WO2022036624A1 - Monitoring method and apparatus, electronic device, and storage medium - Google Patents

Abstract

A monitoring method and apparatus, an electronic device, and a storage medium. The method comprises: obtaining monitoring data acquired by a smart monitoring device (S201); according to the monitoring data and a preset monitoring evaluation model, determining state information of an object to be monitored (S202); and then generating a monitoring instruction according to the state information (S203). The method implements the automatic monitoring and supervision of a nursing object and a nursed object in a nursing activity, timely discovers an abnormal behavior and physiological state of the monitored object to timely instruct the nursing object to deal with, and can timely notify a supervision object of the occurrence of a physiological or behavior anomaly of the nursing object. The method achieves the technical effects of improving timely and effective nursing of the nursed object, discovering an abnormal physiological problem, such as illness of the nursed object, as early as possible, and timely estimating and discovering whether a nursing behavior of the nursing object is appropriate and whether the nursing object maltreats the nursed object.

Description

Monitoring method, device, electronic device, and storage medium technical field

The present application relates to the field of video surveillance, and in particular, to a monitoring method, apparatus, electronic device, and storage medium.

Background technique

The care of people or animals and plants has become a very common activity in our daily life, such as the care of infants and young children, the care of the elderly, the care of teachers for young students such as kindergartens or elementary schools, and the care of pets by pet shop attendants. , the care of animals in zoos, etc.

Some of the existing nursing activities lack monitoring, and the nursing activities installed with monitoring systems also rely heavily on manual monitoring, which cannot realize automatic monitoring of the physiology and behavior of the nursing objects and the objects under care. When a person under care commits abusive behavior, it cannot be detected and stopped in time, and evidence may also be removed artificially, resulting in frequent abuse.

Therefore, the prior art has the technical problem that the automatic monitoring of the nursing behavior cannot be realized.

SUMMARY OF THE INVENTION

The present application provides a monitoring method, device, electronic device, and storage medium to solve the technical problem that automatic monitoring of nursing behavior cannot be realized in the prior art.

In a first aspect, the present application provides a monitoring method, comprising:

acquiring monitoring data collected by an intelligent monitoring device, the monitoring data includes behavior data and physiological data of an object to be monitored, and the object to be monitored includes: a nursing object and a nursing object;

Determine the state information of the object to be monitored according to the monitoring data and a preset monitoring evaluation model;

A monitoring instruction is generated according to the state information, and the monitoring instruction is used to send prompt information to the care object and/or the supervision object, and record the behavior of the care object and/or the supervision object.

In a possible design, the monitoring data includes first behavior data of the monitored object, and correspondingly, the state information of the to-be-monitored object is determined according to the monitoring data and a preset monitoring evaluation model, include:

It is determined according to the first video surveillance data in the first behavior data and the preset surveillance evaluation model that the object under care is not in the video surveillance area, and the first video surveillance data is the video surveillance of the object under care data, the state information is the first abnormal state;

Correspondingly, the generating a monitoring instruction according to the state information includes:

Generate first prompt information for prompting the care object according to the first abnormal state.

In a possible design, after it is determined according to the first video surveillance data in the first behavior data and the preset surveillance evaluation model that the guarded object is not in the video surveillance area, the method further includes:

If it is determined according to the first position monitoring data in the first behavior data and the preset monitoring evaluation model that the guarded object leaves the safe activity area, the first position monitoring data is the position monitoring of the guarded object data, the safety activity area includes the video surveillance area and the non-video surveillance area, then the state information is determined to be a second abnormal state, and the monitoring instruction is used to generate second prompt information to prompt the care object;

If it is determined according to the first position monitoring data in the first behavior data and the preset monitoring evaluation model that the guarded object has not left the safe activity area, the state information is determined as a third abnormality state, the monitoring instruction is used to generate third prompt information for prompting the care object.

In a possible design, the monitoring data includes first physiological data of the monitored object, and the first physiological data includes first physiological characteristic data collected by a first wearable device and information in the safe activity zone. Environmental characteristic data collected by infrared detection equipment;

Correspondingly, the determining the state information of the object to be monitored according to the monitoring data and the preset monitoring evaluation model further includes:

If it is determined according to the first physiological feature data and the preset monitoring and evaluation model that the object under care meets a first preset pending abnormal condition, then the object is determined according to the environmental feature data and the preset monitoring and evaluation model. The person under care is in the fourth abnormal state;

The generating a monitoring instruction according to the state information includes:

Fourth prompt information for prompting the care object and/or the supervision object is generated according to the fourth abnormal state.

Optionally, the monitoring data further includes second physiological data of the care object, and the second physiological data includes second physiological characteristic data collected by the second wearable device and environment collected by the infrared detection device in the safe activity area. characteristic data;

Correspondingly, the state information of the object to be monitored is determined according to the monitoring data and the preset monitoring evaluation model, further comprising:

If it is determined according to the second physiological feature data and the preset monitoring evaluation model that the nursing object meets a second preset pending abnormal condition, then the nursing object is determined according to the environmental feature data and the preset monitoring evaluation model The subject is in the fifth abnormal state;

The generating a monitoring instruction according to the state information includes:

Fifth prompt information for prompting the supervision object is generated according to the fifth abnormal state.

In a possible design, the monitoring data includes the second behavior data of the nursing object, and correspondingly, in the determining according to the environmental characteristic data and the preset monitoring evaluation model that the nursing object is in After the fourth abnormal state, it also includes:

Determine the distance between the object of care and the object of care according to the first behavior data, the second behavior data and the preset monitoring evaluation model;

If the distance is less than the preset distance, use the preset monitoring evaluation model and the second behavior data to determine the behavior characteristics of the care object;

monitoring the duration of time that the subject is in the fourth abnormal state;

If the duration is greater than a preset time threshold, it is determined that the subject under care is in a state of being abused.

If the distance is greater than or equal to the preset distance, determining that the duration is greater than a third preset time threshold;

Eighth prompt information is sent to the supervision object, where the eighth prompt information is used to indicate that the care object has "neglected" abusive behavior to the care object.

In a possible design, the second behavior data includes: action features, facial expression features, and voice features, and the determining that the object under care is in a state of being abused includes:

If it is determined according to the action feature and the preset monitoring evaluation model whether the care object performs the abusive behavior on the care object, if the judgment result is yes, the sixth prompt is sent to the supervision object information;

If the judgment result is no, then according to the facial expression feature and/or the sound feature and the preset monitoring evaluation model, it is judged whether the care object performs the abusive behavior on the care object, if the judgment result is If yes, send the seventh prompt information to the supervision object;

If the determination result is no, when the duration is greater than the preset time threshold, the seventh prompt information is sent to the supervision object.

In a second aspect, the present application provides a monitoring device, comprising:

an acquisition module, configured to acquire monitoring data collected by the intelligent monitoring device, the monitoring data includes behavioral data and physiological data of an object to be monitored, and the object to be monitored includes: a nursing object and a nursing object;

a processing module, configured to determine the state information of the object to be monitored according to the monitoring data and a preset monitoring evaluation model;

The processing module is further configured to generate a monitoring instruction according to the state information, where the monitoring instruction is used to send prompt information to the care object and/or the supervision object.

In a possible design, the monitoring data includes the first behavior data of the guarded object, and correspondingly, the processing module is configured to determine the to-be-monitored according to the monitoring data and a preset monitoring evaluation model The state information of the object, including:

The processing module is configured to determine, according to the first video surveillance data in the first behavior data and the preset surveillance evaluation model, that the object under care is not in the video surveillance area, and the first video surveillance data is the The video surveillance data of the object under care, the state information is the first abnormal state;

Correspondingly, the processing module is further configured to generate a monitoring instruction according to the status information, including:

The processing module is further configured to generate first prompt information for prompting the care object according to the first abnormal state.

In a possible design, the processing module is configured to determine, according to the first video surveillance data in the first behavior data and the preset surveillance evaluation model, that the guarded object is not behind the video surveillance area ,Also includes:

The processing module is further configured to: if it is determined according to the first position monitoring data in the first behavior data and the preset monitoring evaluation model that the guarded object leaves the safe activity area, the first position monitoring data is: The position monitoring data of the guarded object, the safe activity area includes the video monitoring area and the non-video monitoring area, then the state information is determined to be the second abnormal state, and the monitoring instruction is used to generate a prompt that the The second prompt information of the care object;

The processing module is further configured to: if it is determined according to the first position monitoring data in the first behavior data and the preset monitoring evaluation model that the object under care has not left the safe activity area, then The state information is determined to be a third abnormal state, and the monitoring instruction is used to generate third prompt information for prompting the care object.

In a possible design, the monitoring data includes first physiological data of the monitored object, and the first physiological data includes first physiological characteristic data collected by a first wearable device and information in the safe activity zone. Environmental characteristic data collected by infrared detection equipment;

Correspondingly, the processing module is further configured to determine the status information of the object to be monitored according to the monitoring data and a preset monitoring evaluation model, further comprising:

The processing module is further configured to, if it is determined according to the first physiological feature data and the preset monitoring and evaluation model that the object under care meets a first preset pending abnormal condition, then according to the environmental feature data and the The preset monitoring and evaluation model determines that the object under care is in the fourth abnormal state;

The processing module is further configured to generate a monitoring instruction according to the state information, including:

The processing module is further configured to generate fourth prompt information for prompting the care object and/or the supervision object according to the fourth abnormal state.

Optionally, the monitoring data further includes second physiological data of the care object, and the second physiological data includes second physiological characteristic data collected by the second wearable device and environment collected by the infrared detection device in the safe activity area. characteristic data;

Correspondingly, the processing module is further configured to determine the status information of the object to be monitored according to the monitoring data and a preset monitoring evaluation model, further comprising:

The processing module is further configured to, if it is determined according to the second physiological feature data and the preset monitoring and evaluation model that the care object meets a second preset pending abnormal condition, then according to the environmental feature data and the preset monitoring and evaluation model. Suppose the monitoring evaluation model determines that the care object is in the fifth abnormal state;

The processing module is further configured to generate a monitoring instruction according to the state information, including:

The processing module is further configured to generate fifth prompt information for prompting the supervised object according to the fifth abnormal state.

In a possible design, the monitoring data includes second behavior data of the care object, and correspondingly, in the processing module, it is further configured to determine according to the environmental feature data and the preset monitoring evaluation model After the object under care is in the fourth abnormal state, it also includes:

The processing module is further configured to determine the distance between the object of care and the object of care according to the first behavior data, the second behavior data and the preset monitoring and evaluation model;

The processing module is further configured to, if the distance is less than the preset distance, use the preset monitoring evaluation model and the second behavior data to determine the behavioral characteristics of the care object;

The processing module is further configured to monitor the duration that the object under care is in the fourth abnormal state;

The processing module is further configured to determine that the object under care is in a state of being abused if the duration is greater than a preset time threshold.

In a possible design, the second behavior data includes: action features, facial expression features, and voice features, and the processing module is further configured to determine that the object under care is in a state of being abused, including:

The processing module is further configured to judge whether the object of care has performed the abuse on the object of care according to the action feature and the preset monitoring and evaluation model, and if the judgment result is yes, then report to the object of care. The supervision object sends the sixth prompt information;

The processing module is further configured to, if the judgment result is no, according to the facial expression feature and/or the sound feature and the preset monitoring evaluation model, to judge whether the object of care has performed any action on the object under care. If the judgment result is yes, send the seventh prompt message to the supervision object;

The processing module is further configured to send the seventh prompt information to the supervision object when the duration is greater than the preset time threshold if the determination result is no.

In a third aspect, the application provides an electronic device, comprising:

memory for storing program instructions;

The processor is configured to call and execute the program instructions in the memory, and execute any one of the possible monitoring methods provided in the first aspect.

In a fourth aspect, the present application provides a storage medium, where a computer program is stored in the readable storage medium, and the computer program is used to execute any one of the possible monitoring methods provided in the first aspect.

The monitoring method, device, electronic device and storage medium provided by the present application obtain the monitoring data collected by the intelligent monitoring device, determine the status information of the object to be monitored according to the monitoring data and the preset monitoring evaluation model, and then generate the status information according to the status information. Monitoring instructions. It realizes the automatic monitoring and supervision of the care objects and the care objects in the care activities, and timely discovers the abnormal behavior and physiological state of the care objects, so as to notify the care objects to deal with them in time, and when the care objects' physiology or behavior is abnormal, it can Notify supervisory objects in a timely manner. It can improve the timely and effective care of the care recipients, and early detection of abnormal physiological problems such as illnesses of the care recipients. It can also timely evaluate and discover whether the care objects are in place, and whether the care objects have been abused. Technical effects such as behavior.

Description of drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the accompanying drawings used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description These are some embodiments of the present application, and for those of ordinary skill in the art, other drawings can also be obtained from these drawings without any creative effort.

1a-1f are schematic diagrams of monitoring scenarios and monitoring equipment provided by embodiments of the present application;

2 is a schematic flowchart of a monitoring method provided by the first embodiment of the present application;

3 is a schematic flowchart of a monitoring method provided by the second embodiment of the present application;

4 is a schematic flowchart of a monitoring method provided by a third embodiment of the present application;

5 is a schematic flowchart of a monitoring method provided by a fourth embodiment of the present application;

6 is a schematic flowchart of a monitoring method provided by a fifth embodiment of the present application;

FIG. 7 is a schematic structural diagram of a monitoring device according to an embodiment of the present application;

FIG. 8 is a schematic structural diagram of an electronic device provided by the present application.

Specific embodiments of the present application have been shown by the above-mentioned drawings, and will be described in more detail hereinafter. These drawings and written descriptions are not intended to limit the scope of the concepts of the present application in any way, but to illustrate the concepts of the present application to those skilled in the art by referring to specific embodiments.

detailed description

In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances so that the embodiments of the application described herein, for example, can be implemented in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having" and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those expressly listed Rather, those steps or units may include other steps or units not expressly listed or inherent to these processes, methods, products or devices.

The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below with reference to the accompanying drawings.

There are many specific application scenarios for existing nursing activities, including the following scenarios:

1. The babysitter's care of infants and young children.

Because infants and young children cannot express their needs through language, or because babysitters are busy doing other things and neglect to take care of infants and young children. In the prior art, cameras, sound sensors, etc. are generally installed at home to passively monitor the state of infants and young children. Physiological diseases, syncope, etc., cannot transmit the sound in time, making the monitoring system and the nanny unable to detect the abnormality of infants and young children in time.

2. Nursing care for the elderly.

For the elderly who are sick or who are bedridden for a long time and cannot walk, when the carer does not stay by the elderly, the elderly's physiological state is abnormal, such as cardiac arrest, respiratory failure, fever, etc., and the elderly may not be able to make a sound in time Calling nurses, video surveillance also requires manual monitoring all the time, in order to avoid the occurrence of tragedies.

3. Supervision of young students in kindergartens or schools.

The care recipients in this age group already have the initial ability to act autonomously, and strong curiosity always drives the care recipients into dangerous environments, and the existing video surveillance systems in schools or kindergartens cannot Remind teachers in a timely manner after monitoring that the person under care has left the school or classroom without authorization. In addition, young care recipients have not yet fully mastered the ability to express their physical or behavioral needs in language, which leads to young care recipients being intimidated and afraid to speak after being abused, while surveillance video does not. If it is photographed or destroyed artificially, it is impossible to supervise the custody behavior of the caregiver.

4. The care of animals by pet shop or zoo breeders.

Animals can't speak, and breeders can't detect the abnormal state of animals in time. The existing monitoring system requires manual supervision in real time. However, due to the particularity of animals, the monitoring system cannot achieve effective supervision and evaluation of custody behavior. Supervision to serious abuses, and can not achieve refined supervision.

Based on the technical problems in the above-mentioned specific application scenarios, the present application provides a monitoring method. By simultaneously monitoring the physiological and behavioral state information of the nursing object and the nursing object, the trained preset monitoring and evaluation model is used to synthesize physiological and behavioral state information. The data of two or more behaviors can realize the precise and precise monitoring of infants, the elderly, young students, and pets, improve the quality of care of the care recipients, and achieve the technical effect of timely detection and prevention of abusive behaviors of the care recipients. .

1a-1f are schematic diagrams of monitoring scenarios and monitoring devices provided by embodiments of the present application. Figure 1a is a schematic diagram of the layout of monitoring equipment in the house, that is, the safe activity area. As shown in Figure 1a, a plurality of fixed monitoring equipment 11 are arranged in the house, and each monitoring equipment can monitor the monitoring area 111 in real time. The monitoring equipment 11 may include: cameras, infrared imagers, thermal sensors, sound sensors, temperature sensors, radars, etc. The monitoring area covered by the cameras forms a video monitoring area, and the video monitoring area may cover the entire security activity area, or may be smaller than the security activity area. Because it is not convenient to set up camera monitoring in privacy-related areas such as storage rooms, cloakrooms, and toilets, the areas where these cameras cannot obtain surveillance video are non-video surveillance areas. For non-video surveillance areas, infrared imagers and thermal sensors can be arranged. , temperature sensor, sound sensor, etc., when the care object enters the non-video surveillance area, it can still be monitored by the monitoring equipment.

Figure 1b is a schematic diagram of a baby wearable monitoring device. The wearable monitoring device 121 may include an abdominal physiological collection belt device and a leg physiological collection ring device. The wearable monitoring device 121 can read the baby's physiological data and behavioral data, including: heart rate, blood oxygen content, blood pressure, respiratory rate, motion sensing data, body temperature detection data, etc., and the wearable monitoring device 121 can have a wireless communication function , the collected data can be sent to the monitoring center server. The wearable monitoring device 121 may be configured to be waterproof. In addition, the wearable monitoring device 121 can also collect the sound of the surrounding environment, including the sound of the baby and the voice of the caregiver. Optionally, the wearable monitoring device 121 also has a power indicator light to remind the user to charge or replace the battery in time.

Figure 1c is a schematic diagram of a wearable monitoring device for infants or young learners. As shown in FIG. 1 c , the wearable monitoring device 122 may include a wristband and a foot ring, and the functions of the wristband and the foot ring are similar to those of the wearable monitoring device 121 , and details are not described herein again.

Figure 1d is a schematic diagram of a wearable monitoring device for animals. As shown in FIG. 1d , the wearable monitoring device 123 may include a collar, and the collar may collect the physiological data and behavioral data of the animal.

In one possible design, the wearable monitoring device 123 may also include: chest, abdomen and leg wearable devices. For example, wearable devices in the shape of "bracelets" or "watches" can be worn on horses on the chest, abdomen and legs, respectively, to detect the horse's daily activities and infection.

FIG. 1e is a schematic diagram of a wearable monitoring device for a caregiver, that is, a care object. As shown in FIG. 1e, the nursing watch 13 may include the following functions, prompting functions: displaying prompting information, issuing prompting sounds, issuing warning vibrations, etc., including prompting the completion status of nursing tasks and emergency nursing needs according to time; Physiological state data, location information, etc. of the nursing object; monitoring function of the nursing object's own state: real-time monitoring of the nursing object's heart rate, blood pressure, blood oxygen, respiratory rate, movement, exercise status, etc.; wireless communication function: used to communicate with the monitoring center server Data interaction, and calls with supervisory objects.

Fig. 1f is a vital sign sensing pad 14, which is used to obtain the vital signs of the person under care or the care object, such as heart rate, respiratory rate, temperature change, body movement and posture change, etc. From the vital sign data, the person under care can be judged Or the physical activity of the care subject, such as sleep state.

It should also be noted that the monitoring system may further include a GPS or Beidou positioning device and an indoor positioning radar, which are used to detect the position of the guarded object or the guarded object.

FIG. 2 is a schematic flowchart of the monitoring method provided by the first embodiment of the present application. As shown in Figure 2, the method includes:

S201. Obtain monitoring data collected by an intelligent monitoring device.

In this step, the monitoring data includes behavior data and physiological data of the object to be monitored, and the object to be monitored includes: a nursing object and a nursing object.

Specifically, the intelligent monitoring equipment includes fixed monitoring equipment, wearable monitoring equipment, global location positioning equipment such as GPS or Beidou navigation system, etc. shown in Figures 1a-1f. , and upload the collected monitoring data to the monitoring center server.

S202. Determine the state information of the object to be monitored according to the monitoring data and a preset monitoring evaluation model.

In this step, the monitoring center analyzes the collected monitoring data by using a preset monitoring evaluation model, so as to identify the physiological characteristics and behavioral characteristics of the nursing object and the nursing object. In this way, it can be obtained whether the care object needs to be looked after, or whether the care object has a sudden physiological disease, or whether the care object has abused the care object.

For example, in the middle of the night, a person under care, such as an elderly person, has a sudden myocardial infarction, and the physiological data has changed. The physiological data collected by the wearable device is identified by the preset monitoring and evaluation model of the monitoring center that the elderly is in a physiological abnormal state.

For another example, the nanny shows the action of slapping the infant in the surveillance video. At this time, the monitoring center server judges the behavior as abuse to be further verified based on the video image, and then the monitoring center server can retrieve the nanny's monitoring watch, Wearable monitoring equipment for infants and young children, as well as monitoring data from fixed monitoring equipment in the room, comprehensively analyze whether the babysitter is really abusing infants and young children. Because if infants and young children are being abused, their physiological data such as heartbeat, blood pressure, body temperature, etc. will change, that is, the care recipient is in a physiologically abnormal state, and the time taken for the care recipient to recover from the physiological abnormal state to a normal state, or The duration of the abnormal physiological state can be used to determine whether the care object has insufficient care or abused the care object.

Another example: when the baby is crying, the babysitter or other caregivers may ignore the baby's cry. If the monitoring device detects that the baby's cry is longer than a preset time threshold, it can determine that the caregiver has "neglected" abuse.

Another example: babysitters feeding babies illegal drugs, such as sleeping pills. The monitoring equipment can detect that the baby's sleep time is longer than the comparison reference time obtained by the detection model established based on historical data, and the baby's heartbeat or other physiological indicators are low, which can be detected by the monitoring system and reported to the supervisor. object.

S203. Generate a monitoring instruction according to the status information.

In this step, the monitoring instruction is used to send prompt information to the care object and/or the supervision object.

Specifically, when the monitoring center server detects that the person under care has a sudden emergency physiological disease, it can send prompt information to the care object, including displaying the emergency state, making sounds and vibrations, and can classify the emergency degree by the intensity of the sound and vibration. For sudden diseases such as stroke, myocardial infarction, etc. that endanger life, you can also directly send alarm information to the emergency department of the hospital.

For caregivers, if the caregivers suffer from sudden physical diseases, such as fainting, they will directly send alarm and help information to the supervision objects such as family members, community neighborhood committees, and police stations.

If the care object abuses the care object, an alarm message will be sent to the supervision object, and the care object's wearable monitoring device will also issue an alarm prompt message, such as a voice prompt, to prompt the care object to stop his abusive behavior in time.

In the monitoring method provided by this embodiment, the monitoring data collected by the intelligent monitoring device is acquired, the status information of the object to be monitored is determined according to the monitoring data and a preset monitoring evaluation model, and then a monitoring instruction is generated according to the status information. It realizes the automatic monitoring and supervision of the care objects and the care objects in the care activities, and timely discovers the abnormal behavior and physiological state of the care objects, so as to notify the care objects to deal with them in time, and when the care objects' physiology or behavior is abnormal, it can Notify supervisory objects in a timely manner. It can improve the timely and effective care of the care recipients, and early detection of abnormal physiological problems such as illnesses of the care recipients. It can also timely evaluate and find out whether the care objects are in place and whether the care objects have been abused. Technical effects such as behavior.

FIG. 3 is a schematic flowchart of the monitoring method provided by the second embodiment of the present application. As shown in Figure 3, the specific steps of the method include:

S301. Acquire monitoring data collected by an intelligent monitoring device, where the monitoring data includes first behavior data of a guarded object.

In this step, the first behavior data includes first video surveillance data of the guarded object. That is, the video data collected by the cameras installed in the safe activity area.

S302. Determine according to the first video surveillance data in the first behavior data and the preset monitoring evaluation model that the guarded object is not in the video surveillance area, and then determine that the state information of the guarded object is the first abnormal state.

In this step, the first video surveillance data is the video surveillance data of the guarded object.

The preset monitoring evaluation model cannot identify the guarded object from the collected first video surveillance data, that is, the guarded object leaves the range of the video surveillance area.

S303. Generate first prompt information for prompting the care object according to the first abnormal state.

In this step, as long as the monitoring center server determines that the guarded object has left the video surveillance area, it will send the first prompt information to the guarded object, such as a buzzer alarm that lasts for 5s.

The monitoring method provided in this embodiment is suitable for application scenarios with high requirements for video monitoring of the object of care, such as the object of care is an infant, or an animal cub, or an area with many video surveillance blind spots, or non-video surveillance The area is a high-risk area for the care object, which plays a role in reminding the care object to pay attention in time.

FIG. 4 is a schematic flowchart of a monitoring method provided by a third embodiment of the present application. As shown in Figure 4, the specific steps of the method include:

S401. Acquire monitoring data collected by an intelligent monitoring device, where the monitoring data includes first behavior data of a guarded object.

S402. Determine, according to the first video surveillance data in the first behavior data and the preset surveillance evaluation model, that the object to be guarded is not in the video surveillance area.

The principles and terminology of steps S401-S402 are similar to those of S301-S302, and will not be repeated here.

S403. If it is determined according to the first position monitoring data in the first behavior data and the preset monitoring evaluation model that the guarded object has left the safe activity area, determine that the state information of the guarded object is the second abnormal state.

S404. Generate second prompt information for prompting the care object.

Specifically, the first position monitoring data may be GPS positioning data, and the preset monitoring evaluation model determines whether the guarded object has left the safe activity area according to the GPS positioning data. Steps S405-S406.

It should be noted that the second prompt information is used to remind the care object that the care object has left the safe activity area at the current moment, there is an unpredictable safety risk, and the care object needs to be brought back to the safe activity area in time. The second prompt information may include display data, sound, vibration, and the like.

S405. If it is determined according to the first position monitoring data in the first behavior data and the preset monitoring evaluation model that the guarded object has not left the safe activity area, determine the state information as a third abnormal state.

In this step, the preset monitoring evaluation model recognizes through the first location monitoring data, such as GPS positioning data, that the person under care has not left the safe activity area, but just left the video monitoring area, then the preset monitoring evaluation model can further use infrared imaging Monitoring equipment such as instrument and thermal sensor monitor the fat video monitoring area to find the location of the person under care, and can further monitor whether the physiological data of the person under care is abnormal. If there is a physiological abnormal state, enter the next step.

S406. Generate third prompt information for prompting the care object.

In this step, the third prompt information is used to prompt the care object to pay attention to whether the care object in the non-video surveillance area needs to be looked after.

It should be noted that if the physiological state of the person under care is not abnormal, and returns to the video surveillance area within the preset time threshold, it is not necessary to send a reminder message to the care object, or send another alarm cancellation message.

The monitoring method provided by this embodiment further determines whether the behavior of the object under care is abnormal through the first position monitoring data, so that the prompt information is classified and graded, so as to reduce the workload of the object under care, and automatically identify whether the intervention of the object under care is required. Take further caregiving actions.

FIG. 5 is a schematic flowchart of the monitoring method provided by the fourth embodiment of the present application. As shown in Figure 5, the specific steps of the method include:

S501. Obtain monitoring data collected by an intelligent monitoring device.

In this step, the monitoring data includes first physiological data of the object under care, and the first physiological data includes first physiological feature data collected by a first wearable device and environmental features collected by a detection device in the safe activity area data.

The first physiological characteristic data includes physiological characteristic indicators such as heart rate, body temperature, blood pressure, blood oxygen, respiratory rate and the like of the care object.

Environmental characteristic data include: temperature field distribution, humidity, oxygen content, CO ₂ concentration, etc.

In a possible design, the monitoring data further includes second physiological data of the care object, the second physiological data includes second physiological characteristic data collected by the second wearable device and collected by the detection device in the safe activity area environmental characteristics data.

The second physiological characteristic data includes physiological characteristic indicators such as heart rate, body temperature, blood pressure, blood oxygen, and respiratory rate of the care object.

S502. Determine, according to the first physiological characteristic data and the preset monitoring evaluation model, that the object under care meets the first preset pending abnormal condition.

In this step, the monitoring center server automatically uses a preset monitoring and evaluation model according to the first physiological characteristic data of the guarded object to determine whether the physiological characteristics of the guarded object are suspected to be abnormal, that is, the first preset pending Exceptional condition. For example, at least one of the heart rate, blood pressure, respiratory rate, and body temperature of the person under care exceeds the corresponding preset threshold.

S503. Determine, according to the second physiological characteristic data and the preset monitoring evaluation model, that the care object satisfies the second preset pending abnormal condition.

In this step, the monitoring center server, according to the second physiological characteristic data of the nursing object, uses a preset monitoring evaluation model to determine whether the physiological characteristics of the nursing object are suspected to be abnormal, that is, the second preset pending abnormal condition is satisfied. . For example, at least one of the heart rate, blood pressure, respiratory rate, and body temperature of the care object exceeds a corresponding preset threshold.

S504. Determine that the object under care is in a fourth abnormal state according to the environmental characteristic data and the preset monitoring and evaluation model.

In this step, since the suspected abnormal situation of the physiological characteristics of the object under care may be caused by changes in the environment, in order to further confirm whether the object under care really has a physiological abnormality, it is necessary to combine the environmental characteristic data for confirmation. For example, if the person being cared for is an elderly person, the elderly person enters the bathroom to take a bath, and the high temperature and high humidity environment in the bathroom will lead to an increase in the elderly's heartbeat, respiratory rate, body temperature and other indicators. It is possible that these indicators exceed the threshold and will be monitored by the monitoring center. The server monitors that, in order to improve the accuracy of the judgment, the monitoring center server will retrieve the environmental characteristic data such as the temperature distribution, humidity, oxygen content, carbon dioxide concentration, etc. of the bathroom for comprehensive analysis. Coma, etc., then confirm that it is in the fourth abnormal state.

S505. Determine that the nursing object is in the fifth abnormal state according to the environmental characteristic data and the preset monitoring and evaluation model.

In this step, since the suspected abnormal situation of the physiological characteristics of the nursing object may also be caused by the change of the environment, in order to further confirm whether the physiological abnormality of the nursing object really occurs, it is necessary to combine the environmental feature data for confirmation. For example: the monitoring center server detects that the body temperature of the care object has risen above a preset threshold. At this time, combined with the fact that the care object is in the kitchen environment, through the temperature distribution of the kitchen environment, it is found that the care object is cooking food, then its body temperature rises Probably due to false positives from cooking food. Another example: if the care object is in the living room, but the ambient temperature in the living room is normal, but the body temperature of the care object exceeds the preset threshold, the monitoring center server can then call the historical positioning data of the care object to confirm whether it has been to the infectious disease area. If you have been in contact with someone infected with an infectious disease and have symptoms of fever, notify the supervised objects such as community neighborhood committees, hospitals, epidemic prevention departments, police stations, etc., and prompt the supervised objects to take treatment or isolation measures for the care objects.

S506. Generate fourth prompt information for prompting the care object and/or the supervision object.

In this step, after it is determined that the object under care is physiologically abnormal, fourth prompt information is generated to prompt the object under care and/or the object under supervision, so as to timely rescue the object under care.

S507. Generate fifth prompt information for prompting the supervision object.

In this step, after it is determined that the nursing object is abnormal in physiology, fifth prompt information for prompting the supervision object is generated, so as to rescue the nursing object.

This embodiment shows that when the person under care or the person under care has a physiological disease, the monitoring center server can automatically discover the physiological abnormality of the object under care or the person under care, and report it to the object under care, the employer, the community neighborhood committee, the police station, and the hospital. and other supervision objects, so as to realize timely rescue of the care recipients or care objects.

FIG. 6 is a schematic flowchart of a monitoring method provided by a fifth embodiment of the present application. As shown in Figure 6, the specific steps of the method include:

S601. Obtain monitoring data collected by an intelligent monitoring device.

In this step, the monitoring data includes: the first physiological data and the first behavior data of the care object, and the second physiological data and the second behavior data of the care object.

The first physiological data or the second physiological data include: heart rate, body temperature, blood pressure, blood oxygen, respiratory rate and other physiological characteristic data, and corresponding environmental characteristic data such as temperature distribution, humidity, oxygen concentration, carbon dioxide concentration, etc.

The first behavior data or the second behavior data includes: positioning position information, action features, expression features, voice features, and the like.

S602. Determine, according to the first physiological characteristic data and the preset monitoring and evaluation model, that the object under care satisfies the first preset pending abnormal condition.

S603. Determine, according to the environmental characteristic data and the preset monitoring and evaluation model, that the object under care is in a fourth abnormal state.

The implementation principles of steps S602-S603 are similar to those of steps S502 and S504, and are not repeated here.

S604. Determine the distance between the care object and the care object according to the first behavior data, the second behavior data, and the preset monitoring and evaluation model.

In this step, after it is determined that the physiological state of the object under care is abnormal, that is, it is in the fourth abnormal state, according to the positioning position information of the object under care in the first behavior data and the object of care in the second behavior data The distance between the two is calculated based on the positioning and position information, so as to help confirm whether the nursing object is near the nursing object, and the nursing object can find the physiological abnormality of the nursing object.

If the care object is attached to the care object, execute S605; otherwise, execute S612-S613.

S605. If the distance is less than the preset distance, use the preset monitoring evaluation model and the second behavior data to determine the behavior characteristics of the care object.

In this step, if it is determined that the care object is within 5 meters of the care object, whether the behavior characteristics such as the actions and expressions of the care object collected by the camera are to check the abnormal situation of the care object, or whether the care object is being monitored. Comfort or care for the person being cared for.

S606. Monitor the duration that the object under care is in the fourth abnormal state.

In this step, the monitoring center server starts timing when it confirms that the guarded object is in a physiological abnormal state, that is, a fourth abnormal state, that is, detects the duration of the fourth abnormal state.

It should be noted that this step and S604-S605 have no sequence requirement, and can be performed simultaneously.

S607. If the duration is greater than the first preset time threshold, determine whether the nursing object performs the abusive behavior on the object under care according to the action characteristics of the nursing object and the preset monitoring and evaluation model.

In this step, the duration of the fourth abnormal state of the object under care is greater than the first preset time threshold, such as 2 minutes, and the object under care is near the object under care, that is, the distance between the two is less than the preset distance. Assuming that the monitoring and evaluation model recognizes through the action characteristics of the care object, the care object has not taken any comfort or rescue action to the care object, and it can be determined that the care object ignores the care object, which is a kind of abuse, that is, neglected abuse. Step S608 is performed; or if the preset monitoring and evaluation model recognizes through the action features of the care object that the care object is beating or beating the care object, then step S608 is performed. If it is impossible to distinguish whether there is abusive behavior from the action, step S609 is executed.

S608. Send sixth prompt information to the supervision object.

In this step, for the abuse of the care object, the monitoring center server automatically collects the evidence data of the abuse, and sends a reminder message to the supervision object, such as the family member of the care object, the community neighborhood committee, the police station, the supervision institution of the welfare institution, etc. Promptly stop the abuse of care recipients.

S609 , according to the facial expression feature and/or the sound feature and the preset monitoring evaluation model, determine whether the care object abuses the care object.

In this step, when the abusive behavior cannot be distinguished through actions, the monitoring center server further uses the preset monitoring and evaluation model to determine the abusive behavior through facial expressions and/or voice characteristics, for example, whether the abusive behavior is abusive, verbal insult, Behaviors such as spitting can be aided by facial expressions and/or sounds. If it is determined that the object of care has abusive behavior, execute S611, and if it is still unable to determine, execute step S610.

S610. Determine whether the duration is greater than a second preset time threshold.

In this step, through S607 and S609, it is still impossible to determine that the behavior of the nursing object is abusive behavior, but the duration of the physiological abnormality of the nursing object is greater than the second preset time, such as 10 minutes, the behavior of the nursing object can be determined. If the rescue needs of the person under care cannot be met, S611 is directly executed in this case.

S611. Send seventh prompt information to the supervision object.

In this step, when it is confirmed that the behavior of the care object is abuse or improper care, the control center server will send a message to the supervision object, such as the family member of the care object, the community neighborhood committee, the police station, the supervision institution of the welfare institution, the animal protection organization, etc. Prompt information to ensure that the person under care receives timely assistance.

It should also be noted that when it is determined that the care object has abused behavior, a warning prompt message may also be sent to the care object's wearable monitoring device, such as a watch, to remind the care object to stop the abusive behavior.

S612. If the distance is greater than or equal to the preset distance, determine that the duration is greater than a third preset time threshold.

In this step, if the distance between the care object and the care object is greater than or equal to a preset distance such as 10m, a prompt message is first sent to the care object's wearable device, and then it is determined whether the physiological abnormal state of the care object lasts for a period of time. If the value is greater than the third preset time threshold, such as 4 minutes, if it is, it is determined that the care object has "neglected" abusive behavior toward the care object, and S613 is executed.

S613. Send eighth prompt information to the supervision object.

In this step, the eighth prompt information is used to prompt the supervision object that the care object has "neglected" abusive behavior to the care object.

It should also be noted that the data recorded in real time by the monitoring equipment will be uploaded to the database of the monitoring center, which can be used as evidence materials for the abuse of the care object or to evaluate whether the care object is working properly or whether it is good or bad. When entering the video surveillance area, the behavior of the supervised object can also be recorded.

The monitoring method provided by this embodiment, by using a preset monitoring evaluation model and according to monitoring data, evaluates whether the monitored object is properly cared for by the nursing object when the object under care has a physiological abnormality, and determines whether the object under care does not care about the object under care. Carry out abusive behavior, and if it is detected that the nursing behavior is unreasonable or there is abusive behavior, the supervision object will be notified to take timely rescue measures. It realizes the automatic monitoring and judgment of the work behavior of the care recipients, and avoids the problem that the care objects cannot receive timely assistance when they have physical diseases, or that the care objects cannot be detected and stopped in time and retain evidence when they are abused. The effect of security supervision on the object.

FIG. 7 is a schematic structural diagram of a monitoring device according to an embodiment of the present application. The monitoring device can be implemented by software, hardware or a combination of the two. As shown in FIG. 7 , the monitoring device 700 in this embodiment includes:

The acquisition module 701 is configured to acquire monitoring data collected by an intelligent monitoring device, the monitoring data includes behavior data and physiological data of an object to be monitored, and the object to be monitored includes: a nursing object and a nursing object;

a processing module 702, configured to determine the state information of the object to be monitored according to the monitoring data and a preset monitoring evaluation model;

The processing module 702 is further configured to generate a monitoring instruction according to the state information, where the monitoring instruction is used to send prompt information to the care object and/or the supervision object.

In a possible design, the monitoring data includes first behavior data of the object to be cared for, and correspondingly, the processing module 702 is configured to determine the to-be-to-be based on the monitoring data and a preset monitoring evaluation model. Status information of monitored objects, including:

The processing module 702 is configured to determine, according to the first video surveillance data in the first behavior data and the preset surveillance evaluation model, that the guarded object is not in the video surveillance area, and the first video surveillance data is: The video surveillance data of the object under care, the state information is the first abnormal state;

Correspondingly, the processing module 702 is further configured to generate a monitoring instruction according to the status information, including:

The processing module 702 is further configured to generate first prompt information for prompting the care object according to the first abnormal state.

In a possible design, the processing module 702 is configured to determine, according to the first video surveillance data in the first behavior data and the preset surveillance evaluation model, that the guarded object is not in the video surveillance area After that, also include:

The processing module 702 is further configured to: if it is determined according to the first position monitoring data in the first behavior data and the preset monitoring evaluation model that the guarded object leaves the safe activity area, the first position monitoring data is the position monitoring data of the guarded object, the safe activity area includes the video monitoring area and the non-video monitoring area, then the state information is determined as the second abnormal state, and the monitoring instruction is used to generate a prompt Describe the second prompt information of the care object;

The processing module 702 is further configured to: if it is determined according to the first position monitoring data in the first behavior data and the preset monitoring evaluation model that the guarded object has not left the safe activity area, then The state information is determined to be a third abnormal state, and the monitoring instruction is used to generate third prompt information for prompting the care object.

In a possible design, the monitoring data includes first physiological data of the monitored object, and the first physiological data includes first physiological characteristic data collected by a first wearable device and information in the safe activity zone. Environmental characteristic data collected by infrared detection equipment;

Correspondingly, the processing module 702 is further configured to determine the state information of the object to be monitored according to the monitoring data and a preset monitoring evaluation model, further comprising:

The processing module is further configured to, if it is determined according to the first physiological feature data and the preset monitoring and evaluation model that the object under care meets a first preset pending abnormal condition, then according to the environmental feature data and the The preset monitoring and evaluation model determines that the object under care is in the fourth abnormal state;

The processing module 702 is further configured to generate a monitoring instruction according to the state information, including:

The processing module 702 is further configured to generate fourth prompt information for prompting the care object and/or the supervision object according to the fourth abnormal state.

Optionally, the monitoring data further includes second physiological data of the care object, and the second physiological data includes second physiological characteristic data collected by the second wearable device and environment collected by the infrared detection device in the safe activity area. characteristic data;

Correspondingly, the processing module 702 is also used to determine the state information of the object to be monitored according to the monitoring data and a preset monitoring evaluation model, and also includes:

The processing module 702 is further configured to, if it is determined according to the second physiological characteristic data and the preset monitoring evaluation model that the care object satisfies a second preset pending abnormal condition, then according to the environmental characteristic data and the The preset monitoring and evaluation model determines that the care object is in the fifth abnormal state;

The processing module 702 is further configured to generate a monitoring instruction according to the state information, including:

The processing module 702 is further configured to generate fifth prompt information for prompting the supervised object according to the fifth abnormal state.

In a possible design, the monitoring data includes second behavior data of the care object, and correspondingly, in the processing module 702, it is further configured to monitor and evaluate the model according to the environmental feature data and the preset monitoring and evaluation model. After determining that the object under care is in the fourth abnormal state, the method further includes:

The processing module 702 is further configured to determine the distance between the object of care and the object of care according to the first behavior data, the second behavior data and the preset monitoring evaluation model;

The processing module 702 is further configured to, if the distance is less than the preset distance, use the preset monitoring evaluation model and the second behavior data to determine the behavior characteristics of the care object;

The processing module 702 is further configured to monitor the duration that the object under care is in the fourth abnormal state;

The processing module 702 is further configured to determine that the object under care is in a state of being abused if the duration is greater than a preset time threshold.

In a possible design, the second behavior data includes action features, facial expression features, and voice features, and the processing module 702 is further configured to determine that the object under care is in a state of being abused, including:

The processing module 702 is further configured to judge whether the object of care has performed the abusive behavior on the object of care according to the action feature and the preset monitoring and evaluation model, and if the judgment result is yes, send the sending the sixth prompt message by the supervision object;

The processing module 702 is further configured to, if the judgment result is no, according to the facial expression feature and/or the sound feature and the preset monitoring and evaluation model, to judge whether the care object performs the treatment on the care object. For the abuse, if the judgment result is yes, send the seventh prompt message to the supervision object;

The processing module 702 is further configured to send the seventh prompt information to the supervision object when the duration is greater than the preset time threshold if the determination result is no.

It is worth noting that the monitoring device provided by the embodiment shown in FIG. 7 can execute a monitoring method provided by any of the above method embodiments, and its specific implementation principles, technical features, explanations of technical terms, and technical effects are similar. No longer.

FIG. 8 is a schematic structural diagram of an electronic device provided by the present application. As shown in FIG. 8 , the electronic device 800 may include: at least one processor 801 and a memory 802 . FIG. 8 shows an electronic device with a processor as an example.

The memory 802 is used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions.

Memory 802 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.

The processor 801 is configured to execute the computer-executed instructions stored in the memory 802 to implement the methods described in the above method embodiments.

Wherein, the processor 801 may be a central processing unit (central processing unit, referred to as CPU), or a specific integrated circuit (application specific integrated circuit, referred to as ASIC), or is configured to implement one or more of the embodiments of the present application. multiple integrated circuits.

Optionally, the memory 802 may be independent or integrated with the processor 501 . When the memory 802 is a device independent of the processor 801, the electronic device 800 may further include:

The bus 803 is used to connect the processor 801 and the memory 802 . The bus may be an industry standard architecture (abbreviated as ISA) bus, a peripheral component (PCI) bus, or an extended industry standard architecture (EISA) bus or the like. Buses can be divided into address bus, data bus, control bus, etc., but it does not mean that there is only one bus or one type of bus.

Optionally, in terms of specific implementation, if the memory 802 and the processor 801 are integrated on one chip, the memory 802 and the processor 801 can communicate through an internal interface.

The present application also provides a computer-readable storage medium, the computer-readable storage medium may include: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM) ), a magnetic disk or an optical disk and other media that can store program codes. Specifically, the computer-readable storage medium stores program instructions, and the program instructions are used for the methods in the above embodiments.

Other embodiments of the present application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of this application that follow the general principles of this application and include common knowledge or conventional techniques in the technical field not disclosed in this application . The specification and examples are to be regarded as exemplary only, with the true scope and spirit of the application being indicated by the following claims.

It is to be understood that the present application is not limited to the precise structures described above and illustrated in the accompanying drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims (10)

1. A monitoring method, comprising:

   acquiring monitoring data collected by an intelligent monitoring device, the monitoring data includes behavior data and physiological data of an object to be monitored, and the object to be monitored includes: a nursing object and a nursing object;

   Determine the state information of the object to be monitored according to the monitoring data and a preset monitoring evaluation model;

   A monitoring instruction is generated according to the state information, and the monitoring instruction is used to send prompt information to the care object and/or the supervision object.
2. The monitoring method according to claim 1, wherein the monitoring data includes first behavior data of the object under care, and correspondingly, the monitoring data and a preset monitoring evaluation model are determined to determine the Status information of monitored objects, including:

   It is determined according to the first video surveillance data in the first behavior data and the preset surveillance evaluation model that the object under care is not in the video surveillance area, and the first video surveillance data is the video surveillance of the object under care data, the state information is the first abnormal state;

   Correspondingly, the generating a monitoring instruction according to the state information includes:

   Generate first prompt information for prompting the care object according to the first abnormal state.
3. The monitoring method according to claim 2, characterized in that, after determining that the guarded object is not in the video monitoring area according to the first video monitoring data in the first behavior data and the preset monitoring evaluation model, Also includes:

   If it is determined according to the first position monitoring data in the first behavior data and the preset monitoring evaluation model that the guarded object leaves the safe activity area, the first position monitoring data is the position monitoring of the guarded object data, the safety activity area includes the video surveillance area and the non-video surveillance area, then the state information is determined to be a second abnormal state, and the monitoring instruction is used to generate second prompt information to prompt the care object;

   If it is determined according to the first position monitoring data in the first behavior data and the preset monitoring evaluation model that the guarded object has not left the safe activity area, the state information is determined as a third abnormality state, the monitoring instruction is used to generate third prompt information for prompting the care object.
4. The monitoring method according to claim 3, wherein the monitoring data includes first physiological data of the object under care, the first physiological data includes first physiological characteristic data collected by a first wearable device, and Environmental characteristic data collected by the detection equipment in the safe activity area;

   Correspondingly, the determining the state information of the object to be monitored according to the monitoring data and the preset monitoring evaluation model further includes:

   If it is determined according to the first physiological feature data and the preset monitoring and evaluation model that the object under care meets a first preset pending abnormal condition, then the object is determined according to the environmental feature data and the preset monitoring and evaluation model. The person under care is in the fourth abnormal state;

   The generating a monitoring instruction according to the state information includes:

   Fourth prompt information for prompting the care object and/or the supervision object is generated according to the fourth abnormal state.
5. The monitoring method according to any one of claims 2-4, wherein the monitoring data further includes second physiological data of the care object, and the second physiological data includes second physiological data collected by a second wearable device characteristic data and environmental characteristic data collected by the detection equipment in the safe activity area;

   Correspondingly, the determining the state information of the object to be monitored according to the monitoring data and the preset monitoring evaluation model further includes:

   If it is determined according to the second physiological feature data and the preset monitoring evaluation model that the nursing object meets a second preset pending abnormal condition, then the nursing object is determined according to the environmental feature data and the preset monitoring evaluation model The subject is in the fifth abnormal state;

   The generating a monitoring instruction according to the state information includes:

   Fifth prompt information for prompting the supervision object is generated according to the fifth abnormal state.
6. The monitoring method according to claim 4, wherein the monitoring data includes second behavior data of the nursing object, and correspondingly, in the determining according to the environmental characteristic data and the preset monitoring evaluation model After the object under care is in the fourth abnormal state, it also includes:

   determining the distance between the object of care and the object of care according to the first behavior data, the second behavior data and the preset monitoring and evaluation model;

   If the distance is less than the preset distance, use the preset monitoring evaluation model and the second behavior data to determine the behavior characteristics of the care object;

   monitoring the duration of time that the subject is in the fourth abnormal state;

   If the duration is greater than a preset time threshold, it is determined that the subject under care is in a state of being abused.
7. monitoring method according to claim 6, is characterized in that, described second behavior data comprises: action characteristic, facial expression characteristic and sound characteristic, described determining that described object under care is in the state of being abused, comprises:

   If it is determined according to the action feature and the preset monitoring evaluation model whether the care object performs the abusive behavior on the care object, if the judgment result is yes, the sixth prompt is sent to the supervision object information;

   If the judgment result is no, then according to the facial expression feature and/or the sound feature and the preset monitoring evaluation model, it is judged whether the care object performs the abusive behavior on the care object, if the judgment result is If yes, send the seventh prompt information to the supervision object;

   If the determination result is no, when the duration is greater than the preset time threshold, the seventh prompt information is sent to the supervision object.
8. A monitoring device, characterized in that it includes:

   an acquisition module, configured to acquire monitoring data collected by the intelligent monitoring device, the monitoring data includes behavioral data and physiological data of an object to be monitored, and the object to be monitored includes: a nursing object and a nursing object;

   a processing module, configured to determine the state information of the object to be monitored according to the monitoring data and a preset monitoring evaluation model;

   The processing module is further configured to generate a monitoring instruction according to the state information, where the monitoring instruction is used to send prompt information to the care object and/or the supervision object.
9. An electronic device, comprising:

   processor; and,

   a memory for storing executable instructions for the processor;

   Wherein, the processor is configured to execute the monitoring method of any one of claims 1 to 7 by executing the executable instructions.
10. A computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the monitoring method according to any one of claims 1 to 7 is implemented.

Images