Control Method of Nursing Robot, Nursing Robot and Storage Medium

Abstract

The present invention discloses a control method for a nursing robot, a nursing robot, and a computer-readable storage medium. The method includes: determining the current working area where the nursing robot is located, and obtaining the area attribute associated with the working area; when the area attribute is a private attribute, filtering the image information corresponding to the private position of the target nursing object in the target image collected by the imaging device, where the target image includes an image of the target nursing object; determining the user state of the target nursing object according to the filtered target image. When the current working area where the nursing robot is caring is a privacy area, by filtering the image information corresponding to the private position of the target nursing object in the collected target image, the privacy of the target nursing object is protected, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the technical field of robots, and in particular, to a control method for a care robot, a care robot, and a computer-readable storage medium. Background Art

[0002] In the related art, a color camera can be installed in places where care objects such as the elderly and children often appear to realize real-time monitoring of the state of the care object, so that it can be determined whether an accident has occurred to the care object according to the state monitoring result, and then an alarm can be given in time when an accident occurs to the care object. However, in private places such as bedrooms and bathrooms, using a color camera for monitoring will cause the privacy of the care object to be leaked.

[0003] The above content is only used to assist in understanding the technical solution of the present invention, and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] Embodiments of the present application provide a control method for a care robot, a care robot, and a computer-readable storage medium, aiming to solve the technical problem that using a color camera for monitoring in private places such as bedrooms and bathrooms will cause the privacy of the monitored object to be leaked.

[0005] To achieve the above object, an embodiment of the present invention provides a control method for a care robot, and the control method for the care robot includes the following:

[0006] Determine the current working area where the care robot is located, and obtain the area attribute associated with the working area;

[0007] When the area attribute is a private attribute, filter the image information corresponding to the private position of the target care object in the target image collected by the imaging device, where the target image includes an image of the target care object;

[0008] Determine the user state of the target care object according to the filtered target image.

[0009] Optionally, the target image includes an infrared layer and a visible light layer; after the step of determining the current working area where the care robot is located and obtaining the area attribute associated with the working area, the method further includes:

[0010] When the area attribute is a public attribute, determine the brightness of the current working environment of the care robot;

[0011] When it is determined that the working environment is a low-light environment according to the brightness, determine the user state of the target care object according to the infrared layer of the target image;

[0012] When it is determined that the working environment is a bright environment according to the brightness level, the user status of the target care object is determined according to the visible light layer of the target image.

[0013] Optionally, after the step of determining the user status of the target care object according to the filtered target image, it includes:

[0014] When the user status of the target care object is a warning status, obtain the body characteristic data of the target care object collected by the intelligent wearable device, or obtain the body characteristic data of the target care object collected based on the camera device;

[0015] When the body characteristic data is not within the preset healthy range, send an alarm message.

[0016] Optionally, the target image includes a depth layer, an infrared layer and a visible light layer; the step of filtering the image information corresponding to the private position of the target care object in the target image collected by the camera device includes:

[0017] Obtain the height of the target care object in the depth layer of the target image, or the skeleton information of the target care object;

[0018] According to the height or the skeleton information, determine the coordinates of the private position of the target care object;

[0019] Based on the coordinates of the private position of the target care object, filter the image information of the private position of the target care object in the infrared layer and / or the visible light layer.

[0020] Optionally, before the step of filtering the image information corresponding to the private position of the target care object in the target image collected by the camera device, it includes:

[0021] Based on the infrared layer or the depth layer in the target image, determine the facial features and / or body type information of each object located in the target image;

[0022] If it is determined that there are children and / or the elderly among the objects according to the facial features and / or body type information of each object, then the determined children and / or the elderly are used as the target care objects.

[0023] Optionally, after the step of determining the user status of the target care object according to the filtered target image, it further includes:

[0024] According to the user status of the target care object, determine the alarm level corresponding to the target care object;

[0025] Execute corresponding nursing strategies according to the alarm level corresponding to the target cared object; among them, if the user status of the target cared object is in a normal state, determine the alarm level for the target cared object as the first level and execute the nursing strategy corresponding to the first level; if the user status of the target cared object is in a warning state, determine the alarm level for the target cared object as the second level and execute the nursing strategy corresponding to the second level; if the user status of the target cared object is in a fallen state, determine the alarm level for the target cared object as the third level and execute the nursing strategy corresponding to the third level.

[0026] Optionally, after the step of determining the user status of the target cared object according to the filtered target image, it includes:

[0027] Display the image information of the target cared object in the infrared layer or the visible light layer of the target image on the terminal.

[0028] Optionally, the step of displaying the image information of the target cared object in the infrared layer or the visible light layer of the target image on the terminal further includes:

[0029] Determine an emergency plan corresponding to the user status of the target cared object according to the user status of the target cared object;

[0030] Display the emergency plan corresponding to the user status of the target cared object on the terminal.

[0031] In addition, to achieve the above object, the present invention also provides a nursing robot, which includes: a memory, a processor, and a control program of the nursing robot stored on the memory and executable on the processor. When the control program of the nursing robot is executed by the processor, the steps of the control method of the nursing robot as described above are implemented.

[0032] In addition, to achieve the above object, the present invention also provides a computer-readable storage medium, on which a control program of a nursing robot is stored. When the control program of the nursing robot is executed by a processor, the steps of the control method of the nursing robot as described above are implemented.

[0033] A control method for a care robot, the care robot, and a computer-readable storage medium proposed by an embodiment of the present invention. By determining the current working area where the care robot is located and obtaining the area attribute associated with the working area, when the associated area attribute is a private attribute, it indicates that the current working area is a privacy area. Thus, in the target image collected by the imaging device, the image information corresponding to the private position of the target care object is filtered, where the target image includes the image of the target care object. Furthermore, the user state of the target care object is determined based on the filtered target image. When the current working area where the care robot is caring is a privacy area, by filtering the image information corresponding to the private position of the target care object in the collected target image, the privacy of the target care object is protected, and the user experience is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic flowchart of an embodiment of the control method for the care robot of the present invention;

[0035] Figure 2 It is a detailed flowchart of step S10 in the second embodiment of the control method for the care robot of the present invention;

[0036] Figure 3 It is a detailed flowchart of step S20 in the third embodiment of the control method for the care robot of the present invention;

[0037] Figure 4 It is a detailed flowchart of step S30 in the fourth embodiment of the control method for the care robot of the present invention;

[0038] Figure 5 It is a schematic diagram of the terminal structure of the hardware operating environment involved in the embodiment solution of the present invention.

[0039] The implementation, functional features, and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. To better understand the above technical solutions, the exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0041] Refer to Figure 1, in an embodiment of the control method of the care robot of the present invention, the control method of the care robot includes the following steps:

[0042] Step S10: Determine the working area where the care robot is currently located, and obtain the area attributes associated with the working area;

[0043] In this embodiment, the care robot includes a camera device. The user state of the target care object can be detected based on the target image collected by the camera device. To protect the privacy of the target care object, when the working area where the robot is located is a privacy area, the image information of the private position of the target care object in the collected target image can be filtered. Therefore, different area attributes can be set according to the privacy level of different working areas. When the working area where the robot is currently located is determined, the area attributes associated with this working area can be obtained, and then it can be determined whether the collected target image needs to be filtered according to the obtained area attributes. The working area where the robot is currently located can be determined through the target image collected by the camera device, or by positioning the current position of the robot to determine the working area where the care robot is currently located.

[0044] Step S20: When the area attribute is a private attribute, filter the image information corresponding to the private position of the target care object in the target image collected by the camera device, where the target image includes the image of the target care object;

[0045] In this embodiment, the target image collected by the camera device includes a depth layer, an infrared layer, and a visible light layer. The robot can use the corresponding layer based on different requirements and scenarios to care for the target care object, thereby improving the quality of care. When the area attribute associated with the working area where the care robot is currently located is a private attribute, it indicates that the current working area is a privacy area, such as a bathroom, a shower room, etc. To protect the privacy of the target care object, the image information corresponding to the private position of the target care object in the collected target image needs to be filtered. At this time, the depth layer in the target image can be obtained, and the depth data in the depth layer can be converted into point cloud data, so as to obtain the coordinates of the private position of the target care object based on the point cloud data, and filter the image information corresponding to the private position of the target care object in the target image based on the coordinates of this private position. For example, if the image information above the knees of the target care object needs to be filtered, the position coordinates of the knees of the target care object in the collected target image need to be determined first, and then the image information with coordinates above the knees of the target care object in the collected target image can be filtered. In some embodiments, the camera device can be a depth camera, and a depth image is collected through the depth camera, and then the private position of the target care object is filtered based on the collected depth image.

[0046] It can be understood that the private location can be various body parts of the target care recipient, such as the knees, head, etc. Multiple private locations can be set to filter the corresponding sensitive areas on the body of the target care recipient.

[0047] Optionally, since the positions of various parts of the human body to the heels can be calculated based on the height algorithm. For example, if the human height is 160 cm, then the height from the heels to the knees is 48 cm. Therefore, the height of the target care recipient in the depth layer of the target image can be obtained first, and then the coordinates of the private location of the target care recipient can be determined based on the height, so as to filter the image information of the private location of the target care recipient in the infrared layer and / or visible light layer based on the coordinates of the private location of the target care recipient.

[0048] Optionally, in another embodiment, the skeleton information of the target care recipient in the depth layer of the target image is obtained, and then the coordinates of the private location of the target care recipient are determined based on the obtained skeleton information, so as to filter the image information of the private location of the target care recipient in the infrared layer and / or visible light layer based on the coordinates of the private location of the target care recipient. When it comes to private attributes, the sensitive information of the private location in the target care recipient can be efficiently and reliably filtered based on the spatial coordinate information, which can better protect the privacy of the target care recipient.

[0049] Exemplarily, when the care robot is caring for the target care recipient, it first determines the current working area. When it determines that the working area is the bathroom, it obtains the area attribute associated with the bathroom. When the associated area attribute is a private attribute, it obtains the height or skeleton information of the target care recipient in the depth layer of the target image. When the height of the target care recipient obtained is 160 cm, the height from the heels to the knees is calculated as 48 cm according to the height algorithm, so as to determine the position of the knees of the target care recipient, or determine the skeleton corresponding to the knees of the target care recipient by obtaining the skeleton information, and then determine the position coordinates of the knees based on the skeleton corresponding to the knees. Furthermore, based on the determined position coordinates of the knees, the image information of the private location of the target care recipient in the infrared layer and / or visible light layer is filtered, so that the private location of the target care recipient in the finally output image has been filtered, achieving the effect of protecting the privacy of the target care recipient.

[0050] Step S30: Determine the user state of the target care recipient according to the filtered target image.

[0051] In this embodiment, the user state of the target care object is determined according to the target image. The user state includes a warning state, a fall state, and a normal state. When it is detected that the user state of the target care object is the fall state, an alarm message can be directly sent. When it is detected that the time for the target care object to maintain a fixed posture is greater than or equal to the preset time, it indicates that the target care object may be in a coma state, and the user state of the target care object is marked as the warning state. At this time, in order to determine whether the target care object is actually in a coma state and avoid false alarms, by obtaining the body characteristic data of the target care object collected by the smart wearable device, or obtaining the body characteristic data of the target care object collected based on the camera device, when the body characteristic data is not within the preset healthy range, it indicates that the target care object is actually in a coma state, and then an alarm message is sent. The smart wearable device can be a bracelet, a watch, etc. suitable for carrying around, and is used to collect the body characteristic data of the target care object in real time. For example, the blood pressure, heart rate, blood oxygen saturation, etc. of the target care object are collected in real time.

[0052] In some embodiments, the user state can be the behavioral actions made by the target care object or the area where the target care object is located. For example, the guardian can set corresponding risk behaviors or risk areas according to the target care object. When it is detected that the target care object makes the risk behavior or enters the risk area, an alarm message can be directly sent as a warning and to enable the guardian to know in time and stop it.

[0053] Optionally, since there are certain differences between the body characteristic data such as blood pressure, heart rate, and blood oxygen saturation of the elderly and those of healthy young people, following ordinary standards will lead to frequent false alarms. Therefore, a physical examination can be performed on the care object. After the physical examination, authorized professionals set the preset healthy range corresponding to the appropriate body characteristic data according to the physical examination results of the care object, and the set preset healthy range cannot be changed by the user and must be changed by professionals to avoid the target care object triggering changes during daily activities and resulting in frequent false alarms. When it is detected that the body characteristic data of the target care object is not within the preset healthy range, an alarm message is sent.

[0054] Optionally, in still some other embodiments, the body characteristic data of the target care object can be obtained based on the camera device configured on the care robot. By providing a heart rate detection function with an adjacent flash and camera device, when the user state of the target care object is in the warning state, the care robot prompts the target care object to place the hand on the front close to the flash and the camera through voice, so as to detect the heart rate of the target care object through the flash and the camera device, and detect the body temperature of the target care object according to the infrared layer in the collected target image. When the heart rate and body temperature of the target care object are not within the preset healthy range, it indicates that the target care object is actually in a coma state, and then an alarm message is sent.

[0055] Exemplarily, after a physical examination of the target care recipient, a preset health range corresponding to appropriate physical characteristic data is set by a doctor or under the guidance of a doctor. When the care robot is caring for the target care recipient, it first determines the current working area. When the working area is the bathroom, the associated attribute of the bathroom is obtained as a private attribute. Then, the height or skeleton information of the target care recipient in the depth layer of the target image is obtained. When the height of the target care recipient obtained is 160 cm, the height from the heel to the knee is calculated to be 48 cm according to the height algorithm, thereby determining the position coordinates of the target care recipient's knee. Or, the skeleton corresponding to the target care recipient's knee is determined through the obtained skeleton information, thereby determining the position coordinates of the knee. Then, based on the determined position coordinates of the knee, the image information of the private position of the target care recipient in the infrared layer and / or visible light layer is filtered, so that the private position of the target care recipient in the finally output image is filtered, achieving the effect of protecting the privacy of the target care recipient. After that, the user state of the target care recipient is determined according to the filtered target image. When the time for the target care recipient to maintain a fixed posture is greater than or equal to the preset duration, it indicates that the target care recipient may be in a coma state. Then, the user state of the target care recipient is marked as a warning state. At this time, to avoid false alarms, the physical characteristic data of the target care recipient collected by the intelligent wearable device is further obtained, or the physical characteristic data of the target care recipient is collected outside the body based on the camera device, to determine whether the collected physical characteristic data is within the set preset health range. If it is not within the preset health range, it indicates that the target care recipient is actually in a coma state, and then an alarm message is sent to the guardian or the hospital to seek help.

[0056] In the technical solution provided in this embodiment, the current working area of the care robot is determined, and the area attribute associated with the working area is obtained. When the area attribute associated with the working area is a private attribute, the height of the target care recipient in the depth layer of the target image or the skeleton information of the target care recipient is obtained. Then, according to the height or skeleton information, the coordinates of the private position of the target care recipient are determined, so as to filter the image information of the private position of the target care recipient in the infrared layer and / or visible light layer based on the coordinates of the private position of the target care recipient, achieving the effect of protecting the privacy of the target care recipient and improving the user experience. After that, the user state of the target care recipient is determined according to the filtered target image. When the user state of the target care recipient is in a warning state, to avoid false alarms, the physical characteristic data collected by the intelligent wearable device is further obtained, or the physical characteristic data collected by the camera device is used. When the physical characteristic data of the target care recipient is not within the preset health range, an alarm message is sent, achieving the effect of timely alarming.

[0057] Refer to Figure 2, in the second embodiment, based on the first embodiment, after the step S10, it includes:

[0058] Step S40: When the area attribute is a public attribute, determine the brightness level of the working environment where the care robot is currently located;

[0059] In this embodiment, when the area attribute associated with the working area where the care robot is currently located is a public attribute, it indicates that the current working area is a public area, such as a hall, a balcony, etc., and there is no need to filter the private positions of the target care objects in the collected target images. In order to better care for the target care objects, different layers can be used to detect the user status of the target care objects in different environments, so as to improve the quality of care.

[0060] Optionally, the light intensity value of the working environment where the care robot is currently located can be obtained, and the brightness level of the working environment can be determined according to the obtained light intensity value. Furthermore, it can be judged whether the working environment where the care robot is currently located is a low-light environment or a bright-light environment according to the brightness level, so as to collect different images according to different environments.

[0061] Step S50: When it is determined that the working environment is a low-light environment according to the brightness level, determine the user status of the target care object according to the infrared layer of the target image;

[0062] In this embodiment, according to the brightness level of the working environment where the care robot is currently located, it is determined which layer is used to detect the target care object, so that the detected user status is more accurate. Since in a low-light environment, the resolution of the depth layer in the collected target image is too low to detect the target care object or the detection accuracy is low, when in a low-light environment, the infrared layer of the target image can be used to detect the target care object, so as to accurately detect the user status of the target care object, so that when the target care object is in a warning state or a falling state, it can be discovered and alarmed in time.

[0063] Step S60: When it is determined that the working environment is a bright-light environment according to the brightness level, determine the user status of the target care object according to the visible light layer of the target image.

[0064] In this embodiment, since in a bright-light environment, the infrared layer in the collected target image will be exposed, making it difficult to detect the user status of the target care object. Therefore, in a bright-light environment, the visible light layer of the target image can be used to detect the target care object to ensure that the user status of the target care object is accurately determined. Furthermore, when the target care object is in a warning state or a falling state, it can be discovered and alarmed in time.

[0065] Optionally, the user status can be the physical status of the target care recipient, such as coma, fall, etc., or the behavioral actions taken by the target care recipient, or the area where the target care recipient is located. Since the physical conditions of different care recipients are different, corresponding risk behaviors and / or risk areas can be set according to the physical condition of the target care recipient. When the target care recipient performs a risk behavior and / or enters a risk area, it indicates that the user status of the target care recipient is in a warning state, and an alarm message can be directly sent to the guardian and the target care recipient. The form of sending the alarm message can be to output voice to remind the target care recipient, and send the collected target image to the guardian so that the guardian can know, thus achieving the effect of timely alarm.

[0066] Exemplarily, a target care recipient suffering from Alzheimer's disease especially needs to pay attention to monitoring abnormal behaviors. Therefore, specific risk areas and / or risk behaviors can be set. When the target care recipient approaches a risk area such as a kitchen stove and / or performs risk behaviors such as climbing a ladder or going out alone, the user status of the target care recipient is marked as a warning state, and then a reminder voice is output to remind the target care recipient and notify the caregiver. For disabled people, safe areas and risk areas can be set according to their behavioral abilities. When entering a risk area, the user status of the target care recipient is marked as a warning state, and then a voice is output to remind the target care recipient and notify the guardian, achieving the effect of timely alarm and improving the user experience.

[0067] Optionally, obstacle avoidance can be performed based on a camera device. Since the care robot moves with the movement of the target care recipient during care, the distance between the care robot and the target care recipient can be determined through the target image collected by the camera device, so that the care robot can maintain an appropriate distance from the target care recipient to avoid collision or tripping. When the target care recipient exceeds the monitoring range of the camera device, the moving direction is predicted according to the moving speed of the target care recipient for continuous tracking. When it is detected that the current user status of the target care recipient is in a fallen state, a preset voice can be broadcast for reminder, and the response of the target care recipient is recorded, and an alarm message is sent to the guardian or the hospital. If a network anomaly occurs, resulting in the failure of the alarm message to be sent externally, or there is no response from the target or feedback from the caregiver, the speaker can be adjusted to the maximum volume to emit an alarm sound.

[0068] In the technical solution provided in this embodiment, when it is determined that the area attribute associated with the current working area of the care robot is a public attribute, it indicates that the current working area is a public area, and there is no need to filter the image information of the private positions of the target care objects in the target image. Then, by determining the brightness of the current working environment of the care robot, when it is determined that the working environment is a low-light environment based on the brightness, the user status of the target care object is determined according to the infrared layer of the target image. When it is determined that the working environment is a bright-light environment based on the brightness, the user status of the target care object is determined according to the visible light layer of the target image. By determining the brightness of the current working environment of the care robot, the corresponding layer in the target image is obtained in different environments to determine the user status of the target care object, achieving the effect of improving the care quality.

[0069] Referring to Figure 3 , in the third embodiment, based on any of the above embodiments, before step S20, it includes:

[0070] Step S70: Based on the infrared layer or depth layer in the target image, determine the facial features and / or body shape information of each object located in the target image;

[0071] Step S80: If it is determined that there are objects that are children and / or the elderly according to the facial features and / or body shape information of each object, then the determined children and / or the elderly are used as the target care objects.

[0072] In this embodiment, the care robot can care for multiple care objects at the same time, and the care objects can be the elderly and / or children. After the imaging device captures the target image, based on the infrared layer in the target image, the facial features and body shape information of each object in the target image can be determined. Then, according to the facial features and body shape information of each object, the elderly and children in the current working area are determined. Thus, after identifying the elderly and children, the elderly and children are used as target care objects and tracked and cared for in real time.

[0073] In some embodiments, the body shape information of each object can be determined based on the depth layer in the target image. Thus, the children in the current working area are determined according to the body shape information, or the depth layer data is converted into point cloud data to determine the skeleton information of each object. Then, the elderly and children in the current working area are determined according to the skeleton information.

[0074] Optionally, to improve the quality of care, the target care recipient can be determined based on the behavior habits of each care recipient at different time periods, the user status of each care recipient, and / or the priority of each care recipient, so as to preferentially monitor the care recipients in need without affecting the monitoring of other care recipients. The priority of each care recipient can be freely set by the user according to the actual situation. For example, when the user status of a care recipient has been in a normal state for a period of time, other care recipients can be preferentially monitored. For example, when the elderly are resting or have been in a normal state for a period of time, children in a warning state can be preferentially monitored. Of course, when space permits, a location that can monitor multiple care recipients simultaneously can be preferentially selected to monitor multiple care recipients at the same time.

[0075] It can be understood that the care robot or the server can pre-store the priorities corresponding to each care recipient, so that the care robot can obtain the priorities corresponding to each pre-stored care recipient or the priorities corresponding to each care recipient stored in the server to determine the target care recipient. The priorities corresponding to each care recipient at different time periods or different user states can be different, and this embodiment does not make specific limitations on this.

[0076] Optionally, the guardian can pre-register the care recipients to be monitored and collect and store the facial features and / or body type information of each care recipient through a camera device. Thus, when the care robot is monitoring, it compares the facial features and / or body type information of each object in the collected image with the pre-stored facial feature set and body type information set to determine each care recipient.

[0077] Optionally, in this embodiment, different treatments can be performed for different user states of care recipients to achieve different care tasks. For example, when the target care recipient is an infant, music can be played to soothe it when it cries. When the target care recipient is an elderly person, corresponding reminder voices can be output for admonition when they fall or perform risky behaviors. Care recipients can be not only the elderly and children, but also pets, etc., and the guardian can determine the care recipients to be monitored.

[0078] Exemplarily, when the target care object is an infant, if the cry of the infant is detected, it indicates that the current user state of the infant is the warning state. At this time, music can be played through the speaker and the cradle can be shaken for comfort, and the current user state of the infant is recorded and a video is taken, and then the recorded user state and video are sent to the terminal for the guardian to know. After knowing, the guardian can make a voice connection and go to the scene while soothing by voice. When the target care object is a domestic pet, if it is detected that the pet escapes from the door or window, it indicates the warning state, the user is reminded in time, and the picture is recorded and stored locally or uploaded to the cloud for the user to retrieve and view. When the infant or pet is alone at home without the company of adults, when a stranger enters, an alarm message is immediately sent to notify the guardian, a preset voice is broadcast for deterrence, and the elderly and children are notified through smart wearable devices such as bracelets to avoid and hide in the room.

[0079] In the technical solution provided in this embodiment, in the target image collected by the imaging device, before filtering the image information corresponding to the private position of the target care object, based on the infrared layer or depth layer in the target image, the facial features and / or body shape information of each object located in the target image are determined. If it is determined that there are children and / or the elderly among the objects according to the facial features and / or body shape information of each object, the determined children and / or the elderly are used as the target care objects to realize the care of multiple care objects, achieving the effects of improving the care efficiency and enhancing the user experience.

[0080] Refer to Figure 4 , in the fourth embodiment, based on any of the above embodiments, after step S30, it further includes:

[0081] Step S90: Determine the alarm level corresponding to the target care object according to the user state of the target care object;

[0082] Step S100: Execute the corresponding care strategy according to the alarm level corresponding to the target care object; wherein, if the user state of the target care object is the normal state, the alarm level for the target care object is determined to be the first level, and the care strategy corresponding to the first level is executed; if the user state of the target care object is the warning state, the alarm level for the target care object is determined to be the second level, and the care strategy corresponding to the second level is executed; if the user state of the target care object is the fall state, the alarm level for the target care object is determined to be the third level, and the care strategy corresponding to the third level is executed.

[0083] In this embodiment, the corresponding alarm level can be determined according to the user status of the target cared-for object, and then the corresponding care strategy can be executed according to the alarm level corresponding to the target cared-for object, so as to achieve effective care for the target cared-for object. And when there are multiple target cared-for objects, targeted care can be realized. The care strategies corresponding to each alarm level can be formulated according to actual needs, or according to the physical conditions and behavior habits of the target cared-for object.

[0084] Optionally, after determining the user status of the target cared-for object according to the filtered target image, the image information of the target cared-for object in the infrared layer or visible light layer of the target image can be displayed on the terminal. So that the guardian and / or the hospital can timely know the user status of the target cared-for object.

[0085] Optionally, the step of displaying the image information of the target cared-for object in the infrared layer or visible light layer of the target image on the terminal further includes: determining an emergency plan corresponding to the user status of the target cared-for object according to the user status of the target cared-for object, and then displaying the emergency plan corresponding to the user status of the target cared-for object on the terminal, so that the guardian can provide assistance according to the emergency plan.

[0086] Exemplarily, when it is detected that the current user status of the target cared-for object is the normal status and the alarm level corresponding to the target cared-for object is determined to be the first level, the user status of the target cared-for object can be detected based on a preset interval time, and the care strategy of preferentially caring for other target cared-for objects in the early warning state or the falling state can be executed. When it is detected that the current user status of the target cared-for object is the early warning state and the alarm level corresponding to the target cared-for object is determined to be the second level, the body feature data of the target cared-for object collected by the smart wearable device can be obtained, or the body feature data of the target cared-for object collected based on the camera device. When the body feature data is not within the preset healthy range, an alarm message is sent to the caregiver and / or the hospital, and the image information of the target cared-for object in the infrared layer or the visible light layer of the target image is sent to the terminal and displayed, so that the caregiver and / or the hospital can formulate a rescue plan in advance according to the displayed image information, and thus, timely treatment can be carried out when arriving at the scene. When the body feature data is within the preset healthy range, the care robot can be controlled to output voice to ask about the condition of the target cared-for object. According to the response of the target cared-for object, it is determined whether an alarm message needs to be sent. If no alarm message is needed, it indicates that the target cared-for object is in the normal status, and the current early warning state is changed to the normal status, and thus, the care strategy corresponding to the normal user status is executed. When it is detected that the target cared-for object is in the falling state and the alarm level corresponding to the target cared-for object is determined to be the third level, the facial expression and body state of the current target cared-for object can be obtained through the camera device, and voice is output to ask the target cared-for object, and the response is recorded. Thus, according to the facial expression, the body state and the response of the target cared-for object, the injury condition of the target cared-for object is determined, and further, the image information of the target cared-for object in the infrared layer or the visible light layer of the collected target image and the injury condition of the target cared-for object are sent to the terminal and displayed, so that the caregiver and / or the hospital can carry out rescue in time.

[0087] In the technical solution provided in this embodiment, by determining the alarm level corresponding to the target cared-for object according to the user status of the target cared-for object, and executing the corresponding care strategy according to the alarm level corresponding to the target cared-for object. Among them, if the user status of the target cared-for object is the normal status, the alarm level for the target cared-for object is determined to be the first level, and the care strategy corresponding to the first level is executed. If the user status of the target cared-for object is the early warning state, the alarm level for the target cared-for object is determined to be the second level, and the care strategy corresponding to the second level is executed. If the user status of the target cared-for object is the falling state, the alarm level for the target cared-for object is determined to be the third level, and the care strategy corresponding to the third level is executed, so as to achieve effective care for the target cared-for object. And when there are multiple target cared-for objects, targeted care can also be realized.

[0088] Refer to Figure 5 , Figure 5 which is a schematic diagram of the terminal structure of the hardware operating environment involved in the solution of the embodiment of the present invention.

[0089] The terminal in the embodiment of the present invention may be a nursing robot.

[0090] As Figure 5 shown, the terminal may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), etc. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may optionally also be a storage device independent of the aforementioned processor 1001.

[0091] Those skilled in the art can understand that Figure 5 the terminal structure shown in does not constitute a limitation on the terminal, and may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0092] As Figure 5 shown, the memory 1005, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a control program for the nursing robot.

[0093] In Figure 5 the terminal shown, the network interface 1004 is mainly used to connect to the background server and communicate with the background server for data; the processor 1001 may be used to call the control program for the nursing robot stored in the memory 1005 and perform the following operations:

[0094] Determine the working area where the nursing robot is currently located, and obtain the area attributes associated with the working area;

[0095] When the area attribute is a private attribute, filter the image information corresponding to the private position of the target care object in the target image collected by the imaging device, where the target image includes an image of the target care object;

[0096] Determine the user status of the target care object according to the filtered target image.

[0097] Further, the processor 1001 may call the control program of the care robot stored in the memory 1005 and further perform the following operations:

[0098] After the step of determining the working area where the care robot is currently located and obtaining the area attributes associated with the working area, the following steps are further included:

[0099] When the area attribute is a public attribute, determine the brightness level of the working environment where the care robot is currently located;

[0100] When it is determined that the working environment is a low-light environment based on the brightness level, determine the user state of the target care object according to the infrared layer of the target image;

[0101] When it is determined that the working environment is a bright-light environment based on the brightness level, determine the user state of the target care object according to the visible light layer of the target image.

[0102] Further, the processor 1001 may call the control program of the care robot stored in the memory 1005 and further perform the following operations:

[0103] When the user state of the target care object is a warning state, obtain the body feature data of the target care object collected by the smart wearable device, or obtain the body feature data of the target care object collected based on the imaging device;

[0104] When the body feature data is not within the preset healthy range, send an alarm message.

[0105] Further, the processor 1001 may call the control program of the care robot stored in the memory 1005 and further perform the following operations:

[0106] Obtain the height of the target care object in the depth layer of the target image, or the skeleton information of the target care object;

[0107] Determine the coordinates of the private position of the target care object according to the height or the skeleton information;

[0108] Based on the coordinates of the private position of the target care object, filter the image information of the private position of the target care object in the infrared layer and / or the visible light layer.

[0109] Further, the processor 1001 may call the control program of the care robot stored in the memory 1005 and further perform the following operations:

[0110] Based on the infrared layer or depth layer in the target image, determine the facial features and / or body type information of each object located in the target image;

[0111] If it is determined that there are children and / or the elderly among the objects based on the facial features and / or body type information of each object, then the determined children and / or the elderly are used as the target care objects.

[0112] Furthermore, the processor 1001 can call the control program of the care robot stored in the memory 1005 and also perform the following operations:

[0113] Determine the alarm level corresponding to the target care object according to the user status of the target care object;

[0114] Execute the corresponding care strategy according to the alarm level corresponding to the target care object; among them, if the user status of the target care object is in a normal state, then determine the alarm level for the target care object as the first level and execute the care strategy corresponding to the first level; if the user status of the target care object is in a warning state, then determine the alarm level for the target care object as the second level and execute the care strategy corresponding to the second level; if the user status of the target care object is in a fallen state, then determine the alarm level for the target care object as the third level and execute the care strategy corresponding to the third level.

[0115] Furthermore, the processor 1001 can call the control program of the care robot stored in the memory 1005 and also perform the following operations:

[0116] Display the image information of the target care object in the infrared layer or the visible light layer of the target image on the terminal.

[0117] Furthermore, the processor 1001 can call the control program of the care robot stored in the memory 1005 and also perform the following operations:

[0118] Determine the emergency plan corresponding to the user status of the target care object according to the user status of the target care object;

[0119] Display the emergency plan corresponding to the user status of the target care object on the terminal.

[0120] In addition, to achieve the above object, the present invention also provides a care robot, the care robot includes: a memory, a processor, and a control program of the care robot stored on the memory and executable on the processor, and when the control program of the care robot is executed by the processor, the steps of the control method of the care robot as described above are implemented.

[0121] In addition, to achieve the above object, the present invention further provides a computer-readable storage medium, on which a control program of a nursing robot is stored. When the control program of the nursing robot is executed by a processor, the steps of the control method of the nursing robot as described above are implemented.

[0122] It should be noted that, in this article, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or system including that element.

[0123] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0124] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium as described above (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to enable a terminal device (which may be a nursing robot) to execute the methods described in various embodiments of the present invention.

[0125] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the specification and drawings of the present invention, or directly or indirectly applied to other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A control method for a nursing robot, characterized in that, Applied to a care robot, the care robot includes a camera device, and the method includes: Determine the current working area where the care robot is located, and obtain the area attributes associated with the working area; When the area attribute is a private attribute, in the target image collected by the camera device, filter the image information corresponding to the private position of the target care object, including: obtaining the height of the target care object in the depth layer of the target image, or the skeleton information of the target care object; according to the height or the skeleton information, determine the coordinates of the private position of the target care object; based on the coordinates of the private position of the target care object, filter the image information of the private position of the target care object in the infrared layer and / or the visible light layer, where the target image includes an image of the target care object, and the target image includes a depth layer, an infrared layer, and a visible light layer; Determine the user status of the target care object according to the filtered target image.

2. The method according to claim 1, characterized in that, The target image includes an infrared layer and a visible light layer; After the step of determining the current working area where the care robot is located and obtaining the area attributes associated with the working area, it further includes: When the area attribute is a public attribute, determine the brightness of the current working environment of the care robot; When it is determined that the working environment is a low-light environment according to the brightness, determine the user status of the target care object according to the infrared layer of the target image; When it is determined that the working environment is a bright-light environment according to the brightness, determine the user status of the target care object according to the visible light layer of the target image.

3. The method according to any one of claims 1 or 2, characterized in that, After the step of determining the user status of the target care object according to the filtered target image, it includes: When the user status of the target care object is a warning status, obtain the body feature data of the target care object collected by the smart wearable device, or obtain the body feature data of the target care object based on the image collected by the camera device; When the body feature data is not within the preset healthy range, send an alarm message.

4. The method according to claim 1, wherein Before the step of filtering the image information corresponding to the private position of the target care object in the target image collected by the camera device, it includes: Based on the infrared layer or the depth layer in the target image, determine the facial features and / or body type information of each object located in the target image; If it is determined that there are children and / or the elderly among the objects according to the facial features and / or body type information of each object, then take the determined children and / or the elderly as the target care object.

5. The method according to claim 1, wherein After the step of determining the user status of the target care object according to the filtered target image, it further includes: Determine the alarm level corresponding to the target care object according to the user status of the target care object; Execute corresponding nursing strategies according to the alarm levels corresponding to the target cared object; among them, if the user status of the target cared object is in a normal state, determine that the alarm level for the target cared object is the first level and execute the nursing strategy corresponding to the first level; if the user status of the target cared object is in a warning state, determine that the alarm level for the target cared object is the second level and execute the nursing strategy corresponding to the second level; if the user status of the target cared object is in a fallen state, determine that the alarm level for the target cared object is the third level and execute the nursing strategy corresponding to the third level.

6. The method according to claim 1, characterized in that, After the step of determining the user status of the target cared object according to the filtered target image, it includes: Display the image information of the target cared object in the infrared layer or the visible light layer of the target image on the terminal.

7. The method according to claim 6, wherein The step of displaying the image information of the target cared object in the infrared layer or the visible light layer of the target image on the terminal includes: Determine an emergency plan corresponding to the user status of the target cared object according to the user status of the target cared object; Display the emergency plan corresponding to the user status of the target cared object on the terminal.

8. A nursing robot, characterized in that, The nursing robot includes: a memory, a processor, and a control program of the nursing robot stored on the memory and executable on the processor. When the control program of the nursing robot is executed by the processor, the steps of the control method of the nursing robot according to any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium, characterized in that, A control program of a nursing robot is stored on the computer-readable storage medium. When the control program of the nursing robot is executed by a processor, the steps of the control method of the nursing robot according to any one of claims 1 to 7 are implemented.

Images