalman filter algorithm to track and locate the target, filter and smooth the phase information of the target, and obtain the target's phase information. breathing information.

In the above embodiment, the fall detection algorithm, the breathing detection algorithm, and the target detection algorithm support the self-defined configuration of the algorithm parameters, and the user can adjust it according to the needs to meet the individual needs, for example, the falling time length in the above fall detection algorithm The default value of the threshold is 2 seconds, and its adjustable range is between 1 second and 10 seconds. The default value of the standing time threshold is 1 second, and its adjustable range is between 0.5 seconds and 5 seconds. The default value of the confidence threshold is 0.6. 0.4, 0.8 can also be selected as the confidence threshold.

In the above-mentioned embodiment, the processor 102 and the local warning device 121 can be communicated through the 433M communication protocol, the processor 102 sends a control command to the local warning device 121, and the local warning device 121 receives the control command; correspondingly, the processor 102 and the local reporting device 11 can also be connected in communication through the 433M communication protocol, the local reporting device 11 sends a reporting event to the processor 102, and the processor 102 receives the reporting event.

In this embodiment, the processor 102 needs to be paired with the local reporting device 11 first, and then paired with the local warning device 121 .

In some of these embodiments, after the local reporting device 11 reports a reporting event, the processor 102 may issue a control command to the local warning device 121 every 5 seconds, and the local warning device 121 can be controlled by the control command to vibrate. For bell warning, a maximum of 12 control commands can be issued, that is, a ring warning with a maximum duration of 60 seconds. The above-mentioned ringing duration and ringing tone can be modified and controlled by programming.

In the above-mentioned embodiment, the processor 102 sends the second warning information to the designated warning device 123 through the public telephone network module, which can be realized by the Internet of Things IVR (Interactive Voice Response, Interactive Voice Response, IVR for short) technology. Called API (Application Programming Interface, API for short), the operator network sends a voice call to the specified communication address. After the call is picked up, a specified audio is played. The user is guided by the audio and can communicate through communication if necessary. The button information of the device is replied, and the voice platform returns the button information to the application business system through the message receipt, and the application business system can take response measures through the response grading strategy. In this scenario, the initiating end of the voice call is jointly initiated by the observation event provided by the event observation device 10 and the abnormal classification processing rules preset in the system, which requires no manual intervention, is stable and reliable, and has high overall system consistency.

This embodiment provides an abnormality warning method based on a millimeter-wave radar. FIG. 2 is a flowchart of an abnormality warning method based on a millimeter-wave radar according to an embodiment of the present application. As shown in FIG. 2 , the method includes:

Step S201, acquiring observation events detected by the millimeter-wave radar in a preset monitoring scene.

In this embodiment, the millimeter-wave radar can measure and output the following parameters: radial distance, radial velocity, target RCS (Radar Cross Section, RCS for short), signal-to-noise ratio, etc. In addition, for multi-channel radar The system can also provide the bearing or pitch angle of the detection point. Based on the above measurement results, the use of spatial geometric relationship, human posture feature classification, machine learning and other technologies and algorithm solutions can realize the monitoring of emergency events such as personnel fall detection, abnormal activity, and abnormal breathing.

Step S202: Acquire the reporting event locally reported by any target collected by the preset local reporting device.

In this embodiment, the manual warning operation based on the local reporting device and the automatic warning operation based on the millimeter-wave radar are combined to form a unified abnormal warning system, with the automatic warning as the main body and the manual warning as the auxiliary and guarantee. With higher degree of automation, higher reliability, more convenient operation, and better detection accuracy, it can alert abnormal operations in monitoring scenarios.

In the above embodiment, the power of the local reporting device can be provided by the self-generating device. The self-generating device cooperates with the low-power LAN technology to ensure the LAN communication capability of the local reporting device indefinitely, which is more in line with the existence of emergency alerts. High reliability is required for business needs, to avoid abnormal missed reports caused by the exhaustion of the battery of the local reporting device.

Step S203 , according to the characteristic information of the observed event and the reported event, and the correlation between the observed event and the reported event, determine the risk level of the monitoring scenario.

In this embodiment, the local reporting device includes a button-type reporting device and/or a pull-line reporting device, and the reporting event includes a button-type reporting event and a cable-pulling reporting event.

In this embodiment, the processor may determine whether there is an abnormal behavior in the monitoring scene according to the feature information of the observed event according to the preset abnormal classification rules, and determine the abnormal behavior according to the occurrence time interval between the abnormal behavior and the reported event Whether there is a correlation between the behavior and the reported event, and based on the characteristic information of the observed event and the reported event, as well as the correlation between the abnormal behavior and the reported event, determine the risk level of the monitoring scene, which can not only improve the warning in the face of emergency situations It can also provide information about the danger level of the monitoring scene to the police who are not on the scene, so that the police can better deal with such abnormal events.

Step S204 , according to the danger level of the monitoring scene, select a warning device matching the danger level from a variety of preset warning devices to perform warning processing.

In this embodiment, the processor can also preset an exception classification treatment rule to ensure that the warning information can be correctly issued according to the abnormal classification treatment rule in an emergency state, and an automatic warning treatment strategy is given, and the automatic warning treatment strategy can include: : Alarm through local ringing, alarm through application software installed on mobile terminals, alarm through emergency event information push from community or medical institutions, elderly care service institutions, and health service units, and automatic voice call to designated emergency contacts Alert.

Through the above steps S201 to S204, the observation events detected by the millimeter-wave radar in the preset monitoring scene are obtained; the report events reported locally by any target collected by the preset local reporting device are obtained; according to the observation events and the reported events The feature information, as well as the correlation between the observation event and the reported event, determine the danger level of the monitoring scene; according to the danger level of the monitoring scene, select the warning device that matches the danger level from the preset multiple warning devices for warning processing. Through this application, the manual warning operation based on the local reporting device and the automatic warning operation based on the millimeter wave radar are combined to form a unified abnormal warning system, with the automatic warning as the main body and the manual warning as the auxiliary and guarantee to realize the degree of automation Higher, more reliable, more convenient operation, and better detection accuracy for abnormal warning operations in monitoring scenarios; and based on various information to determine the risk level of the monitoring scene, and determine the corresponding warning scheme based on the risk level of the monitoring scene , to ensure that the warning processing can be carried out according to the corresponding warning scheme in various situations, solve the problem of low accuracy of warning on abnormal events in related technologies, and achieve the technical effect of improving the accuracy of warning on abnormal events.

In some of these embodiments, according to the feature information of the observed event and the reported event, and the correlation between the observed event and the reported event, determining the risk level of the monitoring scenario is implemented by the following steps:

Step 1, according to the characteristic information of the observed event, determine whether there is abnormal behavior in the monitoring scene, wherein the abnormal behavior includes the target falling behavior and the abnormal breathing behavior of the target.

Step 2: In the case of abnormal behaviors in the monitoring scene, the risk level of the monitoring scene is determined according to the characteristic information of the observed event.

Step 3, when the number of reported events is greater than zero, determine the risk level of the monitoring scenario according to the feature information of the reported events.

Step 4: When there is abnormal behavior in the monitoring scene and the number of reported events is greater than zero, determine the risk level of the monitoring scene according to the characteristic information of the observed events and the reported events, and the correlation between the observed events and the reported events.

In this embodiment, a fall detection algorithm, a breathing detection algorithm, a target detection algorithm, etc. may be built in the processor. Perform feature analysis on the observed events of abnormal events, target bed resting events and target bed exit events, and use the built-in fall detection algorithm, breathing detection algorithm, target detection algorithm, etc. in the processor to determine whether the target falls and abnormal breathing of the target occurs in the monitoring scene Behavior.

In this embodiment, only the millimeter-wave radar detects abnormal behavior in the monitoring scene, only the local reporting device collects one or more reporting events, the millimeter-wave radar detects abnormal behavior in the monitoring scene, and the local reporting device collects more than one event. In three cases equal to one reported event, the risk level of the monitoring scenario can be determined according to the preset exception classification rules.

For example, when the millimeter-wave radar detects abnormal behaviors in the monitoring scene but the local reporting device does not send the reported event, the risk level of the monitoring scene can be determined according to the feature information of the observed event, including the following steps:

Step 1: Determine the number of normal targets other than abnormal targets in the monitoring scene according to the characteristic information of the observed events, wherein the abnormal targets correspond to abnormal behaviors.

Step 2: Determine whether the abnormal behavior disappears according to the characteristic information of the observed event.

Step 3: Determine the danger level of the monitoring scene according to the number of normal targets in the monitoring scene and the existence state of abnormal behavior.

When the millimeter-wave radar does not detect abnormal behavior in the monitoring scene but the number of reported events sent by the local reporting device is greater than zero, the risk level of the monitoring scene can be determined according to the feature information of the reported events, including the following steps:

Step 1: Determine the occurrence frequency of the reported event within a preset first time period according to the characteristic information of the reported event.

Step 2: Determine the danger level of the monitoring scenario according to the frequency of occurrence of the reported event within the first time period.

Similarly, when the millimeter-wave radar detects abnormal behavior in the monitoring scene but the number of reported events sent by the local reporting device is greater than zero, it is necessary to combine the feature information of the observed event and the reported event to determine the abnormality in the observed event. Whether there is a correlation between the behavior and the reported event, and determine the risk level of the monitoring scenario based on the correlation between the abnormal behavior and the reported event, which includes the following steps:

Step 1: Determine the number of normal targets other than abnormal targets in the monitoring scene according to the characteristic information of the observed events, wherein the abnormal targets correspond to abnormal behaviors.

Step 2: Determine whether the abnormal behavior disappears according to the characteristic information of the observed event.

Step 3: Determine the occurrence frequency of the reported event within a preset first time period according to the characteristic information of the reported event.

Step 4, according to the characteristic information of the observed event and the reported event, determine the occurrence time interval of the abnormal behavior and the reported event within the preset second time period.

Step 5, in the case that the occurrence time interval between the abnormal behavior and the reported event in the second time period is less than the preset fifth threshold, determine that there is a correlation between the abnormal behavior and the reported event.

Step 6: Determine the risk level of the monitoring scene according to the number of normal targets in the monitoring scene, the existence status of abnormal behaviors, the frequency of reported events within the first time period, and the correlation between abnormal behaviors and reported events.

In this embodiment, when the time interval between the occurrence of the abnormal behavior and the reported event within the second time period is less than the preset fifth threshold, for example, the abnormal behavior and the reported event both occur at least once within 3 minutes, then it is determined that the The abnormal behavior is associated with the reported event, and the monitoring scenario is a high risk level. The second time period and the fifth threshold can be configured according to the actual needs of the user to meet the actual needs of different application scenarios.

In the above embodiment, by combining the manual warning operation based on the local reporting device and the automatic warning operation based on the millimeter wave radar, a unified abnormal warning system is formed, with the automatic warning as the main body and the manual warning as the auxiliary and guarantee, Realize higher automation, higher reliability, more convenient operation, and better detection accuracy for abnormal warning operations in monitoring scenarios.

In this embodiment, the risk level includes low risk level, medium risk level and high risk level; according to the number of normal targets in the monitoring scene, the existence state of abnormal behavior, the occurrence frequency of the reported event in the first time period and the abnormality The correlation between behaviors and reported events to determine the risk level of a monitoring scenario includes: according to the number of normal targets in the monitoring scenario, the existence of abnormal behaviors, the frequency of reported events in the first time period, and abnormal behavior and reporting The correlation between events is used to determine the risk score of the monitoring scene; when the risk score of the monitoring scene is less than or equal to the preset first threshold, the monitoring scene is determined to be of low risk level; or when the risk score of the monitoring scene is greater than or equal to the preset first threshold When the first threshold is less than or equal to the preset second threshold, the monitoring scene is determined to be at a medium risk level; or when the risk score of the monitoring scene is greater than the second threshold, it is determined that the monitoring scene is at a high risk level.

In this embodiment, the lower limit of the risk score can be set to 0 points, and the upper limit can be set to 100 points, wherein the first threshold value can be set to 50 points, and the second threshold value can be set to 70 points, that is, when the risk degree of the monitoring scene is When the score is between 0 and 50 points, the monitoring scene is determined to be of low risk level; when the risk score of the monitoring scene is between 51 and 70 points, the monitoring scene is determined to be of medium risk level; when the risk score of the monitoring scene is When the score is between 71 and 100, the monitoring scene is determined to be of high risk level.

In this embodiment, the danger of the monitoring scene is determined according to the number of normal targets in the monitoring scene, the existence state of abnormal behaviors, the frequency of reported events within the first time period, and the correlation between abnormal behaviors and reported events Degree scoring is achieved through the following steps:

Step 1, when there is abnormal behavior in the monitoring scene and/or the number of reported events is greater than zero, determine the risk score of the monitoring scene as a preset first score.

Step 2, when the number of normal targets is greater than a preset third threshold, determine that the risk score is reduced by a preset second score.

Step 3: When the occurrence frequency of the reported event in the first time period is greater than the preset fourth threshold, determine that the risk score is increased by the preset third score.

Step 4, when there is a correlation between the abnormal behavior and the reported event, determine the risk score as a preset fourth score.

Step 5, when the abnormal behavior disappears, determine that the risk score is reduced by a preset fifth value.

In this embodiment, when the millimeter-wave radar detects that abnormal behaviors (such as target falling behavior and abnormal breathing behavior of the target, etc.) occur in the monitoring scene, the risk score of the monitoring scene can be determined to be a preset first score. The first score is 60 points. Similarly, when the local reporting device is triggered once (for example, the button-type reporting device is pressed once or the wire-pulling reporting device is pulled once), the risk score of the monitoring scene can be determined to be 60. point.

In the above embodiment, a target detection algorithm is preset in the processor. Therefore, the number of normal targets other than abnormal targets in the monitoring scene can be detected by millimeter-wave radar. If abnormal behavior and/or reporting events occur, monitoring In addition to abnormal targets (fall targets or abnormal breathing targets) in the scene, there are other normal targets, that is, when the number of normal targets is greater than or equal to 1, the risk score is reduced by a preset second value, the second value Can be 20 points.

In the above embodiment, taking the local reporting device as an example of a button-type reporting device, if the occurrence frequency of the reporting event in the first time period is greater than the preset fourth threshold, that is, the second occurrence after pressing the button once or more key operations, it is determined that the risk score is increased by a preset third point value, and each key operation in the first time period can increase the risk score by 10 points, and the first time period can be 3 minutes. .

In the above embodiment, when the time interval between the occurrence of the abnormal behavior and the reported event in the second time period is less than the preset fifth threshold, for example, the abnormal behavior and the reported event occur at least once within 3 minutes, it is determined that the abnormal behavior and the reported event occur at least once. The abnormal behavior is associated with the reported event, and at the same time, the monitoring scenario is determined to be at a high risk level, and the risk score of the monitoring scenario is determined to be a preset fourth score, and the fourth score may be 100 points.

In the above-mentioned embodiment, a fall detection algorithm and a breathing detection algorithm are also preset in the processor. When the millimeter wave radar detects that the abnormal target has recovered from a fall state to a standing state (for example, when it rises to a default value of 1.4 meters or more) and reaches When it is detected for a certain period of time, or when it is detected that the breathing condition of the abnormal target has recovered from abnormal to normal for a certain period of time, it can be determined that the abnormal behavior has disappeared; or the reported event of the local reporting device has been manually reset, it is determined that the reported event has disappeared, and the abnormal behavior has disappeared. And/or when the reported event disappears, it may be determined that the risk score is reduced by a preset fifth point value, where the fifth point value is 50 points.

In the above embodiment, the first score, the second score, the third score, the fourth score, the fifth score, and the corresponding relationship between the risk score and the risk level can be customized according to user needs, Meet the individual needs of users.

In some of the embodiments, the warning device includes a local warning device, a remote warning device and a designated warning device; according to the danger level of the monitoring scene, a warning device matching the danger level is selected from a variety of preset warning devices to perform the warning processing as follows: Steps to achieve:

Step 1, when the monitoring scene is at a low risk level, a local warning device is used for local warning or no warning is triggered.

In step 2, when the monitoring scene is at a medium-risk level, a local warning device is used to perform a local warning, and a remote warning device is used to send first warning information to a preset mobile terminal.

Step 3, when the monitoring scene is of high risk level, use the local warning device to perform local warning, use the remote warning device to send the first warning information to the preset mobile terminal, and use the designated warning device to send the second warning to the preset communication address. Warning message.

In this embodiment, the method further includes: when the danger level of the monitoring scene rises from the first danger level to the second danger level, on the basis that the warning device matching the first danger level has been selected to perform the warning processing, superimposing the selection The warning device that matches the second danger level performs warning processing, and determines that the first warning information and/or the second warning information includes information on the increase of the danger level of the monitoring scene, for example, when the danger level of the monitoring scene rises from the medium danger level to the high danger level When the local warning device is used for local warning and the remote warning device is used to send the first warning information to the preset mobile terminal, the designated warning device should also be used to send the second warning information to the preset communication address, and at the same time , the first warning information and/or the second warning information includes information on the increase of the danger level of the monitoring scene.

In this embodiment, sub-rules can be set for the local warning device, the remote warning device, and the designated warning device. For example, when the monitoring scene is at a low risk level, the local warning device is used for local warning or no warning is triggered; when monitoring When the scene is at a medium risk level, the local warning device is used for local warning, and the remote warning device is used to send the first warning information to the preset mobile terminal; when the monitoring scene is at a high risk level, the local warning device is used for local warning, and the The remote warning device sends the first warning information to the preset mobile terminal, and uses the designated warning device to send the second warning information to the preset communication address.

In other embodiments, when the monitoring scene is at a medium risk level, a designated warning device may also be used to send the second warning information to a preset communication address. When it is at the medium risk level, the message subject of the first warning message and the second warning message is a medium risk warning; when the monitoring scene is at a high risk level, the message subject of the first warning message and the second warning message is a high risk warning. In the face of an emergency, it can not only improve the accuracy of the warning, but also provide the alarm personnel who are not on the scene with the risk level information of the monitoring scene, so that the alarm personnel can better deal with such abnormal events.

This embodiment also provides an electronic device. FIG. 3 is a schematic diagram of the hardware structure of the electronic device according to the embodiment of the present application. As shown in FIG. 3 , the electronic device includes a memory 304 and a processor 302 , and the memory 304 stores a memory 304 . A computer program, the processor 302 is configured to run the computer program to perform the steps in any one of the above method embodiments.

Specifically, the above-mentioned processor 302 may include a central processing unit (CPU), or a specific integrated circuit (Application Specific Integrated Circuit, ASIC for short), or may be configured as one or more integrated circuits implementing the embodiments of the present application.

Among others, memory 304 may include mass storage for data or instructions. By way of example and not limitation, the memory 304 may include a Hard Disk Drive (HDD), a floppy disk drive, a Solid State Drive (SSD), flash memory, optical disk, magneto-optical disk, magnetic tape, or universal serial A bus (UniversalSerial Bus, referred to as USB) drive or a combination of two or more of these. Memory 304 may include removable or non-removable (or fixed) media, where appropriate. Where appropriate, memory 304 may be internal or external to the millimeter wave radar based anomaly warning system. In certain embodiments, the memory 304 is a non-volatile (Non-Volatile) memory. In a specific embodiment, the memory 304 includes a read-only memory (Read-Only Memory, referred to as ROM for short) and a random access memory (Random Access Memory, referred to as RAM for short). In a suitable case, the ROM can be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, referred to as PROM), an erasable PROM (Erasable Programmable Read-Only Memory, referred to as EPROM), an electrically programmable ROM Erasing PROM (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), Electrically Rewritable ROM (Electrically Alterable Read-Only Memory, referred to as EAROM) or flash memory (FLASH) or a combination of two or more of these. In an appropriate case, the RAM may be Static Random-Access Memory (SRAM for short) or Dynamic Random Access Memory (DRAM for short), wherein the DRAM may be a fast page mode dynamic memory Random Access Memory (Fast Page ModeDynamic Random Access Memory, referred to as FPMDRAM), Extended Date Out Dynamic Random Access Memory (Extended Date Out Dynamic Random Access Memory, referred to as EDODRAM), Synchronous Dynamic Random Access Memory (Synchronous Dynamic Random-Access Memory) Access Memory, referred to as SDRAM) and so on.

Memory 304 may be used to store or cache various data files required for processing and/or communication use, and possibly computer program instructions executed by processor 302 .

The processor 302 reads and executes the computer program instructions stored in the memory 304 to implement any one of the millimeter-wave radar-based abnormality warning methods in the foregoing embodiments.

Optionally, the aforementioned electronic device may further include a transmission device 306 and an input/output device 308 , wherein the transmission device 306 is connected to the aforementioned processor 302 , and the input/output device 308 is connected to the aforementioned processor 302 .

Optionally, in this embodiment, the above-mentioned processor 302 may be configured to perform the following steps through a computer program:

S1, acquire observation events detected by the millimeter-wave radar in a preset monitoring scene.

S2: Acquire the reporting event locally reported by any target collected by the preset local reporting device.

S3, according to the characteristic information of the observed event and the reported event, and the correlation between the observed event and the reported event, determine the risk level of the monitoring scene.

S4, according to the danger level of the monitoring scene, select a warning device matching the danger level from a variety of preset warning devices to perform warning processing.

It should be noted that, for specific examples in this embodiment, reference may be made to the examples described in the foregoing embodiments and optional implementation manners, and details are not described herein again in this embodiment.

In addition, in combination with the abnormality warning method based on the millimeter wave radar in the above embodiment, the embodiment of the present application may provide a storage medium for implementation. A computer program is stored on the storage medium; when the computer program is executed by the processor, any one of the millimeter-wave radar-based abnormality warning methods in the foregoing embodiments is implemented.

Those skilled in the art should understand that the technical features of the above embodiments can be combined arbitrarily. In order to simplify the description, all possible combinations of the technical features in the above embodiments are not described. However, as long as these technical features There is no contradiction in the combination of the above, and they should be considered to be within the scope of the description in this specification.

The above examples only represent several embodiments of the present application, and the descriptions thereof are specific and detailed, but should not be construed as a limitation on the scope of the present application. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the scope of protection of the present application should be determined by the appended claims.

Claims (10)

1. An abnormality warning method based on a millimeter wave radar, characterized by comprising:

acquiring an observation event detected by a millimeter wave radar in a preset monitoring scene;

acquiring a reporting event which is acquired by a preset local reporting device and is reported locally by any target;

determining the danger level of the monitoring scene according to the characteristic information of the observation event and the reported event and the incidence relation between the observation event and the reported event;

and selecting the warning device matched with the danger grade from a plurality of preset warning devices to perform warning processing according to the danger grade of the monitoring scene.

2. The millimeter wave radar-based anomaly warning method according to claim 1, wherein determining the risk level of the monitoring scene according to the feature information of the observation event and the reported event and the association relationship between the observation event and the reported event comprises:

determining whether abnormal behaviors exist in the monitoring scene or not according to the characteristic information of the observation event, wherein the abnormal behaviors comprise target falling behaviors and target breathing abnormal behaviors;

determining the danger level of the monitoring scene according to the characteristic information of the observation event under the condition that abnormal behaviors exist in the monitoring scene;

determining the danger level of the monitoring scene according to the characteristic information of the reported events under the condition that the number of the reported events is greater than zero;

and under the condition that abnormal behaviors exist in the monitoring scene and the number of the reported events is larger than zero, determining the danger level of the monitoring scene according to the characteristic information of the observation event and the reported events and the incidence relation between the observation event and the reported events.

3. The millimeter wave radar-based anomaly warning method according to claim 2, wherein determining the danger level of the monitoring scene according to the characteristic information of the observation event comprises:

determining the number of normal targets except for abnormal targets in the monitoring scene according to the characteristic information of the observation event, wherein the abnormal targets correspond to the abnormal behaviors;

determining whether the abnormal behavior disappears or not according to the characteristic information of the observation event;

and determining the danger level of the monitoring scene according to the number of the normal targets in the monitoring scene and the existence state of the abnormal behavior.

4. The millimeter wave radar-based anomaly warning method according to claim 2, wherein determining the risk level of the monitoring scene according to the characteristic information of the reported event comprises:

determining the occurrence frequency of the reporting event in a preset first time period according to the characteristic information of the reporting event;

and determining the danger level of the monitoring scene according to the occurrence frequency of the reporting event in the first time period.

5. The millimeter wave radar-based anomaly warning method according to claim 2, wherein determining the risk level of the monitoring scene according to the feature information of the observation event and the reported event and the association relationship between the observation event and the reported event comprises:

determining the number of normal targets except for abnormal targets in the monitoring scene according to the characteristic information of the observation event, wherein the abnormal targets correspond to the abnormal behaviors;

determining whether the abnormal behavior disappears or not according to the characteristic information of the observation event;

determining the occurrence frequency of the reporting event in a preset first time period according to the characteristic information of the reporting event;

determining occurrence time intervals of the abnormal behaviors and the reported events in a preset second time period according to the characteristic information of the observation events and the reported events;

determining that an association relationship exists between the abnormal behavior and the reporting event under the condition that whether the occurrence time interval of the abnormal behavior and the reporting event in the second time period is smaller than a preset fifth threshold value or not;

and determining the danger level of the monitoring scene according to the number of the normal targets in the monitoring scene, the existence state of the abnormal behavior, the occurrence frequency of the reporting event in the first time period and the incidence relation between the abnormal behavior and the reporting event.

6. The millimeter wave radar-based abnormality warning method according to claim 5, wherein the danger levels include a low danger level, a medium danger level, and a high danger level; determining the risk level of the monitoring scene according to the number of the normal targets in the monitoring scene, the existence state of the abnormal behavior, the occurrence frequency of the reporting event in the first time period and the incidence relation between the abnormal behavior and the reporting event, wherein the determining the risk level of the monitoring scene comprises:

determining a risk degree score of the monitoring scene according to the number of the normal targets in the monitoring scene, the existence state of the abnormal behavior, the occurrence frequency of the reporting event in the first time period and the incidence relation between the abnormal behavior and the reporting event;

when the risk degree score of the monitoring scene is smaller than or equal to a preset first threshold value, determining that the monitoring scene is in a low risk level;

or when the risk degree score of the monitoring scene is larger than the first threshold and is smaller than or equal to a preset second threshold, determining that the monitoring scene is a medium risk level;

or when the risk degree score of the monitoring scene is larger than the second threshold value, determining that the monitoring scene is in a high risk level.

7. The millimeter wave radar-based anomaly warning method according to claim 6, wherein according to the number of the normal targets in the monitoring scene, the existence state of the abnormal behavior, the occurrence frequency of the reporting event in the first time period and the correlation between the abnormal behavior and the reporting event, determining the risk score of the monitoring scene comprises:

when abnormal behaviors exist in the monitoring scene and/or the number of reported events is larger than zero, determining the risk score of the monitoring scene as a preset first score;

when the number of the normal targets is larger than a preset third threshold value, determining that the risk score is reduced by a preset second score;

when the occurrence frequency of the reporting event in the first time period is greater than a preset fourth threshold, determining that the risk score is increased by a preset third score;

when the abnormal behavior and the reported event have an incidence relation, determining the risk score as a preset fourth score;

and when the abnormal behavior disappears, determining that the risk score is reduced by a preset fifth value.

8. An abnormality warning system based on a millimeter wave radar, characterized in that the system comprises: the system comprises an event observation device, a local reporting device and a warning device; wherein,

the event observation device comprises a millimeter wave radar and a processor, and the processor is in communication connection with the millimeter wave radar, the local reporting device and the warning device;

the millimeter wave radar is used for detecting observation events occurring in a preset monitoring scene;

the local reporting device is used for collecting a reporting event of any target reported locally and manually;

the processor is used for executing the millimeter wave radar-based abnormality warning method according to any one of claims 1 to 7;

the warning device comprises a local warning device, a remote warning device and a designated warning device, and the warning device is controlled by the processor to execute corresponding warning actions.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to perform the millimeter wave radar-based abnormality warning method according to any one of claims 1 to 7.

10. A storage medium having a computer program stored therein, wherein the computer program when executed by a processor implements the millimeter wave radar-based abnormality warning method according to any one of claims 1 to 7.

Images