Robot-based nursing method and system, electronic equipment and storage medium

Abstract

The invention discloses a nursing method and system based on a robot, electronic equipment and a storage medium, and relates to the technical field of robots. Body index data of a target person is obtained through the robot, and the body state of the target person is predicted through the body index data; a management plan of the target person is made according to the body state prediction result, and nursing suggestions are given according to the management plan and daily real-time behaviors of the target person. It can be understood that the technical scheme that the robot replaces manual nursing of the target personnel is achieved, the social nursing strength is enhanced, meanwhile, compared with manual nursing (nursing workers), the quality depends on the subjective consciousness of the nursing personnel, good nursing quality can be guaranteed through nursing of the robot, and the nursing efficiency is improved. Therefore, the requirements of current social development are met.

Description

Technical Field

[0001] The present application relates to the field of robotics technology, and in particular to a robot-based nursing method, system, electronic device, and storage medium. Background Art

[0002] With the development of the aging trend, the ranks of the elderly population are constantly growing, while the proportion of the labor force in the social structure is also declining. In this situation of one increase and the other decrease, there is a shortage of care for the elderly. Among them, the need for care is particularly obvious for some elderly people with underlying diseases. Taking diabetes as an example, diabetic patients require relatively stricter health management, such as strict control of diet, management of blood pressure and blood sugar, reasonable arrangement of daily routines, and taking medicine on time. Therefore, it is particularly important to have sufficient care for improving the condition of diabetic patients. It should be noted that in addition to underlying diseases, the elderly themselves also need care, but currently they mainly rely on manual care (for example, caregivers or family members), which results in insufficient social care.

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

[0004] The main purpose of this application is to provide a robot-based care method, system, electronic device and storage medium, aiming to solve the technical problem of insufficient social care force.

[0005] To achieve the above objectives, the present application proposes a robot-based care method, which includes:

[0006] Acquiring physical indicator data of a target person through a robot, and obtaining a physical condition prediction result of the target person based on the physical indicator data and a preset condition prediction model;

[0007] generating a real-time management plan for the target person based on the physical condition prediction result;

[0008] Outputting care recommendations based on the real-time management plan and the real-time behavior of the target person.

[0009] Optionally, the robot is provided with a blood pressure detection unit, a blood sugar detection unit, a heart rate detection unit, and a blood oxygen saturation detection unit, and the step of obtaining the target person's physical indicator data through the robot includes:

[0010] Acquiring the blood pressure data of the target person through the blood pressure detection unit, acquiring the blood sugar data of the target person through the blood sugar detection unit, acquiring the heart rate data of the target person through the heart rate detection unit, and acquiring the blood oxygen data of the target person through the blood oxygen saturation detection unit;

[0011] using the blood pressure data, the blood sugar data, the heart rate data, and the blood oxygen data as body index data;

[0012] The physical indicator data and the physical condition data of the target person are input into a preset state prediction model to obtain the physical state prediction result.

[0013] Optionally, the real-time management plan includes at least one time node and a node event corresponding to the time node, and the step of outputting care suggestions based on the real-time management plan and the real-time behavior of the target person includes:

[0014] When the current time reaches the time node, the real-time behavior of the target person is obtained by the robot;

[0015] When the real-time behavior is different from the node event, the care suggestion is generated according to the node event and a preset large language model, and the care suggestion is output through the robot.

[0016] Optionally, the step of obtaining the real-time behavior of the target person by the robot includes:

[0017] Acquire a scene image of the scene in which the robot is located through a camera on the robot;

[0018] determining a candidate region in the scene image based on a difference between the scene image and a preset priori image, wherein the preset priori image is an image obtained when no person exists in the scene;

[0019] Performing person recognition in the candidate area, and obtaining video data of the target person when the target person is recognized;

[0020] The video data is subjected to behavior recognition using a preset behavior recognition model to obtain the real-time behavior of the target person.

[0021] Optionally, after the step of performing personnel recognition on the candidate area, the method further includes:

[0022] If the target person is not identified, changing the position of the robot in the scene, and returning to the step of acquiring a scene image of the scene in which the robot is located through the camera on the robot based on the changed position of the robot; or

[0023] If the target person is not identified, the scene in which the robot is located is changed, and based on the new scene, the step of obtaining the scene image of the robot in the scene through the camera on the robot is returned to.

[0024] Optionally, the physical state prediction result includes each state type and the probability of each state type, and the step of generating the real-time management plan for the target person according to the physical state prediction result includes:

[0025] The state type with the highest probability among the state types is taken as the target type;

[0026] Determining a basic management plan for the target personnel based on the target type;

[0027] If the historical target type corresponding to the historical physical condition prediction result obtained at the previous monitoring time point is the same as the target type, determining the health development trend of the target person based on the difference between the historical physical condition prediction result and the physical condition prediction result;

[0028] The basic management plan is adjusted according to the health development trend to obtain the real-time management plan.

[0029] Optionally, the step of adjusting the basic management plan according to the health development trend to obtain the real-time management plan includes:

[0030] When the health development trend is deteriorating, adjusting the item parameters of the preset node items in the basic management plan toward a preset first direction;

[0031] When the health development trend is improving, the item parameters of the preset node items in the basic management plan are adjusted toward a preset second direction, wherein the preset first direction and the preset second direction are opposite.

[0032] Optionally, the robot-based nursing system includes:

[0033] A monitoring module is used to obtain physical indicator data of a target person through a robot, and obtain a physical condition prediction result of the target person based on the physical indicator data and a preset condition prediction model;

[0034] A management module, configured to generate a real-time management plan for the target person based on the physical condition prediction result;

[0035] The care module is used to output care suggestions based on the real-time management plan and the real-time behavior of the target person.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes an electronic device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is configured to implement the steps of the robot-based care method as described above.

[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the robot-based care method as described above are implemented.

[0038] In addition, to achieve the above-mentioned objectives, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the robot-based care method as described above.

[0039] One or more technical solutions proposed in this application have at least the following technical effects:

[0040] In an embodiment of the present application, a robot obtains the physical index data of a target person, and based on the physical index data and a preset state prediction model, obtains a physical state prediction result of the target person; based on the physical state prediction result, a real-time management plan for the target person is generated; and based on the real-time management plan and the real-time behavior of the target person, a care suggestion is output. That is, the present application obtains the physical index data of the target person through the robot, and predicts the physical state of the target person based on the physical index data, and then formulates a management plan for the target person based on the physical state prediction result, and then gives care suggestions based on the management plan and the daily real-time behavior of the target person. It can be understood that the present application realizes the technical solution of replacing manual care for target persons by robots, enhancing social care power. At the same time, compared with manual care (caregivers), the quality of which depends on the subjective consciousness of the caregivers, the present application uses robots for care, which can also ensure better care quality, thereby meeting the needs of current social development. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0043] Figure 1 This is a flow chart of the first embodiment of the robot-based care method of the present application;

[0044] Figure 2 This is a flow chart of the second embodiment of the robot-based care method of the present application;

[0045] Figure 3 This is a flowchart of the third embodiment of the robot-based care method of the present application;

[0046] Figure 4 This is a flowchart of the fourth embodiment of the robot-based care method of the present application;

[0047] Figure 5 This is a schematic diagram of the framework of the robot-based care method of this application;

[0048] Figure 6 This is a schematic diagram of the device structure of the hardware operating environment involved in the robot-based care method in the embodiment of the present application.

[0049] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0050] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0051] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0052] With the development of the aging trend, the ranks of the elderly population are constantly growing, while the proportion of the labor force in the social structure is also declining. In this situation of one increase and the other decrease, there is a shortage of care for the elderly. Among them, the need for care is particularly obvious for some elderly people with underlying diseases. Taking diabetes as an example, diabetic patients require relatively stricter health management, such as strict control of diet, management of blood pressure and blood sugar, reasonable arrangement of daily routines, and taking medicine on time. Therefore, it is particularly important to have sufficient care for improving the condition of diabetic patients. It should be noted that in addition to underlying diseases, the elderly themselves also need care, but currently they mainly rely on manual care (for example, caregivers or family members), which results in insufficient social care.

[0053] The main solution of the embodiment of the present application is: obtaining the physical indicator data of the target person through a robot, and obtaining the physical condition prediction result of the target person based on the physical indicator data and a preset state prediction model; generating a real-time management plan for the target person according to the physical condition prediction result; and outputting care recommendations based on the real-time management plan and the real-time behavior of the target person.

[0054] This application will obtain the target person's physical indicator data through the robot, and predict the target person's physical condition through the physical indicator data, and then formulate a management plan for the target person based on the physical condition prediction results, and then give care suggestions based on the management plan and the target person's daily real-time behavior. It can be understood that this application realizes the technical solution of replacing manual care for target persons with robots, enhancing social care power. At the same time, compared with manual care (caregivers), the quality depends on the subjective consciousness of the caregivers. This application uses robots for care, which can also ensure better care quality, thereby meeting the needs of current social development.

[0055] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a cloud platform, computer, mobile phone, etc., or an electronic device that can realize the above functions.

[0056] Based on the above introduction, the embodiment of the present application provides a robot-based care method, referring to Figure 1 , which is a flow chart of the first embodiment of the robot-based care method of this application.

[0057] In this embodiment, the robot-based care method is applied to any functional node in the data governance system and includes steps S10 to S30:

[0058] Step S10, obtaining physical indicator data of a target person through a robot, and obtaining a physical condition prediction result of the target person based on the physical indicator data and a preset condition prediction model;

[0059] It should be noted that in this embodiment, the implementation entity of the above-mentioned robot-based care method can be a robot-based care system, or a cloud server in the robot-based care system. The robot-based care system can be composed of a cloud server and a robot. The cloud server communicates with the robot. Typically, the cloud server will issue control instructions to the robot according to a pre-set care strategy, controlling the robot to provide care for the target person. It is worth noting that the above-mentioned target person can be an ordinary elderly person or an elderly person with underlying diseases, such as diabetes and hypertension.

[0060] Exemplarily, a care system or cloud server issues control instructions to a robot, instructing it to acquire physical indicator data of a target individual. The frequency of acquiring the target individual's physical indicators can be set based on the care strategy and the type of target individual, such as daily, weekly, or monthly, without limitation. Furthermore, the physical indicator data can include blood pressure, heart rate, respiration, weight, body fat percentage, and BMI (Body Mass Index), which can be collected by sensors or data collection devices configured on the robot. The robot can upload the collected physical indicator data to the cloud server, which then uses the physical indicator data and a preset state prediction model to predict the target individual's physical condition and obtain a physical condition prediction result. The preset state prediction model can be a pre-trained neural network prediction model. For example, by acquiring a large number of elderly test samples, such as those collected from a physical examination center or hospital, and labeling the collected results, samples can be obtained for training the preset state prediction model. The labeled collected results can include the test conclusion, such as normal, weak, underweight, overweight, malnourished, overnutrition, or other underlying conditions. Therefore, on this basis, the predicted results of the physical condition of the target person mentioned above can be normal, weak, thin, fat, malnourished, overnourished or other basic diseases, etc., which will not be repeated here.

[0061] Step S20, generating a real-time management plan for the target person based on the physical condition prediction result;

[0062] It should be noted that in this implementation, in addition to predicting the physical condition of the target person, a real-time management plan for the target person will also be generated. The real-time management plan refers to a management plan obtained based on the real-time condition of the target person.

[0063] For example, a mapping relationship between physical status and real-time management plan can be pre-established. After obtaining the physical status prediction result, the management plan corresponding to the physical status prediction result can be directly obtained through the mapping relationship and used as the above-mentioned real-time management plan. In addition, precautions can be first determined based on the physical status prediction result, and then the real-time management plan can be specified based on the precautions. Generally, different physical statuses (i.e., physical status prediction results) will correspond to different precautions. For example, for a target person who is thin or malnourished, precautions may include eating more protein. For a target person who is overweight or overnourished, precautions may include eating more vegetables. For a target person with underlying medical conditions, such as hypertension, precautions may include reducing salt intake, eating more potatoes, spinach, tomatoes, milk, yogurt, cheese, almonds, oats, and black beans, and regularly engaging in aerobic exercise. The above-mentioned process of determining precautions based on the physical status prediction result can also be achieved through a predictive model. For example, after an elderly person undergoes a physical examination or examination, in addition to the conclusion, there may also be medical advice. The medical advice can serve as a label for the examination conclusion, thereby forming a training sample for the predictive model. Of course, existing literature materials can also be used as training samples. Then generate a real-time management plan based on the precautions. The real-time management plan can include a diet management plan and an exercise management plan. For example, when the precautions include eating more protein or eating more vegetables, the above-mentioned diet management plan can be to select some meats or vegetables as optional recipes for the target person to choose. When the target person goes out to buy food or prepares to cook, remind or suggest the target person to refer to the recipe to buy food or cook, etc. When the precautions include easy aerobic exercise, the exercise management plan for the day is generated according to the user's preferences, weather or season. The exercise management plan includes sports (such as slow walking, jogging, square dancing, etc.), exercise time points (can give priority to user preferences, can also be determined according to weather conditions, etc., which will not be repeated here) and exercise volume (can be reflected by exercise duration, number of steps or length).

[0064] Step S30: Outputting care suggestions based on the real-time management plan and the real-time behavior of the target person.

[0065] It should be noted that after generating the real-time management plan, it is also necessary to implement the plan. In this embodiment, the implementation of the management plan can be supervised by a robot.

[0066] For example, the robot can capture the target person's real-time behavior and then output care recommendations based on the real-time behavior and the real-time management plan. For example, the robot can capture an image of the target person through a camera installed on the robot. A behavior recognition model is then used to identify the target person's behavior from the image. A determination is made as to whether the real-time behavior is consistent with the real-time management plan. If not, corresponding care recommendations can be given to promptly correct the target person's behavior. For example, if the real-time management plan requires the target person to exercise at this time, but the target person's real-time behavior is identified as watching TV, a voice care recommendation to exercise promptly can be output through the robot's speaker.

[0067] In this embodiment, a robot acquires the physical index data of a target person, and based on the physical index data and a preset state prediction model, obtains a physical state prediction result of the target person; based on the physical state prediction result, a real-time management plan for the target person is generated; and based on the real-time management plan and the real-time behavior of the target person, a care recommendation is output. That is, this application acquires the physical index data of a target person through a robot, predicts the physical state of the target person based on the physical index data, and then formulates a management plan for the target person based on the physical state prediction result, and then gives care recommendations based on the management plan and the real-time behavior of the target person. It can be understood that this application implements a technical solution in which robots replace human care for target persons, enhancing social care capabilities. At the same time, compared to human care (caregivers), where the quality depends on the subjective consciousness of the caregivers, this application uses robots to provide care, which can also ensure better care quality, thereby meeting the needs of current social development.

[0068] In a feasible embodiment, the robot is provided with a blood pressure detection unit, a blood sugar detection unit, a heart rate detection unit, and a blood oxygen saturation detection unit. The step of obtaining the target person's physical index data by the robot includes steps S11 to S13:

[0069] Step S11, obtaining the blood pressure data of the target person through the blood pressure detection unit, obtaining the blood sugar data of the target person through the blood sugar detection unit, obtaining the heart rate data of the target person through the heart rate detection unit, and obtaining the blood oxygen data of the target person through the blood oxygen saturation detection unit;

[0070] Step S12, using the blood pressure data, the blood sugar data, the heart rate data, and the blood oxygen data as body index data;

[0071] Step S13: input the physical indicator data and the physical condition data of the target person into a preset state prediction model to obtain the physical state prediction result.

[0072] It should be noted that in this embodiment, the robot is also equipped with a blood pressure detection unit, a blood glucose detection unit, a heart rate detection unit, and a blood oxygen saturation detection unit for obtaining the target person's physical indicator data. For example, the blood pressure detection unit can be a cuff-type blood pressure monitor or a cuff-free technology (such as plethysmography or ultrasound), and is integrated into the robot; the blood glucose detection unit can be an integrated fingertip blood sampling device and blood glucose test strips, or use non-invasive technology such as an optical biosensor; the heart rate detection unit can be a photoplethysmogram (PPG) sensor; and the blood oxygen saturation detection unit can also typically use a PPG sensor, that is, it can share the same sensor with the heart rate detection unit. Accordingly, the target person's blood pressure data can be obtained through the blood pressure detection unit. For example, during the test, the robot can eject the cuff-type blood pressure monitor, and then the target person can wear it themselves and start pressurized measurement to obtain blood pressure data. The target person's blood glucose data is obtained through the blood glucose detection unit, such as through a non-invasive optical biosensor. Similarly, the heart rate data of the target person is obtained through the heart rate detection unit, and the blood oxygen data of the target person is obtained through the blood oxygen saturation detection unit. The blood pressure data, blood sugar data, heart rate data and blood oxygen data obtained will be used as physical indicator data. After the physical indicator data and the physical condition data of the target person are input into the preset state prediction model, the physical state prediction result of the target person is obtained. Among them, the physical condition data of the target person can be the basic information of the target person, such as height, age, weight, gender and medical history, and the physical condition data can be pre-stored data. The preset state prediction model can make predictions based on the characteristics of the input data to obtain the physical state of the target person, that is, the above-mentioned physical state prediction result.

[0073] It is understood that the target person's physical indicator data can be collected by a robot located near the target person. The collected physical indicator data is then transmitted by the robot to a cloud server. The cloud server then uses its configured preset state prediction model and the physical indicator data and physical condition data to predict the target person's physical condition. In other words, in this embodiment, the target person's physical condition can be predicted and evaluated at any time based on the robot's detection results, thereby providing a preliminary physical condition reference for the target person.

[0074] Reference Figure 2, which is a flow chart of the second embodiment of the robot-based nursing method of the present application, proposed based on the first embodiment of the robot-based nursing method of the present application. In this embodiment, the same or similar contents as the above embodiments can be referred to the above introduction, and will not be repeated hereafter. The real-time management plan includes at least one time node and the node matters corresponding to the time node. The step of outputting nursing suggestions based on the real-time management plan and the real-time behavior of the target person includes steps S21 to S22:

[0075] Step S21, when the current time reaches the time node, obtaining the real-time behavior of the target person through the robot;

[0076] Step S22, when the real-time behavior is different from the node event, the care suggestion is generated according to the node event and the preset large language model, and the care suggestion is output through the robot.

[0077] It should be noted that the above-mentioned real-time management plan includes at least one time node and the node matters corresponding to the time node and the node. Accordingly, in actual applications, multiple time nodes and node matters corresponding to each time node may be included. Since the relevant supervision or implementation process of each time node is basically the same, in this embodiment, one of them will be used as an example for description.

[0078] Exemplarily, if it is monitored that the current time has reached the above-mentioned time node, the robot is used to obtain the target person's implementation behavior. It is worth noting that the above-mentioned time node can refer to an absolute time point, such as a certain time of the day, or a relative time point, such as a preset time before a meal or a preset time after a meal. The robot collects images including the target person, and then identifies the target person's real-time behavior based on the image, such as through a preset behavior recognition model. Among them, the preset behavior recognition model can be deployed on the robot or on a cloud server. Alternatively, the behavior of the target person can be identified by calling a third-party behavior recognition model. The specific process will not be repeated here.

[0079] The real-time behavior is compared with the node items. If the two are different, care suggestions are generated based on the node items and the preset large language model. For example, if the node item is going out for exercise, but the real-time behavior is watching TV, the node items and the preset inquiry template can be combined to generate prompt words to inquire with the large language model. For example, the prompt word can be "Now is exercise time, please persuade the elderly (or patient) family members to exercise as a family member", or it can be combined with the real-time behavior at the same time, such as the prompt word can be "Now is exercise time, please persuade the elderly (or patient) family members to stop watching TV and exercise as a family member". The prompt word is input into the preset large language model, and the output result of the preset large language model is used as the care suggestion, and the care suggestion is output through the speaker on the robot.

[0080] It's worth noting that in addition to triggering the output of care suggestions when the target person's real-time behavior differs from the node event, it can also trigger the generation and output of care suggestions when the target person is identified as unhappy. In this case, the prompt word can be "Your elder is depressed. Please chat with the elderly as a friend or family member," thereby communicating with the target person.

[0081] For elderly people with illnesses, the above management plan can include a plan to urge them to take medication. For example, for patients with diabetes, the real-time management plan can include a time node before meals, and accordingly, the node item under this node is insulin injection. In addition, for other types of diseases, the corresponding time node for taking medication can be after meals (to reduce drug irritation on the stomach).

[0082] In a feasible implementation manner, the step of obtaining the real-time behavior of the target person by the robot includes steps S211 to S214:

[0083] Step S211, obtaining a scene image of the scene in which the robot is located through the camera on the robot;

[0084] Step S212, determining a candidate region in the scene image based on a difference between the scene image and a preset priori image, wherein the preset priori image is an image obtained when no person exists in the scene;

[0085] Step S213: performing person recognition on the candidate area, and obtaining video data of the target person when the target person is recognized;

[0086] Step S214: performing behavior recognition on the video data using a preset behavior recognition model to obtain the real-time behavior of the target person.

[0087] For example, the robot can be equipped with a high-definition camera, which captures an image of the scene in which the robot is located. This camera can be used to capture images from a fixed location within the scene. The captured scene image is then compared with a preset prior image to determine the difference between the scene image and the preset prior image, and the areas that differ are identified as candidate areas. It is worth noting that the preset prior image refers to an image of the scene without any human presence. For example, when the robot is deployed, a location where possible activity is cleared and the robot can capture the scene to obtain the preset prior image. It is understood that by comparing the scene image with the preset prior image to determine the difference, candidate areas can be obtained, helping to quickly identify areas suspected of being a target person, thereby accelerating target person identification. Person identification in the candidate areas can include facial recognition to determine whether the candidate area is the target person, or it can include other features such as hair, body shape, and clothing to avoid the problem of failing to identify the target person due to angle errors that prevent facial features from being captured. Once the target person is confirmed to be identified, the robot can then capture video data of the target person. The video data is uploaded to the cloud server, which can call the interface of the third-party preset behavior recognition model to perform behavior recognition on the video data, thereby obtaining the real-time behavior of the target person.

[0088] In a feasible implementation manner, after the step of identifying people in the candidate area, the method further includes steps S215 to S216:

[0089] Step S215, if the target person is not recognized, changing the position of the robot in the scene, and returning to the step of acquiring a scene image of the scene in which the robot is located through the camera on the robot based on the changed position of the robot; or

[0090] Step S216: If the target person is not identified, the scene in which the robot is located is changed, and based on the new scene, the step of obtaining the scene image of the robot in the scene through the camera on the robot is returned to.

[0091] For example, if the target person is not identified, the robot's position in the scene may be changed, taking into account the possibility that the target person is obscured. Based on the changed position, the robot then returns to the step of acquiring the scene image of the robot's scene using the camera on the robot. This is equivalent to changing the viewing angle of the captured image, retaking a new scene image, and then performing recognition. It is worth noting that after the position is changed, the preset prior image for comparison can be synchronously replaced, ensuring that the position of the new preset prior image matches the position of the newly captured scene image. Alternatively, after the position is changed, the new scene image is converted to the shooting angle of the initial preset prior image based on the robot's shooting posture change during the position change. Alternatively, the initially determined candidate area is projected onto the new scene image to obtain a new candidate area. Based on the new candidate area, the robot then returns to the step of performing person recognition on the candidate area, and if the target person is recognized, the step of acquiring video data of the target person is performed.

[0092] In addition to changing the shooting position, the robot's scene can also be changed. For example, after the robot's position has changed a predetermined number of times within the same scene, the robot's scene can be changed. For example, the robot can be controlled to move to another room (i.e., another scene). Based on the new scene, the robot can then return to the step of acquiring the scene image of the robot's scene through the robot's camera.

[0093] Reference Figure 3 , is a flow chart of the second embodiment of the robot-based nursing method of the present application, which is proposed based on the first embodiment of the robot-based nursing method of the present application. In this embodiment, the same or similar contents as the above embodiments can be referred to the above introduction, and will not be repeated hereafter. The body state prediction result includes each state type and the probability of each state type. The step of generating the real-time management plan of the target person according to the body state prediction result includes steps S31 to S34:

[0094] Step S31, taking the state type with the highest probability among the state types as the target type;

[0095] Step S32, determining a basic management plan for the target personnel based on the target type;

[0096] Step S33, when the historical target type corresponding to the historical physical condition prediction result obtained at the previous monitoring time point is the same as the target type, determining the health development trend of the target person based on the difference between the historical physical condition prediction result and the physical condition prediction result;

[0097] Step S34: adjusting the basic management plan according to the health development trend to obtain the real-time management plan.

[0098] Exemplarily, the above-mentioned physical state prediction results may include various state types and the probabilities of each state type. Among them, each state type may be normal, thin, malnourished, etc., and the specific ones may refer to the above-mentioned embodiments, or may be set by technical personnel according to actual conditions. Accordingly, each state type also includes a probability, and the state type with the highest probability among the various state probabilities is used as the target type. And the basic management plan for the target person is determined based on the target type. Among them, the basic management plan may be a pre-set or a management plan for the target type. It is worth noting that when a real-time management plan is generated for the target person for the first time, the basic management result can be directly used as the real-time management plan.

[0099] In addition, when the basic management plan is not generated for the first time, the previous monitoring time point is obtained to obtain the historical physical state prediction result, wherein the previous monitoring time point refers to the time point at which the physical indicator data needs to be obtained relative to the current moment according to the frequency of obtaining the physical indicator data of the target person. If the historical target type corresponding to the historical physical state prediction result is the same as the currently determined target type, the health development trend of the target person is determined based on the difference between the historical physical state prediction result and the physical state prediction result. Referring to the above-mentioned examples where each state type can be normal, thin, and malnourished, in actual applications, each state type can be set with a weight, wherein the weight also represents the severity of the state type. For example, in the order of normal, thin, and malnourished, the severity and weight will increase in sequence. Accordingly, based on the weight of each state type, the probabilities in the historical physical state prediction results and the current physical state prediction results (i.e., the aforementioned physical state prediction results) are weighted and summed to obtain the quantitative scores of the two prediction results. The difference between the quantitative scores of the two prediction results is the aforementioned difference. The health development trend of the target person is then determined based on this difference. For example, if the quantitative score of the historical physical state prediction results is greater than the quantitative score of the current physical state prediction results, then the health development trend of the target person is positive, i.e., improving. Conversely, if the quantitative score of the historical physical state prediction results is less than the quantitative score of the current physical state prediction results, then the health development trend of the target person is negative, i.e., deteriorating. If the two quantitative scores are the same, i.e., there is no difference, then the development trend can be determined to maintain the status quo. In addition, if the historical target type corresponding to the historical physical state prediction results is different from the target type, the basic management plan can be directly used as the real-time management plan.

[0100] For example, the basic management plan is adjusted according to the health development trend to obtain a real-time management plan. It is understandable that the adjustment of the basic management plan is mainly to adjust the node items. For example, if the node item is exercise, the amount of exercise can be adjusted, such as increasing or decreasing the amount of exercise.

[0101] In a feasible implementation manner, the steps S341 to S342 of adjusting the basic management plan according to the health development trend to obtain the real-time management plan are as follows:

[0102] Step S341, when the health development trend is deteriorating, adjusting the item parameters of the preset node items in the basic management plan toward a preset first direction;

[0103] Step S342, when the health development trend is improving, adjusting the item parameters of the preset node items in the basic management plan toward a preset second direction, wherein the preset first direction and the preset second direction are opposite.

[0104] Exemplarily, when the above-mentioned health development trend is a deterioration, the item parameters of the preset node items in the basic management plan can be adjusted to the preset first direction. For example, when the node item is exercise, the item parameter can be the amount of exercise, and accordingly, the first direction can be a reduction direction, that is, reducing the amount of exercise. And when the health development trend is improvement, the item parameters of the preset node items in the basic management plan can be adjusted to the preset second direction. Similarly, if the node item is exercise, the item parameter can be the amount of exercise, and accordingly, the second direction can be an increase direction, that is, increasing the amount of exercise. It can be understood that in this embodiment, the management plan will be adjusted in real time according to the health development trend of the target person, so as to ensure that the management plan matches the physical condition of the target person.

[0105] In addition, refer to Figure 4 , is a framework diagram of an embodiment of the present application, which includes a target person, a robot and a cloud server, wherein the robot and the cloud server can form a robot-based care system. The robot can be used to collect the physical index data of the target person and collect images of the target person. There will be data interaction between the robot and the cloud server. For example, the robot sends the collected physical index data and images to the cloud server. An AI model is deployed on the cloud server, which can be the above-mentioned preset state prediction model or the above-mentioned behavior prediction model. The pregnancy device combines the data sent by the robot and the control instructions of the robot generated by the IA model to control the robot, and then take care of the target person.

[0106] The present application also provides a robot-based nursing system, referring to Figure 5 , the robot-based care system includes:

[0107] The monitoring module 10 is used to obtain the physical index data of the target person through the robot, and obtain the physical condition prediction result of the target person based on the physical index data and a preset condition prediction model;

[0108] A management module 20 is configured to generate a real-time management plan for the target person based on the physical condition prediction result;

[0109] The care module 30 is configured to output care suggestions based on the real-time management plan and the real-time behavior of the target person.

[0110] Optionally, the robot is provided with a blood pressure detection unit, a blood sugar detection unit, a heart rate detection unit, and a blood oxygen saturation detection unit, and the monitoring module 10 is further used to:

[0111] Acquiring the blood pressure data of the target person through the blood pressure detection unit, acquiring the blood sugar data of the target person through the blood sugar detection unit, acquiring the heart rate data of the target person through the heart rate detection unit, and acquiring the blood oxygen data of the target person through the blood oxygen saturation detection unit;

[0112] using the blood pressure data, the blood sugar data, the heart rate data, and the blood oxygen data as body index data;

[0113] The physical indicator data and the physical condition data of the target person are input into a preset state prediction model to obtain the physical state prediction result.

[0114] Optionally, the real-time management plan includes at least one time node and a node item corresponding to the time node, and the nursing module 30 is further configured to:

[0115] When the current time reaches the time node, the real-time behavior of the target person is obtained by the robot;

[0116] When the real-time behavior is different from the node event, the care suggestion is generated according to the node event and a preset large language model, and the care suggestion is output through the robot.

[0117] Optionally, the nursing module 30 is further configured to:

[0118] Acquire a scene image of the scene in which the robot is located through a camera on the robot;

[0119] determining a candidate region in the scene image based on a difference between the scene image and a preset priori image, wherein the preset priori image is an image obtained when no person exists in the scene;

[0120] Performing person recognition in the candidate area, and obtaining video data of the target person when the target person is recognized;

[0121] The video data is subjected to behavior recognition using a preset behavior recognition model to obtain the real-time behavior of the target person.

[0122] Optionally, the nursing module 30 is further configured to:

[0123] If the target person is not identified, changing the position of the robot in the scene, and returning to the step of acquiring a scene image of the scene in which the robot is located through the camera on the robot based on the changed position of the robot; or

[0124] If the target person is not identified, the scene in which the robot is located is changed, and based on the new scene, the step of obtaining the scene image of the robot in the scene through the camera on the robot is returned to.

[0125] Optionally, the body state prediction result includes each state type and the probability of each state type, and the management module 20 is further configured to:

[0126] The state type with the highest probability among the state types is taken as the target type;

[0127] Determining a basic management plan for the target personnel based on the target type;

[0128] If the historical target type corresponding to the historical physical condition prediction result obtained at the previous monitoring time point is the same as the target type, determining the health development trend of the target person based on the difference between the historical physical condition prediction result and the physical condition prediction result;

[0129] The basic management plan is adjusted according to the health development trend to obtain the real-time management plan.

[0130] Optionally, the management module 20 is further configured to:

[0131] When the health development trend is deteriorating, adjusting the item parameters of the preset node items in the basic management plan toward a preset first direction;

[0132] When the health development trend is improving, the item parameters of the preset node items in the basic management plan are adjusted toward a preset second direction, wherein the preset first direction and the preset second direction are opposite.

[0133] The robot-based nursing system provided in this application utilizes the robot-based nursing method described in the aforementioned embodiments, aiming to address the technical issue of insufficient nursing resources in society. Compared to the prior art, the beneficial effects of the robot-based nursing system provided in the embodiments of this application are the same as those of the robot-based nursing method described in the aforementioned embodiments. Other technical features of the robot-based nursing system are the same as those disclosed in the aforementioned embodiments and are not further elaborated here.

[0134] The present application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the robot-based care method in the above-mentioned embodiment one.

[0135] Reference below Figure 6 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present application. The electronic devices in the embodiments of the present application may include, but are not limited to, mobile terminals such as computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), and fixed terminals such as computers. Figure 6 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0136] like Figure 6As shown, the electronic device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. Various programs and data required for the operation of the electronic device are also stored in RAM 1004. The processing device 1001, ROM 1002, and RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an electronic device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0137] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0138] The electronic device provided in this application, utilizing the robot-based care method of the aforementioned embodiment, can address the technical issue of insufficient caregivers in society. Compared to the prior art, the beneficial effects of the electronic device provided in this application are the same as those of the robot-based care method of the aforementioned embodiment. Other technical features of the electronic device are the same as those disclosed in the aforementioned embodiment and are not further elaborated here.

[0139] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0140] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0141] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer program) stored thereon, and the computer-readable program instructions are used to execute the robot-based care method in the above-mentioned embodiment.

[0142] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0143] The computer-readable storage medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0144] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by an electronic device, the electronic device:

[0145] Monitoring the total number of tasks processed by the functional node within a preset time window and the task processing interval, and determining the task processing rate of the functional node based on the total number of tasks and the task processing interval;

[0146] Determining a node pressure degree of the functional node based on a node computing resource usage rate of the functional node and the task processing rate;

[0147] When it is determined that the functional node is overloaded according to the node pressure level, a first backpressure signal is sent to a node related to the functional node, wherein the first backpressure signal is used to reduce a data sending rate of the related node.

[0148] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0149] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0150] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0151] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned robot-based care method, thereby resolving the technical issue of insufficient caregivers in society. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the robot-based care method provided in the aforementioned embodiments, and are not further elaborated here.

[0152] The present application also provides a computer program product, comprising a computer program, which implements the steps of the above-mentioned robot-based care method when executed by a processor.

[0153] The computer program product provided in this application can solve the technical problem of regulating the data governance system. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the robot-based care method provided in the above embodiment, and will not be repeated here.

[0154] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A robot-based nursing method, characterized in that: The robot-based care method includes: Acquiring physical indicator data of a target person through a robot, and obtaining a physical condition prediction result of the target person based on the physical indicator data and a preset condition prediction model; generating a real-time management plan for the target person based on the physical condition prediction result; Outputting care recommendations based on the real-time management plan and the real-time behavior of the target person.

2. The robot-based care method according to claim 1, wherein: The robot is provided with a blood pressure detection unit, a blood sugar detection unit, a heart rate detection unit, and a blood oxygen saturation detection unit. The step of obtaining the target person's physical index data by the robot includes: Acquiring the blood pressure data of the target person through the blood pressure detection unit, acquiring the blood sugar data of the target person through the blood sugar detection unit, acquiring the heart rate data of the target person through the heart rate detection unit, and acquiring the blood oxygen data of the target person through the blood oxygen saturation detection unit; using the blood pressure data, the blood sugar data, the heart rate data, and the blood oxygen data as body index data; The physical indicator data and the physical condition data of the target person are input into a preset state prediction model to obtain the physical state prediction result.

3. The robot-based care method according to claim 1, wherein: The real-time management plan includes at least one time node and a node event corresponding to the time node. The step of outputting care suggestions based on the real-time management plan and the real-time behavior of the target person includes: When the current time reaches the time node, the real-time behavior of the target person is obtained by the robot; When the real-time behavior is different from the node event, the care suggestion is generated according to the node event and a preset large language model, and the care suggestion is output through the robot.

4. The robot-based care method according to claim 3, wherein: The step of obtaining the real-time behavior of the target person by the robot includes: Acquire a scene image of the scene in which the robot is located through a camera on the robot; determining a candidate region in the scene image based on a difference between the scene image and a preset priori image, wherein the preset priori image is an image obtained when no person exists in the scene; Performing person recognition in the candidate area, and obtaining video data of the target person when the target person is recognized; The video data is subjected to behavior recognition using a preset behavior recognition model to obtain the real-time behavior of the target person.

5. The robot-based care method according to claim 4, wherein: After the step of performing personnel recognition on the candidate area, the method further includes: If the target person is not identified, changing the position of the robot in the scene, and returning to the step of acquiring a scene image of the scene in which the robot is located through the camera on the robot based on the changed position of the robot; or If the target person is not identified, the scene in which the robot is located is changed, and based on the new scene, the step of obtaining the scene image of the robot in the scene through the camera on the robot is returned to.

6. The robot-based care method according to claim 1, wherein: The physical state prediction result includes each state type and the probability of each state type. The step of generating the real-time management plan for the target person according to the physical state prediction result includes: The state type with the highest probability among the state types is taken as the target type; Determining a basic management plan for the target personnel based on the target type; If the historical target type corresponding to the historical physical condition prediction result obtained at the previous monitoring time point is the same as the target type, determining the health development trend of the target person based on the difference between the historical physical condition prediction result and the physical condition prediction result; The basic management plan is adjusted according to the health development trend to obtain the real-time management plan.

7. The robot-based care method according to claim 6, wherein: The step of adjusting the basic management plan according to the health development trend to obtain the real-time management plan: When the health development trend is deteriorating, adjusting the item parameters of the preset node items in the basic management plan toward a preset first direction; When the health development trend is improving, the item parameters of the preset node items in the basic management plan are adjusted toward a preset second direction, wherein the preset first direction and the preset second direction are opposite.

8. A robot-based nursing system, characterized in that: The robot-based care system includes: A monitoring module is used to obtain physical indicator data of a target person through a robot, and obtain a physical condition prediction result of the target person based on the physical indicator data and a preset condition prediction model; A management module, configured to generate a real-time management plan for the target person based on the physical condition prediction result; The care module is used to output care suggestions based on the real-time management plan and the real-time behavior of the target person.

9. An electronic device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the robot-based care method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the robot-based care method according to any one of claims 1 to 7 are implemented.

Images