Nursing methods, equipment, media and program products

Abstract

The present application discloses a care method, device, medium and program product, and relates to the field of computer technology. The method includes: determining the subject care needs of the first subject based on the subject care data; executing the care feedback operation that matches the subject care needs; generating care log data based on the subject care data. On the one hand, the device can automatically collect and analyze the subject care data, and execute the corresponding care feedback operation, reducing manpower costs and improving care efficiency; on the other hand, by determining the needs expressed by the subject's behavior, the device can avoid blindly performing care feedback, so that the care feedback operation matches the actual needs of the subject, reducing invalid or erroneous care feedback operations, improving care accuracy, and helping to improve care quality. In addition, the device can also generate a care log by analyzing the subject care data, thereby automatically recording the subject's behavior at different time nodes.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular to a nursing method, device, medium and program product. Background Art

[0002] The child care terminal is a device used to monitor the status of children, and is designed to help child caregivers better care for and supervise children.

[0003] In the related art, child monitoring equipment usually includes a video monitor, which captures the child's activities through a camera and transmits these images in real time to the caregiver's terminal device (such as a mobile phone, tablet, etc.). The caregiver can understand the child's status in real time through the terminal device.

[0004] However, the video monitor can only provide the real-time activity picture of the child, and the caregiver needs to keep checking the monitor picture, which consumes a lot of the caregiver's time and energy and has low care efficiency. Summary of the invention

[0005] The present application provides a nursing method, device, medium and program product, and the technical solution is as follows:

[0006] In one aspect, a nursing method is provided, the method comprising:

[0007] Collecting subject care data of the first subject, the subject care data including data collected by a collection component from a physical environment containing the first subject, the subject care data being used to characterize subject behavior generated by the first subject's activities in the physical environment;

[0008] Determining a subject care demand of the first subject based on the subject care data, wherein the subject care demand refers to a feedback demand expressed by the first subject through the subject behavior;

[0009] executing a care feedback operation that matches the care needs of the subject, wherein the care feedback operation is used to respond to the subject's behavior;

[0010] Nursing log data is generated based on the subject nursing data, and the nursing log data is used to record the subject historical behavior of the first subject.

[0011] In another aspect, a nursing device is provided, the device comprising:

[0012] a data collection module, used to collect subject care data of the first subject, wherein the subject care data includes data collected by the collection component from the physical environment containing the first subject, and the subject care data is used to characterize subject behavior generated by the first subject's activities in the physical environment;

[0013] a data processing module, configured to determine a subject care demand of the first subject based on the subject care data, wherein the subject care demand refers to a feedback demand expressed by the first subject through the subject behavior;

[0014] An operation execution module, used for executing a care feedback operation matching the care demand of the subject, wherein the care feedback operation is used for responding to the subject's behavior;

[0015] A data generation module is used to generate nursing log data based on the subject nursing data, and the nursing log data is used to record the subject historical behavior of the first subject.

[0016] On the other hand, a computer device is provided, which includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement any of the above-mentioned care methods.

[0017] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction, at least one program, a code set or an instruction set is stored in the storage medium, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement any of the above-mentioned care methods.

[0018] On the other hand, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs any of the above-described nursing methods.

[0019] The beneficial effects brought by the technical solution provided by the embodiment of the present application include at least:

[0020] After the device collects the subject care data of the subject in the physical environment, it will analyze the subject care data to determine the demand information expressed by the subject through behavior, so that the device can perform care feedback operations that match the subject's needs. On the one hand, the device can automatically collect and analyze the subject care data and perform corresponding care feedback operations, reducing labor costs and improving care efficiency; on the other hand, by determining the needs expressed by the subject's behavior, the device can avoid blind care feedback, match the care feedback operation with the subject's actual needs, reduce invalid or erroneous care feedback operations, improve care accuracy, and help improve care quality. In addition, the device can also generate a care log by analyzing the subject care data, thereby automatically recording the subject's behavior at different time nodes. Relevant personnel can quickly understand the subject's situation through the care log, improving the efficiency of human-computer interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a schematic diagram of a computer system provided by an exemplary embodiment of the present application;

[0023] Figure 2 is a schematic diagram of a computer system provided by another exemplary embodiment of the present application;

[0024] Figure 3 is a schematic diagram of a computer system provided by yet another exemplary embodiment of the present application;

[0025] Figure 4 is a flow chart of a nursing method provided by an exemplary embodiment of the present application;

[0026] Figure 5 is a schematic diagram of a demand analysis model provided by an exemplary embodiment of the present application;

[0027] Figure 6 is a flow chart of a nursing method provided by another exemplary embodiment of the present application;

[0028] Figure 7 is a flowchart of a nursing method provided by another exemplary embodiment of the present application;

[0029] Figure 8 is a flowchart of a nursing method provided by another exemplary embodiment of the present application;

[0030] Fig. 9 is a structural block diagram of a nursing device provided by an exemplary embodiment of the present application;

[0031] Fig.10 It is a structural block diagram of a computer device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the present application clearer, the implementation mode of the present application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0033] In this application, the terms "first", "second", etc. are used to distinguish identical or similar items with substantially the same effects and functions. It should be understood that there is no logical or temporal dependency between "first" and "second", nor is there any limitation on quantity and execution order.

[0034] It should be noted that before collecting relevant data of users and during the process of collecting relevant data of users, this application can display a prompt interface, pop-up window or output voice prompt information, and the prompt interface, pop-up window or voice prompt information is used to prompt the user that its relevant data is currently being collected, so that this application only starts to execute the relevant steps of obtaining relevant data of users after obtaining the confirmation operation issued by the user to the prompt interface or pop-up window, otherwise (that is, when the confirmation operation issued by the user to the prompt interface or pop-up window is not obtained), the relevant steps of obtaining relevant data of users are terminated, that is, the relevant data of users are not obtained. In other words, all user data collected by this application are collected with the consent and authorization of the user, and the collection, use and processing of relevant user data need to comply with relevant laws, regulations and standards.

[0035] The child care terminal is a device used to monitor the status of children, and is designed to help child caregivers better take care of and supervise children. In the related art, child care equipment usually includes a video monitor, which captures the activity images of children through a camera and transmits these images to the caregiver's terminal device (such as a mobile phone, tablet, etc.) in real time. The caregiver can understand the status of the child in real time through the terminal device. However, the video monitor can only provide real-time activity images of the child, and the caregiver needs to continuously check the monitor screen, which consumes a lot of the caregiver's time and energy, and the care efficiency is low.

[0036] Based on this, the present application provides a care method. After the device collects the subject care data of the subject in the physical environment, it will analyze the subject care data to determine the demand information expressed by the subject through behavior, so that the device can perform care feedback operations that match the subject's needs. In addition, the device can also generate a care log by analyzing the subject care data, thereby automatically recording the subject's behavior at different time nodes.

[0037] First, a computer system for implementing the care method involved in the present application is introduced.

[0038] Figure 1 A schematic diagram of a computer system provided by an exemplary embodiment of the present application is as follows: Figure 1 As shown, the computer system includes a nursing terminal 110 .

[0039] In some embodiments, the nursing terminal 110 is a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart home appliance, a smart vehicle terminal, a smart robot, a smart camera, a smart speaker, a smart wearable device, etc., but is not limited thereto. Optionally, a client of a first application is installed and running in the nursing terminal 110. The first application refers to an application that provides a nursing function. The first application can be a traditional application, a cloud application, a small program or an application module in a host application, or a web platform. This embodiment does not limit this.

[0040] The care terminal 110 is connected to a collection component, which is used to collect data on the physical environment including a first subject, wherein the first subject refers to the object being cared for, such as infants, the elderly, the disabled, etc.; the collection component includes at least one of a camera, a microphone, a sensor, etc., which are not limited here; the data collected by the collection component can be called subject care data, which includes at least one of subject action data, subject expression data, subject sound data, etc.

[0041] Optionally, the acquisition component includes at least one of the following components:

[0042] (1) Collection components installed in the nursing terminal 110. For example: the mobile phone camera and microphone in a smart phone; the camera, microphone and various sensors in an intelligent robot.

[0043] (2) A collection component remotely connected to the nursing terminal 110, the collection component is connected to the nursing terminal 110 via a wireless network or a wired network. For example, a camera is installed at a suitable position in the room, the camera will collect image data of the child being cared for in real time, and then send the image data to the nursing terminal 110.

[0044] After the nursing terminal 110 acquires the subject nursing data through the acquisition component, the first application may process the subject nursing data as follows:

[0045] (1) Requirements analysis.

[0046] Optionally, the nursing terminal 110 includes a demand analysis model, which is a trained machine learning model (for example, a neural network model, etc.). The subject care data is input into the demand analysis model, and the demand analysis model processes the subject care data to obtain the subject care needs of the first subject, such as hunger, need for sleep, bad mood, safety risks, etc.

[0047] After determining the subject care needs of the first subject, the care terminal 110 will perform a care feedback operation that matches the subject care needs through the first application. For example, if it is detected that the child being cared for is hungry, a message will be played or pushed to remind the caregiver; or, if it is detected that the child being cared for is at risk of falling, an alarm sound will be played or a message will be pushed to alert the caregiver.

[0048] (2) Log generation.

[0049] The nursing terminal 110 also generates nursing log data based on the subject nursing data. Illustratively, the nursing log data can be implemented as a growth album, a video diary, an emotion record, etc., which is not limited here.

[0050] In some embodiments, the computer system further includes a server 120, which is connected to the nursing terminal 110 via a communication network 130, which can be implemented as a wired network or a wireless network. Optionally, the server 120 refers to a background server of the first application, which is used to provide background services for the first application.

[0051] Illustratively, after the nursing terminal 110 obtains the subject's care data, it sends the subject's care data to the server 120. The server 120 includes a demand analysis model. The server 120 analyzes the subject's care data to obtain the subject's care needs. Then, the server 120 sends the subject's care needs to the nursing terminal 110. The nursing terminal 110 executes a nursing feedback operation that matches the subject's care needs through the first application; or, the server 120 determines an operation instruction based on the subject's care needs, and sends the operation instruction to the nursing terminal 110. After receiving the operation instruction, the nursing terminal 110 executes a nursing feedback operation corresponding to the operation instruction through the first application.

[0052] The server 120 also generates nursing log data based on the subject nursing data, and then pushes the nursing log data to the nursing terminal 110. After receiving the nursing log data, the nursing terminal 110 can display the nursing log data in the first application.

[0053] It is worth noting that the server 120 can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, a cloud server that provides basic cloud computing services, and can also be implemented as a node in a blockchain system.

[0054] For example, the nursing terminal is implemented as a smart phone, and the collection component is implemented as a smart camera remotely connected to the smart phone. Figure 2 The physical environment 210 includes a smart camera 201 and a subject 202 , wherein the smart camera can be used to collect data from the physical environment 210 to obtain subject care data, such as images, videos, audios, etc. of the subject 202 .

[0055] The smart camera 201 is connected to the smart phone 220 via a wireless network. The smart phone 220 has a client of a first application installed and running. The care function provided by the first application includes at least one of the following functions:

[0056] (1) Demand prompts.

[0057] After the smart camera 201 collects the subject care data, it sends the subject care data to the smart phone 220. After determining the subject care needs corresponding to the subject care data, the smart phone 220 can perform a care feedback operation that matches the subject care needs. For example, when it is detected that the subject 202 is hungry, a notification 221 will be pushed in the first application of the smart phone 220 to prompt the caregiver through the notification 221, and / or the smart phone 220 will send a voice control instruction to the smart camera 201, and the voice control instruction is used to control the smart camera 201 to play a prompt sound, such as: playing the sound of "baby is hungry".

[0058] (2) Log generation.

[0059] The smart phone 220 will also generate care log data based on the subject care data. In an illustrative manner, the care log data can be implemented as a growth album. If the smart phone 220 recognizes that the collected subject action data indicates that the child being cared for performs a preset behavior (for example, smiling, turning over, yawning, etc.), it will obtain image or video data containing the preset behavior, and create a growth album 222 based on the obtained image or video data, and the user can view the growth album 222 through the first application.

[0060] (3) Subject interaction.

[0061] Optionally, the smartphone 220 can also send control instructions to the smart camera 201, thereby controlling the smart camera 201 to play sound to achieve remote interaction with the main body 202. For example, the smart camera 201 can be controlled by the smartphone 220 to play nursery rhymes, storybook interpretations, white noise, etc.

[0062] In some embodiments, the control instructions are instructions triggered by user operations, for example, when a user clicks the "play nursery rhyme" button on the application interface of the first application of the smart phone 220, the smart phone 220 sends a play control instruction to the smart camera 201, and the smart camera 201 plays the nursery rhyme. Alternatively, the control instructions are instructions automatically triggered according to the subject's care needs, for example, when the subject 202 is detected to be hungry, the smart phone 220 automatically sends a play control instruction to the smart camera 201, and the smart camera 201 plays the nursery rhyme.

[0063] In some embodiments, the number of smart phones 220 can be one or more. For the case where there are multiple care terminals 110, the multiple care terminals are all installed with the client of the first application. The client of the first application installed in each care terminal is logged in with a user account, and the user account is an authorized account. That is to say, multiple users can collaboratively care for the first subject through the first application if they are authorized. When multiple users use the first application, different user permissions correspond to different care functions. For example: User 1 has care permission a, then the first application used by User 1 can receive push messages determined based on the subject's care needs, etc. User 2 has care permission b, then the first application used by User 2 can view care log data generated based on the subject's care data.

[0064] Take the case where the nursing terminal is implemented as an intelligent robot. For illustration, please refer to Figure 3 , the intelligent robot 310 includes a collection component, such as Figure 3 Camera 311 is shown.

[0065] After the intelligent robot 310 obtains the subject care data through the collection component, it will determine the subject care needs corresponding to the subject care data. Then the intelligent robot 310 can perform care feedback operations that match the subject care needs. For example, when it detects that the subject is hungry, the intelligent robot 310 can play a prompt sound, such as: playing the sound of "Baby is hungry".

[0066] Optionally, the intelligent robot 310 also generates nursing log data based on the subject nursing data. In some embodiments, the intelligent robot 310 includes a screen component, and the user can view the nursing log data through the screen component.

[0067] Optionally, the intelligent robot 310 can also automatically perform interactive operations based on the subject's care needs. For example, when it detects that the cared child is hungry, the intelligent robot 310 automatically plays nursery rhymes and performs soothing actions to soothe the cared child.

[0068] In some embodiments, the intelligent robot 310 is connected to the smart phone 320 via a wireless network. A client of a second application is installed and running in the smart phone 320. The second application refers to an application that provides a smart robot management function. The second application can be a traditional application, a cloud application, a small program or an application module in a host application, or a web platform, which is not limited in this embodiment.

[0069] Schematically, the intelligent robot 310 determines the subject care needs corresponding to the subject care data, and can push care information to the smart phone 320. For example, when the intelligent robot 310 detects that the subject is hungry, it pushes prompt information to the smart phone 320, prompts the user through the prompt information, and the user can view the prompt information in the second application of the smart phone 320. Among them, the intelligent robot 310 pushes the care information to the smart phone 320, which can also be implemented as care log data.

[0070] The user can also send control instructions to the intelligent robot 310 through the smart phone 320 to control the robot to perform corresponding operations. For example, when the user sees a reminder message that the cared child is hungry in the second application of the smart phone 320, the user can click the "comfort" button in the application interface of the second application of the smart robot 310. The smart phone 320 will send a soothing control instruction to the intelligent robot 310. After receiving the soothing control instruction, the intelligent robot 310 will automatically play nursery rhymes and perform soothing actions to comfort the cared child.

[0071] Next, the specific process of the nursing method provided in the embodiment of the present application is introduced.

[0072] Figure 4 is a flowchart of a nursing method provided in an embodiment of the present application, and the method is applied to Figure 1 Taking the nursing terminal shown as an example, the method is as follows: steps 410 to 440.

[0073] Step 410, collecting subject care data of the first subject.

[0074] The subject care data includes data collected by the collection component from the physical environment containing the first subject. The subject care data is used to characterize the subject behavior generated by the first subject's activities in the physical environment.

[0075] Optionally, the subject care data is used to identify the needs of the first subject and generate log data of the first subject, and the subject care data includes at least one of the following data:

[0076] (1) Subject action data.

[0077] The subject motion data is used to indicate the motion performed by the first subject in the physical environment, such as stretching, turning over, yawning, standing, etc. Optionally, the acquisition component for acquiring the subject motion data includes at least one of a camera, a motion sensor, and the like.

[0078] Schematically, if the subject motion data is collected by a camera, the camera is installed at a suitable location in the physical environment or in a nursing terminal. When the first subject moves in the physical environment, the camera can capture the physical environment screen and obtain an image or video as the subject motion data. If the subject motion data is collected by a motion sensor, the motion sensor can be implemented as at least one of an acceleration sensor, a gyroscope sensor, an infrared sensor, etc. Schematically, the acceleration sensor or the gyroscope sensor is installed at a key part of the body of the first subject (for example, the wrist, waist, ankle, etc.) to capture and measure the dynamic motion information of the key parts in real time. The infrared sensor is installed at a suitable location in the physical environment or in a nursing terminal to capture the motion trajectory information of the first subject in the physical environment; the data collected by the motion sensor (for example, dynamic motion information and motion trajectory information, etc.) can be stored in the form of a time series, and each time point corresponds to the reading of one or more sensors, including timestamp, sensor type, reading value and other information.

[0079] The subject motion data can fully present the actual activity status of the first subject in the physical environment, which helps to accurately identify the subject's needs in different situations.

[0080] (2) Subject expression data.

[0081] The subject expression data is used to indicate the facial expression of the first subject, such as smiling, frowning, blinking, crying, etc. Optionally, the collection component for collecting the subject expression data can be implemented as a camera.

[0082] Illustratively, the camera is installed at a suitable location in the physical environment or in a nursing terminal. When the first subject moves in the physical environment, the camera can capture the physical environment and obtain an image or video as the subject's expression data.

[0083] Optionally, the camera used to collect the subject's expression data and the camera used to collect the subject's motion data can be the same or different. Schematically, if the camera used to collect the subject's expression data and the camera used to collect the subject's motion data are different, a first camera can be installed in the physical environment to collect the subject's motion data, and a second camera can be installed to collect the subject's expression data. The first camera can be installed at a higher position to cover the range of activities of the first subject in the physical environment and obtain the first subject's overall motion posture; the second camera can be installed in a position where the first subject's face can be clearly and stably photographed to obtain the first subject's facial expression.

[0084] The subject's expression data directly reflects the current emotional feelings of the first subject, which is the key basis for understanding his or her psychological state and helps to identify the subject's psychological care needs.

[0085] (3) Subject sound data.

[0086] The subject sound data is used to indicate the sound made by the first subject in the physical environment, such as laughter, crying, etc. Optionally, the collection component for collecting the subject sound data can be implemented as a microphone.

[0087] Illustratively, the microphone is installed at a suitable location in the physical environment or in a nursing terminal. When the first subject moves in the physical environment, the microphone will capture and record the sounds in the physical environment in real time. The subject's voice can be identified by analyzing the sounds collected by the microphone.

[0088] The subject's sound data supplements the subject's status information in the physical environment from the auditory dimension. Combined with the action data and expression data, it can restore the subject's scene and status at the time in a more three-dimensional way, avoid the judgment bias caused by relying solely on visual information, and make the identification of the subject's needs more comprehensive and accurate.

[0089] It should be noted that, in addition to the above-mentioned data, the subject care data may also include some other data, which is not limited in the embodiments of the present application. For example, the subject care data also includes environment-related data and subject health data. The environment-related data is used to indicate various types of data related to the physical environment, such as temperature, humidity, air quality, etc. Optionally, the acquisition component for collecting environment-related data can be implemented as an environment monitoring sensor. Schematically, the environment monitoring sensor includes a temperature and humidity sensor (for detecting the temperature and humidity in the physical environment) and a gas sensor (for detecting the air quality in the physical environment). The subject health data is used to indicate data related to the health status of the first subject, such as physiological indicators such as heart rate and body temperature. Optionally, the acquisition component for collecting subject health data can be implemented as a health monitoring sensor. Schematically, the health monitoring sensor includes a heart rate sensor, a body temperature sensor, etc. The health monitoring sensor can be integrated on a wearable device, and the first subject wears the wearable device, thereby obtaining the subject health data of the first subject through the wearable device.

[0090] In an embodiment of the present application, the subject care data of the first subject is collected when the data collection authorization is obtained. Schematically, a user account is logged in to the care terminal. Before data collection, a prompt interface, pop-up window or voice prompt information is displayed. The prompt interface, pop-up window or voice prompt information is used to prompt the user that the subject care data is currently being collected, and the purpose, scope, method of data collection, and subsequent use and processing of the data are clearly stated. This makes the present application only start to execute the relevant steps of collecting the subject care data of the first subject after obtaining the user's confirmation operation on the prompt interface or pop-up window, otherwise (that is, when the user's confirmation operation on the prompt interface or pop-up window is not obtained), the subject care data of the first subject is not collected. In other words, the subject care data collected by the present application is collected with the consent and authorization of the user, and the collected data is only used for purposes within the scope of authorization.

[0091] Step 420 , determining the subject care needs of the first subject based on the subject care data.

[0092] The subject care demand refers to the feedback demand expressed by the first subject through the subject behavior.

[0093] Optionally, the subject's care needs include physiological care needs, psychological care needs, safety care needs, etc., which are not limited here.

[0094] Illustratively, when the first subject is in a target physiological state, it is determined that the first subject has a physiological care need that matches the target physiological state, and the target physiological state includes hunger, sleepiness, body pain or discomfort, etc. Taking hunger as an example, when the first subject has hunger, it means that the first subject has a need to eat.

[0095] When the first subject is in the target psychological state, it is determined that the first subject has a psychological care need that matches the target psychological state. The target psychological state includes a depressed state, an excited state, a self-entertainment state, a nervous and fearful state, etc. Taking the self-entertainment state as an example, infants and young children may perform some simple repetitive actions to entertain themselves, such as kicking their legs repeatedly. When the first subject is in the self-entertainment state, it indicates that the first subject has an interaction need. Taking the depressed state as an example, when the first subject is in the depressed state, it indicates that the first subject has a comfort need.

[0096] When the first subject is in a target safety state (such as a dangerous state in the action risk state described below), it is determined that the first subject has a safety care need that matches the target safety state, and the target safety state includes a state close to a dangerous area, a state in an unfamiliar environment, a state of encountering an abnormal sound, etc. Taking the state close to a dangerous area as an example, when the first subject is in a state close to a dangerous area, such as the edge of a crib, close to a power socket, at the stairwell, at the edge of a window, etc., it indicates that the first subject has a danger avoidance need.

[0097] In some embodiments, the subject care data is analyzed by a demand analysis model to obtain the subject care needs of the first subject, wherein the demand analysis model is a pre-trained machine learning model, for example, the demand analysis model is a pre-trained neural network model.

[0098] There are different demand analysis methods for different subject care data. The following introduces the demand analysis methods for subject action data, subject expression data, and subject voice data respectively:

[0099] (1) Subject action data.

[0100] In some embodiments, the action data of the subject is analyzed to obtain the action risk state of the first subject. Schematically, the action risk state can be simply divided into a safe state or a dangerous state; the dangerous state can specifically be a state of being close to a dangerous area, encountering an abnormal sound, a falling risk state, a suffocation risk state, etc., which are not limited here.

[0101] Optionally, the demand analysis model includes a motion recognition sub-model, and the subject care data is analyzed by the motion recognition sub-model to determine the motion risk state of the first subject.

[0102] ● Training scheme for the action recognition sub-model

[0103] Illustratively, a first training data set is obtained, which includes a plurality of sample action data, for example, images or videos or sensor acquisition data of a sample subject performing a sample action, each sample action data being annotated with a reference action risk state.

[0104] For a single sample action data, the sample action data is input into a sample action recognition model, and the sample action recognition model can be implemented as at least one of a convolutional neural network (CNN), a long short-term memory network (LSTM), etc. The sample action recognition model extracts the action feature representation of the sample action data, and the action feature representation refers to the characteristics of the sample action performed by the sample subject; then the sample action recognition model analyzes the action feature representation to obtain the predicted action risk state of the sample action. In some embodiments, if the sample action data is implemented as image or video data, the sample action recognition model also extracts the scene feature representation of the sample action data, and the scene feature representation refers to the characteristics of the physical environment in which the sample subject is located; then the sample action recognition model analyzes the action feature representation and the scene feature representation to obtain the predicted action risk state of the sample action. By extracting the scene feature representation and combining it with the action feature representation, the sample action recognition model can consider the influence of the actual scene in which the action occurs on the action type determination, thereby more accurately analyzing the action risk state of the sample action.

[0105] Based on the difference between the predicted action risk state and the reference action risk state, a first loss is obtained, wherein the loss function used to calculate the first loss includes a cross-entropy loss function (Cross-Entropy Loss), a mean square error loss function (Mean-Squared-Error Loss, MSE), etc., which are not limited here; the sample action recognition model is trained by the first loss, that is, the model parameters of the sample action recognition model are updated using the back propagation algorithm and the first loss.

[0106] The sample action recognition model is iteratively trained using multiple sample action data in the first training data set until the sample action recognition model meets the preset training conditions, and the training is stopped. The sample action recognition model obtained at this time is also the action recognition sub-model. The sample action recognition model meets the preset training conditions when: the first loss obtained by the sample action recognition model is less than or equal to the first preset loss, or the number of training times of the sample action recognition model reaches the first preset number of times.

[0107] Optionally, after determining the action risk status of the first subject, a first care requirement is determined as the subject care requirement based on the action risk status of the first subject.

[0108] Schematically, different action risk states correspond to different care needs. A first requirement mapping table is obtained, wherein the first requirement mapping table includes multiple candidate care needs, and each candidate care need is associated with one or more action risk states. Through the first requirement mapping table, a candidate care need that matches the action risk state of the first subject is determined as the first care need, wherein if the first requirement mapping table does not contain a candidate care need that matches the action risk state of the first subject, then there is no first care need.

[0109] (2) Subject expression data.

[0110] In some embodiments, the subject expression data is analyzed to obtain the emotion type of the first subject, where the emotion type may include positive emotions (such as happiness, surprise, etc.) or negative emotions (such as sadness, anger, etc.).

[0111] Optionally, the demand analysis model includes an expression recognition sub-model, and the expression recognition sub-model is used to analyze the subject expression data and determine the emotion type of the first subject.

[0112] ●Training scheme for the expression recognition sub-model

[0113] Schematically, a second training data set is obtained, wherein the second training data set includes a plurality of sample expression data, for example, images or videos of sample subjects under different emotion types, and each sample expression data is annotated with a reference emotion type.

[0114] For a single sample expression data, the sample expression data is input into a sample expression recognition model, which can be implemented as at least one of a convolutional neural network, a residual network (ResNet), etc. The sample expression recognition model extracts the expression feature representation of the sample expression data, and the expression feature representation refers to the feature of the facial expression of the sample subject. Then, the sample expression recognition model analyzes the expression feature representation to obtain the predicted emotion type of the sample expression.

[0115] Based on the difference between the predicted emotion type and the reference emotion type, a second loss is calculated. The loss function used to calculate the second loss may include a cross entropy loss function, a mean square error loss function, etc. The sample expression recognition model is trained by the second loss, that is, the model parameters of the sample expression recognition model are updated by using the back propagation algorithm and the second loss.

[0116] The sample expression recognition model is iteratively trained using multiple sample expression data in the second training data set until the sample expression recognition model meets the preset training conditions, and then the training is stopped. The sample expression recognition model obtained at this time is also the expression recognition sub-model. The preset training condition may refer to: the second loss obtained by the sample expression recognition model is less than or equal to the second preset loss, or the number of training times of the sample expression recognition model reaches the second preset number of times.

[0117] Optionally, after determining the emotion type of the first subject, a second care requirement is determined based on the emotion type of the first subject.

[0118] Schematically, different emotion types correspond to different care needs. A second demand mapping table is obtained, wherein the second demand mapping table includes multiple candidate care needs, and each candidate care need is associated with one or more emotion types. Through the second demand mapping table, a candidate care need that matches the emotion type of the first subject is determined as the second care need, wherein if the second demand mapping table does not include a candidate care need that matches the emotion type of the first subject, then there is no second care need.

[0119] (3) Subject sound data.

[0120] In some embodiments, the subject voice data is analyzed to obtain the voice type of the first subject, and the voice type includes: normal speaking, anxious shouting, sad crying, happy laughter, etc.

[0121] Optionally, the demand analysis model includes a voice recognition sub-model, and the voice recognition sub-model is used to analyze the subject voice data and determine the voice type of the first subject.

[0122] ● Training scheme for the sound recognition sub-model

[0123] Illustratively, a third training data set is obtained, wherein the third training data set includes a plurality of sample sound data, for example, voice records or conversation contents of a sample subject in different emotional states, and each sample sound data is annotated with a reference sound type.

[0124] For a single sample sound data, the sample sound data is input into the sample sound recognition model, which can be implemented as at least one of a recurrent neural network (RNN), a long short-term memory network, a Transformer-based model, etc. The sample sound recognition model extracts the sound feature representation of the sample sound data, and the sound feature representation includes acoustic features (pitch, timbre, volume, speaking speed, intonation, etc.) and semantic features extracted from the sound. For acoustic features, the pitch feature reflects the high and low changes of the sound, the timbre feature can distinguish the uniqueness of the main voice, the volume feature reflects the strength of the sound, the speaking speed and intonation change features show the rhythm and tone changes of the speech, etc.; the semantic feature is the semantic content feature reflected after the sound is converted into text through speech recognition technology. Then, the sample sound recognition model analyzes the sound feature representation to obtain the predicted sound type of the sample sound.

[0125] Based on the difference between the predicted sound type and the reference sound type, a third loss is calculated. The loss function used to calculate the third loss may also include a cross entropy loss function, a mean square error loss function, etc. The sample sound recognition model is trained by the third loss, that is, the model parameters of the sample sound recognition model are updated by using the back propagation algorithm and the third loss.

[0126] The sample sound recognition model is iteratively trained using multiple sample sound data in the third training data set until the sample sound recognition model meets the preset training conditions, and then the training is stopped. The sample sound recognition model obtained at this time is also the sound recognition sub-model. The preset training condition may mean that the third loss obtained by the sample sound recognition model is less than or equal to the third preset loss, or the number of training times of the sample sound recognition model reaches the third preset number of times.

[0127] Optionally, after determining the voice type of the first subject, a third care requirement is determined based on the voice type of the first subject.

[0128] Indicatively, different sound types correspond to different care needs. A third demand mapping table is obtained, which includes multiple candidate care needs, each candidate care need is associated with one or more sound types, for example: emotional comfort needs are associated with sound types such as sad crying, anxious sighs, and angry roars; medical care needs are associated with sound types such as continuous coughing, wheezing, and painful groans. Through the third demand mapping table, a candidate care need that matches the sound type of the first subject is determined as the third care need, wherein if the third demand mapping table does not contain a candidate care need that matches the sound type of the first subject, then there is no third care need.

[0129] For the training scheme described above, optionally, the sample subjects in the first training data set, the second training data set and the third training data set can be implemented as the first subject, that is, the above-mentioned demand analysis model is a model constructed for the first subject. For example: in the scenario of caring for infants and young children, the first subject refers to the infant and young child, and the first training data set is constructed using images or videos or sensor collection data of the infant and young child making various actions (such as crawling, reaching out, turning over, etc.) to train the action recognition sub-model so that it can judge whether the infant and young child's actions are safe; collect images and video data of infants and young children showing different expressions (happy, sad, sleepy, etc.) to form a second training data set, and train the expression recognition sub-model to identify their emotional state; then collect audio data of various sounds made by infants and young children (crying, babbling, laughing, etc.) to construct a third training data set, and train the sound recognition sub-model to identify their sound types.

[0130] In some embodiments, if only the first care need is identified, the first care need will be used as the main care need; if only the second care need is identified, the second care need will be used as the main care need; if only the third care need is identified, the third care need will be used as the main care need.

[0131] In some embodiments, if at least two of the first care need, the second care need, and the third care need are identified, the at least two identified care needs are used as the main care needs. Optionally, different care needs have different demand priorities, and the demand priorities are used to characterize the urgency of the care needs. Schematically, the demand priority of the safety care need is greater than the demand priority of the psychological care need. The demand priority can be used to determine the care feedback operation later.

[0132] In some embodiments, the subject care need of the first subject is determined based on at least one of the action risk state of the first subject, the emotion type of the first subject, and the voice type of the first subject.

[0133] The following is an example of determining the subject care needs of the first subject based on the action risk state of the first subject, the emotion type of the first subject, and the voice type of the first subject.

[0134] Optionally, the subject action data is analyzed to obtain the action risk state of the first subject; the subject expression data is analyzed to obtain the emotion type of the first subject; the subject voice data is analyzed to obtain the voice type of the first subject; and based on the action risk state of the first subject, the emotion type of the first subject and the voice type of the first subject, the subject care needs of the first subject are determined.

[0135] In some embodiments, the demand analysis model includes a demand identification sub-model, which analyzes the action risk state of the first subject, the emotion type of the first subject, and the voice type of the first subject to determine the subject care needs of the first subject.

[0136] For illustration, please refer to Figure 5 , which shows an overall flow chart of obtaining the subject's care needs through the needs analysis model, such as Figure 5 As shown, the demand analysis model includes an action recognition sub-model 510 , an expression recognition sub-model 520 , a sound recognition sub-model 530 and a demand recognition sub-model 540 .

[0137] (1) Action recognition sub-model 510.

[0138] The subject action data is input into the action recognition sub-model 510, the action feature representation of the subject action data is extracted, and the action feature representation is analyzed to obtain the action risk state of the first subject; or the action feature representation and scene feature representation of the subject action data are extracted, and the action feature representation and scene feature representation are analyzed to obtain the action risk state of the first subject.

[0139] (2) Expression recognition submodule 520.

[0140] The subject expression data is input into the expression recognition sub-model 520, the expression feature representation of the subject expression data is extracted, and the expression feature representation is analyzed to obtain the expression type of the first subject.

[0141] (3) Sound recognition sub-model 530.

[0142] The subject voice data is input into the voice recognition sub-model 530, the voice feature representation of the subject voice data is extracted, and the voice feature representation is analyzed to obtain the voice type of the first subject.

[0143] (4) Demand identification sub-model 540.

[0144] The action risk state of the first subject, the emotion type of the first subject and the voice type of the first subject are input into the demand recognition sub-model to obtain the subject care demand of the first subject.

[0145] ●Training scheme for demand identification sub-model

[0146] In an illustrative manner, a fourth training data set is obtained, wherein the fourth training data set includes a plurality of sample data combinations, for example, the sample data combination includes the action risk state, emotion type and sound type corresponding to the sample subject. Each sample data combination is annotated with one or more reference care demand types.

[0147] For a single sample data combination, the sample data combination is input into a sample demand recognition model. The sample demand recognition model can be implemented as at least one of a convolutional neural network, a recurrent neural network, a long short-term memory network, a Transformer-based model, and the like.

[0148] Optionally, the sample demand recognition model includes an input layer, a hidden layer and an output layer, in which the action risk state, emotion type and sound type corresponding to the sample subject are mapped to a sample vector representation in the input layer; the sample vector representation is input into the hidden layer, and the sample feature representation corresponding to the sample vector representation is extracted through the hidden layer; then the sample feature representation is input into the output layer, and the output layer usually includes multiple neurons, each neuron corresponds to a care demand category, and the sample feature representation is analyzed by multiple neurons to obtain a predicted probability distribution, which is used to characterize the probability that the sample data combination belongs to each care demand category, and the reference probability distribution is determined according to the reference care demand type marked by the sample data combination, and the probability corresponding to the reference care demand type in the reference probability distribution is 1, and the others are 0; based on the difference between the predicted probability distribution and the reference probability distribution, the fourth loss is determined, and the loss function used to calculate the fourth loss may include a cross entropy loss function, a mean square error loss function, etc. The sample demand recognition model is trained by the fourth loss, that is, the model parameters of the sample demand recognition model are updated using the back propagation algorithm and the fourth loss.

[0149] The sample demand identification model is iteratively trained using multiple sample data combinations in the fourth training data set until the sample demand identification model meets the preset training conditions, and then the training is stopped. The sample demand identification model obtained at this time is also the demand identification sub-model. The preset training condition may refer to: the fourth loss obtained by the sample demand identification model is less than or equal to the fourth preset loss, or the number of training times of the sample demand identification model reaches the fourth preset number of times.

[0150] In other embodiments, the subject's care needs may also be obtained by directly and comprehensively analyzing the subject's action data, the subject's expression data, and the subject's voice data through the need recognition model.

[0151] Optionally, the subject action data, the subject expression data, and the subject voice data of the first subject are input into the demand analysis model to obtain the subject care needs of the first subject. The training process of the demand analysis model can refer to the training process of the demand identification sub-model, which will not be repeated here.

[0152] In the above embodiment, by analyzing the subject's motion data, the subject's expression data, and the subject's voice data respectively, the needs of the first subject are determined from multiple different dimensions such as motion risk status, emotion type, and voice type, thereby obtaining a more comprehensive and accurate subject care needs.

[0153] Step 430, performing a care feedback operation that matches the subject's care needs.

[0154] The care feedback operation is used to respond to the subject's behavior, that is, the care feedback operation is a targeted measure taken according to the needs of the first subject.

[0155] Optionally, the nursing feedback operation includes at least one of the following operations:

[0156] (1) Requirement prompt operation.

[0157] The demand prompting operation is used to prompt the first subject's subject care needs. Schematically, the demand prompting operation refers to an operation of prompting a caregiver of the first subject's subject care needs.

[0158] The demand prompt operation includes at least one of a visual prompt, an auditory prompt, a tactile prompt, etc. The embodiment of the present application does not limit the specific prompt content of the demand prompt operation.

[0159] Illustratively, with regard to visual cues, if an infant approaches a dangerous area (indicating that the infant has a need to avoid danger), the care device can light up a striking red warning light and display an image of a prohibition sign to attract the caregiver's attention; if the infant has a need to eat, the care device can flash a soft white or light blue light to attract the caregiver's attention. Optionally, an image of a bottle or food can be displayed in the light projection area near the crib to clearly inform the caregiver that feeding operations need to be performed.

[0160] For auditory prompts, corresponding voices are issued according to the different care needs of infants and young children. For example, when the infant's diaper may need to be changed, the voice prompt content is "The baby's diaper is wet, please change it in time"; when the infant is close to a dangerous area, the voice prompt will use a more urgent tone, and the voice prompt content is "Attention! The baby is in danger."

[0161] For tactile prompts, the smart wearable device (watch or bracelet) worn by the caregiver can receive tactile prompts. When the infant or toddler needs care, the device will vibrate.

[0162] (2) Nursing interaction operations.

[0163] The care interaction operation is used to interact with the first subject to meet the subject care needs of the first subject.

[0164] Among them, the interactive forms of nursing interactive operations include at least one of voice interaction, video interaction, game interaction, learning interaction, etc.

[0165] For example, taking voice interaction as an example, when infants and young children are in a bad mood, appropriate nursery rhymes or conversations can be played to soothe them.

[0166] In some embodiments, if it is identified that the first subject has multiple subject care needs, the care feedback operation is determined according to the demand priorities corresponding to the multiple subject care needs.

[0167] In schematic form, the care feedback operations corresponding to the care needs of multiple subjects are determined according to the demand priorities corresponding to the care needs of multiple subjects. The multiple care feedback operations have corresponding operation priorities, and the demand priority is positively correlated with the operation priority. The higher the operation priority, the earlier the care feedback operation is executed. For example, if the operation priority of care feedback operation a is higher than the operation priority of care feedback operation b, then care feedback operation a is executed first and then care feedback operation b.

[0168] Step 440 , generating nursing log data based on the subject nursing data.

[0169] The care log data is used to record the subject's historical behavior of the first subject.

[0170] In some embodiments, the nursing log data includes behavior-recording nursing log data, which is used to record information such as the specific behavior of the first subject and the time when the behavior occurred.

[0171] Optionally, when the subject care data indicates that the first subject performs a preset behavior, target behavior data is acquired to generate care log data, where the target behavior data refers to data collected when the first subject performs the preset behavior.

[0172] The execution of the preset behavior includes at least one of executing a preset action, showing a preset expression, making a preset sound, etc. The target behavior data can be implemented in various forms such as images, videos, and audio.

[0173] Indicatively, when a specific action, expression or sound of an infant is detected (such as smiling, yawning, stretching, etc., which can be set by the user or by the system default), the care device will obtain images or videos of infants performing specific actions or expressions. Then, the acquired images and videos are classified and a growth album is generated. For example, according to the action and expression category, all smiling moments are classified into one category, yawning into one category, and stretching into another category. This makes it easy for caregivers to quickly locate and review the appearance of infants in different emotions and states. Alternatively, it can also be classified in chronological order, with daily, weekly or monthly records grouped separately, so that the growth album presents a clear time context. Optionally, the growth album supports timeline display and tag management, which is convenient for caregivers to review and share.

[0174] In the above embodiment, the target behavior data of the first subject when performing the preset behavior is accurately captured through the subject care data, and the care log data is generated accordingly. Compared with traditional manual records, it is more accurate, can reduce the interference of human factors, and improve the accuracy and reliability of the records.

[0175] In some embodiments, the nursing log data also includes at least one of emotion-recording nursing log data, social-interaction nursing log data, and the like.

[0176] The emotion recording nursing log data refers to the record of the emotional state of the first subject, and includes information such as the emotion type (such as happiness, sadness, anger, calmness, etc.), the frequency and duration of the emotion. When the subject nursing data indicates that the first subject is in the target emotional state, the emotion type of the target emotional state, the frequency of occurrence of the target emotional state, the duration information of the target emotional state, etc. are recorded to generate the nursing log data.

[0177] The social interaction care log data is used to record the interaction between the first subject and other subjects (people or pets), and includes information such as the start and end time of the interaction, the interaction object, and the interaction type (such as conversation, hug, play, etc.). When the subject care data indicates that the first subject has the target interaction behavior, the start and end time of the interaction, the interaction object, the interaction type, etc. of the target interaction behavior are recorded to generate the care log data.

[0178] It should be noted that the above examples of nursing log data are only for illustrative purposes and are not limited here.

[0179] Optionally, after the nursing log data is generated, in response to receiving a viewing operation on the nursing log data, the nursing log data is displayed on the nursing terminal. Schematically, when the caregiver clicks the "view log" button on the first application of the nursing terminal, the nursing terminal will display the nursing log data. Taking the behavior recording nursing log data as an example, the nursing log data is presented in the form of a timeline, so that the caregiver can clearly see the behavior of the first subject at different time points. Taking the emotion recording nursing log data as an example, the nursing log data is presented in the form of a chart, such as showing an emotion change curve, the horizontal axis is time, and the vertical axis is the emotion value (the emotion result quantified by the target algorithm). Taking the social interaction nursing log data as an example, the nursing log data is displayed in a timeline plus card layout, and the time point of each social interaction is clearly marked on the timeline. The corresponding card displays the avatar or nickname of the interactive object, as well as a brief description of the interaction. Clicking the card can expand to view the complete interactive video record or detailed text record, including some key dialogue content and the changes in the subject's expression during the interaction.

[0180] In summary, the care method provided by the embodiment of the present application, after the device collects the subject care data of the subject in the physical environment, will analyze the subject care data to determine the demand information expressed by the subject through behavior, so that the device can perform care feedback operations that match the subject's needs. On the one hand, the device can automatically collect and analyze the subject care data, and perform corresponding care feedback operations, reducing labor costs and improving care efficiency; on the other hand, by determining the needs expressed by the subject's behavior, the device can avoid blindly performing care feedback, so that the care feedback operation matches the actual needs of the subject, reducing invalid or erroneous care feedback operations, improving care accuracy, and helping to improve care quality. In addition, the device can also generate a care log by analyzing the subject care data, thereby automatically recording the subject's behavior at different time nodes. Relevant personnel can quickly understand the subject's situation through the care log, improving the efficiency of human-computer interaction.

[0181] In some embodiments, the care feedback operation is used to prompt the first subject's care needs. For example, please refer to Figure 6 , Figure 4 The illustrated embodiment may also be implemented as the following steps 610 to 640 .

[0182] Step 610, collecting subject care data of the first subject.

[0183] The subject care data includes data collected by the collection component from the physical environment containing the first subject. The subject care data is used to characterize the subject behavior generated by the first subject's activities in the physical environment.

[0184] Optionally, the subject care data includes at least one of subject action data, subject expression data and subject sound data.

[0185] Step 620 , determining the subject care needs of the first subject based on the subject care data.

[0186] The subject care demand refers to the feedback demand expressed by the first subject through the subject behavior.

[0187] Optionally, the subject action data is analyzed to obtain the action risk state of the first subject; the subject expression data is analyzed to obtain the emotion type of the first subject; the subject voice data is analyzed to obtain the voice type of the first subject; and based on the action risk state of the first subject, the emotion type of the first subject and the voice type of the first subject, the subject care needs of the first subject are determined.

[0188] In some embodiments, according to the current growth stage of the first subject, a first weight corresponding to the action risk state of the first subject, a second weight corresponding to the emotion type of the first subject, and a third weight corresponding to the voice type of the first subject are determined; based on the first weight, the second weight and the third weight, the subject care needs of the first subject are determined.

[0189] Optionally, the demand analysis model includes an action recognition sub-model, an expression recognition sub-model, a sound recognition sub-model and a demand recognition sub-model. The action risk state of the first subject is obtained by analyzing the subject action data through the action recognition sub-model, the emotion type of the first subject is obtained by analyzing the subject expression data through the expression recognition sub-model, and the voice type of the first subject is obtained by analyzing the subject voice data through the sound recognition sub-model; the action risk state of the first subject, the emotion type of the first subject and the voice type of the first subject are analyzed through the demand recognition sub-model to obtain the subject care needs of the first subject.

[0190] Indicatively, the growth stage refers to the age group of the first subject, for example, the growth stage of infants and young children is divided into the neonatal period (0-3 months), infant period (4-12 months), toddler period (13-36 months), etc. At different growth stages, the first subject's motor ability, emotional expression and voice characteristics will be different, so their care needs will also be different.

[0191] In the embodiment of the present application, when determining the care needs of the subject, the weights corresponding to the action risk state, emotion type, and sound type of the first subject are determined according to the characteristics of different growth stages.

[0192] Indicatively, a detailed rule base is established for different growth stages. For example, in the neonatal period, the first weight corresponding to the action risk state is set to a higher value (such as 0.6), the second weight corresponding to the emotion type is moderate (such as 0.3), and the third weight corresponding to the sound type is lower (such as 0.1). In the infant period, the weights are adjusted accordingly, for example, the first weight of the action risk state is set to 0.5, the second weight of the emotion type is set to 0.3, and the third weight of the sound type is set to 0.2. The different weight values ​​are reasonably determined according to the development and change laws of various aspects of the subject at each stage. Optionally, the growth stage of the first subject is identified, and the weight corresponding to the growth stage is extracted from the rule base.

[0193] After determining the first weight, the second weight and the third weight, based on the first weight, the second weight and the third weight, the action risk state, emotion type and sound type are analyzed from the dimensions of safety care needs, psychological care needs and physiological care needs, respectively, to obtain the first need score, the second need score and the third need score; the first need score is used to characterize the probability that the first subject has a safety care need, the second need score is used to characterize the probability that the first subject has a psychological care need, and the third need score is used to characterize the probability that the first subject has a physiological care need.

[0194] Among them, the dimension of safety care needs can be a general dimension of all safety care needs, or a specific dimension of a safety care need. The dimension of psychological care needs can be a general dimension of all psychological care needs, or a specific dimension of a psychological care need. The dimension of physiological care needs can be a general dimension of all physiological care needs, or a specific dimension of a physiological care need.

[0195] Illustratively, the demand identification sub-model will analyze from the dimensions of safety care needs, psychological care needs, and physiological care needs based on the first weight, the second weight, and the third weight, respectively, to obtain a first demand score.

[0196] The trained demand identification sub-model includes algorithm logic for safety care needs, algorithm logic for physiological care needs, and algorithm logic for psychological care needs.

[0197] Taking the algorithm logic for safe care needs as an example, in the demand identification sub-model, sub-demand score 1 will be determined based on the action risk state, sub-demand score 2 will be determined based on the emotion type, and sub-demand score 3 will be determined based on the sound type. Sub-demand score 1 represents the demand degree score corresponding to the action risk state of the first subject under the dimension of safe care needs. Sub-demand score 2 represents the demand degree score corresponding to the emotion type of the first subject in terms of safe care needs. Sub-demand score 3 represents the demand degree score corresponding to the sound type of the first subject from the perspective of safe care needs. Then, the first weight, second weight and third weight are used to weightedly sum sub-demand score 1, sub-demand score 2 and sub-demand score 3 to obtain the first demand score.

[0198] The algorithm logic for physiological care needs and the algorithm logic for psychological care needs are similar to the algorithm logic for safety care needs. Therefore, the instructions for determining the second need score and determining the third need score can refer to the above instructions for determining the first need score, and will not be repeated here.

[0199] After determining the first need score, the second need score, and the third need score, determining the subject care need of the first subject according to the first need score, the second need score, and the third need score. Optionally, for the method of determining the subject care need of the first subject, the method includes at least one of the following methods:

[0200] (1) When the first need score is greater than the first preset score, the safety care need is determined as the main care need; when the second need score is greater than the second preset score, the psychological care need is determined as the main care need; when the third need score is greater than the third preset score, the physiological care need is determined as the main care need.

[0201] (2) Determine the subject care needs of the first subject according to the score intervals to which the first need score, the second need score, and the third need score respectively belong.

[0202] Indicatively, the value range of each demand score is divided into different level intervals. For example, for the first demand score, 0-0.3 is a low safety care demand level, 0.3-0.6 is a medium safety care demand level, and 0.6-1 is a high safety care demand level; similar divisions are also made for the second and third demand scores, such as 0-0.4 is a low psychological / physiological care demand level, 0.4-0.7 is a medium psychological / physiological care demand level, and 0.7-1 is a high psychological / physiological care demand level. The main care needs are determined according to the combination of the level intervals of the three demand scores. For example, when the first demand score is at a low level, the second demand score is at a high level, and the third demand score is at a medium level, the main care needs can be determined as "focusing on psychological comfort on the basis of paying attention to physiological conditions, while maintaining basic attention to safety." This method can more carefully determine the care strategy based on different score combinations.

[0203] In the above embodiment, by determining the weights corresponding to different behavioral performances based on the current growth stage of the first subject, the differences in motor ability, emotional expression, and voice characteristics among individuals of different age groups are fully considered, thereby achieving personalized care for individuals at different growth stages, avoiding the use of unified standards while ignoring the unique needs of each stage, and improving the accuracy of the determined care needs.

[0204] Step 631, determining the content of the demand prompt based on the subject's care needs.

[0205] The demand prompt content is used to prompt the subject care needs of the first subject.

[0206] Optionally, the content of the requirement prompt content includes at least one of image, text, video, audio, etc., which is not limited here.

[0207] In some embodiments, the above method is performed by a caregiver terminal installed in a physical environment containing the first subject.

[0208] Optionally, environmental data corresponding to the physical environment including the first subject is obtained; when the environmental data indicates that there is a second subject within the preset range of the first subject, voice prompt information is determined as the demand prompt content based on the subject's care needs, and the voice prompt information is used to indicate the voice played by the care terminal; when the environmental data indicates that there is no second subject within the preset range of the first subject, a remote prompt message is determined as the demand prompt content based on the subject's care needs, and the remote prompt message is used to indicate the prompt message sent by the care terminal to the first terminal.

[0209] Optionally, the environmental data includes a first coordinate position of a first subject in the physical environment. When the first subject is detected to exist in the physical environment, the second coordinate position of the second subject in the physical environment is obtained; based on the first coordinate position and the second coordinate position, it is determined whether the second subject is within a preset range of the first subject. It is assumed that the preset range of the first subject is a circular area with the first subject as the center and a preset distance as the radius. If the second subject is within the circular area, it means that the environmental data indicates that the second subject exists within the preset range of the first subject. If the second subject is outside the circular area, it means that the environmental data indicates that the second subject does not exist within the preset range of the first subject.

[0210] Optionally, the first coordinate position of the first subject in the physical environment, whether the first subject exists in the physical environment, and the second coordinate position of the second subject in the physical environment are determined through images or videos captured by the camera of the nursing terminal.

[0211] Indicatively, if the caregiver is in the room where the infant is (that is, there is a second subject within the preset range of the first subject), the care terminal will generate a voice prompt based on the current subject care needs. For example, if the infant is detected to have signs of hunger, the voice prompt can be "Baby is hungry". This voice prompt is a voice prompt played in real time by the care terminal, which clearly informs the caregiver of the specific needs of the infant at the moment through voice prompts, so that the caregiver can take timely action.

[0212] If the caregiver is not in the room where the infant is (that is, there is no second subject within the preset range of the first subject), the care terminal will generate a remote reminder message based on the subject's care needs. The remote reminder message is a message used to send to the first terminal (such as a mobile device such as the caregiver's mobile phone). Optionally, different message priorities and push methods are set according to the priority of the subject's care needs. For example, in an emergency involving the life safety of an infant (such as abnormal breathing, severe falls, etc.), the remote reminder message will be set to the highest priority, and a strong reminder method of pop-up windows, vibration and ringtones will be used to ensure that the caregiver can receive the message and take action as soon as possible.

[0213] In the above embodiment, whether the second subject is within the preset range of the first subject is determined based on environmental data, and then different prompting methods are used. When the second subject is within the preset range, voice prompt information is selected to directly attract attention on the spot, making it convenient for nearby caregivers to quickly know the needs and take action; and when the second subject is not within the preset range, a remote prompt message is used to ensure that the relevant caregivers who are not on site (such as remote family members, medical staff on duty, etc.) receive the subject's demand information in a timely manner, realizing accurate adaptation of prompting methods according to actual scenarios, and avoiding the problem of insufficient information transmission that may be caused by a unified prompt method.

[0214] Step 632: Execute a demand prompt operation on the demand prompt content as a nursing feedback operation.

[0215] Indicatively, the demand prompt content mainly prompts the caregiver of the corresponding subject care needs in different forms, and the demand prompt operation is to present the demand prompt content in an appropriate manner.

[0216] Optionally, the demand prompt operation includes at least one of a visual prompt, an auditory prompt, and a tactile prompt. For instructions on the demand prompt operation, please refer to step 430 and will not be repeated here.

[0217] In some embodiments, the nursing terminal is associated with the first terminal. After generating the demand prompt information, a demand prompt request is sent to the first terminal based on the demand prompt information. The demand prompt request is used to request to present the demand prompt content on the first terminal. The first terminal is used to present the demand prompt information after receiving the demand prompt request.

[0218] Step 640 , generating nursing log data based on the subject nursing data.

[0219] The care log data is used to record the subject's historical behavior of the first subject.

[0220] To sum up, in the care method provided in the embodiment of the present application, after the device collects the subject care data of the subject in the physical environment, it will analyze the subject care data to determine the demand information expressed by the subject through behavior. The device will generate demand prompt content based on the demand information, and then execute the demand prompt operation on the demand prompt content, thereby conveying the subject's needs to the corresponding caregivers and ensuring the timeliness of the care response.

[0221] In some embodiments, the nursing feedback operation is used to indicate the interaction operation with the first subject. For example, please refer to Figure 7 , Figure 4 The illustrated embodiment may also be implemented as the following steps 710 to 740 .

[0222] Step 710, collecting subject care data of the first subject.

[0223] The subject care data includes data collected by the collection component from the physical environment containing the first subject. The subject care data is used to characterize the subject behavior generated by the first subject's activities in the physical environment.

[0224] Optionally, the subject care data includes at least one of subject action data, subject expression data and subject sound data.

[0225] Step 720 , determining the subject care needs of the first subject based on the subject care data.

[0226] The subject care demand refers to the feedback demand expressed by the first subject through the subject behavior.

[0227] Step 731, determining equipment operation instructions based on the subject's care needs.

[0228] The device operation instruction is used to control the nursing terminal to perform the nursing interaction operation, and the nursing interaction operation is used to meet the subject nursing needs of the first subject.

[0229] Optionally, the device operation instructions include at least one of instructions corresponding to voice interaction, instructions corresponding to learning interaction, instructions corresponding to game interaction, etc. Illustratively, the instructions corresponding to voice interaction can be implemented as playing nursery rhymes, playing story interpretation, etc., and the instructions corresponding to learning interaction can be implemented as infant learning interaction, pinyin teaching interaction, etc.

[0230] Optionally, different subject care needs correspond to different device operation instructions. The method for determining device operation instructions based on subject care needs also includes: obtaining a preset instruction library, in which each subject care need in the preset instruction library corresponds to one or more device operation instructions; and obtaining corresponding device operation instructions from the preset instruction template library according to the currently determined subject care needs.

[0231] In some embodiments, the device operation instruction may also be adjusted according to the target parameter to obtain the adjusted device operation instruction as the currently determined device operation instruction.

[0232] The target parameters include at least one of the following parameters:

[0233] (1) Subject-related parameters.

[0234] Optionally, the subject-related parameters include at least one of growth stage, preference information, etc.

[0235] Indicatively, for the growth stage, subjects of different ages have different cognitive levels, interest preferences and receptive abilities. For example, for infants and young children, the instructions corresponding to the learning interaction can be adjusted to make it simpler, more intuitive and interesting, such as colorful simple graphic cognitive interactions. For preference information, by analyzing the records of the subject's past participation in care interaction operations, we can understand the types of interactions and specific content that the subject often chooses. For example, if the subject has chosen to play a certain type of story interpretation many times in the past, the instructions corresponding to the voice interaction can be adjusted to give priority to pushing story interpretation content of similar style or the same series.

[0236] (2) Environmental related parameters.

[0237] Optionally, the environment-related parameters include at least one of noise level, space size, etc.

[0238] Indicatively, for the noise level, if the physical environment is noisy, the corresponding instructions for voice interaction need to be adjusted to increase the volume of voice playback, or choose a more recognizable voice timbre to ensure that the subject can clearly hear the interactive voice content. For the size of the space, the size of the space will affect the selection and implementation of game interaction. Adjust the corresponding instructions for voice interaction so that its activity range adapts to the size of the space in the current physical environment.

[0239] It should be noted that the above examples of target parameters are only for illustrative purposes and are not intended to be limiting.

[0240] Step 732, performing a nursing interaction operation as a nursing feedback operation according to the device operation instruction.

[0241] The interactive form of the nursing interaction operation includes at least one of voice interaction, game interaction, learning interaction, etc. For a detailed description of the nursing interaction operation, please refer to step 430, which will not be described in detail here.

[0242] The above-mentioned nursing interaction operation is an interactive operation automatically determined according to the subject's nursing needs. In other embodiments, the nursing interaction operation can also be an operation actively triggered by the user. Optionally, in response to receiving the interactive triggering operation, a device operation instruction is generated based on the interactive triggering operation; and the nursing interaction operation is executed according to the device operation instruction.

[0243] Step 740 , generating nursing log data based on the subject nursing data.

[0244] The care log data is used to record the subject's historical behavior of the first subject.

[0245] To sum up, in the care method provided in the embodiment of the present application, after the device collects the subject care data of the subject in the physical environment, it will analyze the subject care data to determine the demand information expressed by the subject through behavior. The device will generate device operation instructions based on the demand information, and then execute the care interaction operations corresponding to the device operation instructions, so as to quickly respond to the needs of the subject, reduce the waiting time of the subject, avoid the situation where the needs are ignored or delayed, and ensure the timeliness of the care work.

[0246] In some embodiments, the above-mentioned nursing terminal can be implemented as a nursing robot (i.e. Figure 3 The intelligent robot shown is schematic, please refer to Figure 8 , Figure 4 The illustrated embodiment may also be implemented as the following steps 810 to 840 .

[0247] Step 810, collecting subject care data of the first subject.

[0248] The subject care data includes data collected by the collection component from the physical environment containing the first subject. The subject care data is used to characterize the subject behavior generated by the first subject's activities in the physical environment.

[0249] Optionally, the subject care data includes at least one of subject action data, subject expression data and subject voice data. The acquisition component can be implemented as a camera, microphone, sensor, etc. installed on the care robot.

[0250] Step 820, determining the subject care needs of the first subject based on the subject care data.

[0251] The subject care demand refers to the feedback demand expressed by the first subject through the subject behavior.

[0252] Step 831, determining robot control instructions based on the subject's care needs.

[0253] Among them, the robot control instructions are used to control the nursing robot.

[0254] Optionally, the voice control content and the motion control content are determined based on the subject's care needs, the voice control content is used to instruct the voice to be played by the care robot, and the motion control content is used to instruct the actions to be performed by the care robot; based on the voice control content and the motion control content, the robot control instructions are determined.

[0255] (1) Determine robot control instructions based on physiological care needs.

[0256] Indicatively, when the infant is detected to have signs of hunger (i.e., the need to eat), the action control content and voice control content are determined. The action control content is used to control the robot to move to the designated location where infant food and tableware are stored, accurately grab the appropriate milk bottle or food container and the matching feeding utensils, and then move smoothly to the appropriate feeding position next to the infant. The voice control content is used to let the robot say soothing words such as "Baby, are you hungry? Let's eat." During the feeding process, according to the preset feeding amount and time interval, the caregiver is reminded in time or the robot is controlled to pause and continue the feeding action.

[0257] If the infant is judged to be sleepy (i.e., has a need for sleep), the action control content and voice control content are determined. The action control content is used to allow the robot to assist in adjusting the sleeping environment, such as closing the curtains, dimming the lights, and then gently pushing the crib to a quiet and comfortable corner. The voice control content is used to play soft lullabies to help infants fall asleep. During sleep, the robot can also continuously monitor the surrounding noise and temperature, and once an abnormality occurs, it will remind the caregiver to make adjustments through voice or action.

[0258] (2) Determine robot control instructions based on safety care requirements.

[0259] Schematically, when the robot detects that an infant is approaching a dangerous area (such as at the stairwell, near a power socket, where sharp objects are placed, etc.), it determines the action control content and voice control content. The action control content is used to enable the robot to move quickly between the infant and the dangerous area to form a physical barrier to prevent the infant from getting closer. The voice control content can be implemented as "Baby, danger, can't go over." Optionally, the robot can also send an alarm message to the caregiver's mobile phone or other terminal to inform the location and time of the dangerous situation. If the infant tries to bypass the robot and continue to approach the dangerous area, the robot can take further action, such as extending a robotic arm (if available) to gently carry the infant away from the dangerous area, or attracting the infant's attention by making specific sounds or flashing lights to guide it to a safe area.

[0260] If the robot detects small foreign objects around infants and young children (such as small objects that may be swallowed by mistake, soft objects that may cause suffocation, etc.), it determines the action control content and voice control content. The action control content is used to allow the robot to quickly approach and pick up the foreign object and place it in a safe high place or storage container. The voice control content is used to tell infants and young children "this thing cannot be played with, it will be dangerous." Optionally, during daily care, the concept of which objects are dangerous and cannot be touched is conveyed to infants and young children through voice and action demonstrations to strengthen the safety awareness of infants and young children.

[0261] (3) Determine robot control instructions based on psychological care needs.

[0262] Indicatively, when infants and young children are alone and need company (such as not interacting with others for a long time, showing boredom or loneliness), the motion control content and voice control content are determined. The motion control content is used to enable the robot to start various interactive game modes. For example, the robot can start a simple ball-catching game, throw the ball to the infant through precise motion control, and accurately catch the ball when the infant throws it back. The voice control content is used to continuously interact with the infant and young children by voice during the game.

[0263] In the above scheme, by determining the voice control content and the action control content, the care robot can use voice and action to interact with the cared subject at the same time, thereby improving the richness and effectiveness of the interaction and improving the efficiency of the interaction.

[0264] Step 832, executing the first control operation corresponding to the robot control instruction as a nursing feedback operation.

[0265] Illustratively, the motion control operation corresponding to the motion control content in the robot control instruction is executed, and the voice control operation corresponding to the voice control content in the robot control instruction is executed.

[0266] Optionally, interactive feedback information corresponding to the first subject within a historical time period is obtained, where the historical time period refers to a time period in which the care robot performs a first control operation, and the interactive feedback information is used to characterize the state of the first subject within the historical time period in which the care robot performs the first control operation; the robot control instructions are adjusted based on the interactive feedback information; and a second control operation is performed according to the adjusted robot control instructions.

[0267] The interactive feedback information includes at least one of visual feedback information, auditory feedback information, physiological data feedback information, etc.

[0268] Indicatively, during the historical time period when the nursing robot performs the first control operation, the interactive feedback information corresponding to the first subject (infant) is collected. For example, for visual feedback information, the camera installed in the room or the visual sensor carried by the robot itself is used to observe the facial expressions and body movements of the infant. These visual information can directly reflect the emotional state and participation enthusiasm of the infant at that time. For auditory feedback information, sound-related feedback information is collected with the help of a microphone. For physiological data feedback information, physiological data, such as heart rate data, are collected through smart devices worn by infants (such as smart bracelets, foot rings, etc.).

[0269] After determining the interactive feedback information, the robot control instructions are adjusted to better meet the needs of infants and young children and improve the effect of nursing interaction. For example: If the feedback information shows that the infant is in a bad mood, such as crying frequently or looking bored, the robot control instructions can be adjusted to prioritize the operation of soothing emotions. For example, the instructions are changed to control the robot to play soft and soothing music, and tell simple bedtime stories in a gentle tone to help infants and young children calm down. For another example, when it is found that infants and young children are not highly involved in the current operation, and are slow in movement and lack of concentration in game interaction, the difficulty or form of the game can be adjusted according to the specific situation.

[0270] It should be emphasized that instruction adjustment is not a one-time process, but a dynamic and continuous optimization process. For example, after the adjustment, continue to observe the feedback information of infants and young children, further adjust the instructions based on the feedback information, and continuously optimize the interactive operation to make it more suitable for the status and needs of infants and young children.

[0271] Step 840 , generating nursing log data based on the subject nursing data.

[0272] The care log data is used to record the subject's historical behavior of the first subject.

[0273] Optionally, the nursing log data is displayed. Schematically, a screen component is installed on the nursing robot, and in response to receiving a viewing operation on the nursing log data, the nursing log data is displayed on the screen component.

[0274] To sum up, the nursing method provided in the embodiment of the present application can be executed by a nursing robot. The nursing robot can perform rich first control operations according to the control instructions, create a multi-dimensional interactive scene, thereby increasing the richness and effectiveness of the interaction, and the nursing robot can accurately perform nursing operations according to the control instructions generated by the system, thereby improving the nursing effect.

[0275] It should be noted that the sequence of the method steps provided in the embodiments of the present application can be appropriately adjusted, and the steps can be increased or decreased accordingly according to the circumstances. Any technician familiar with the technical field can easily think of the changed methods within the technical scope disclosed in the present application, and they should be included in the protection scope of the present application, so they will not be repeated here.

[0276] Fig. 9 FIG. 1 is a schematic diagram of a nursing device provided by an exemplary embodiment of the present application. Fig. 9 As shown, the device comprises:

[0277] A data collection module 910 is used to collect subject care data of a first subject, wherein the subject care data includes data collected by a collection component on a physical environment containing the first subject, and the subject care data is used to characterize subject behavior generated by the first subject's activities in the physical environment;

[0278] A data processing module 920, configured to determine a subject care demand of the first subject based on the subject care data, wherein the subject care demand refers to a feedback demand expressed by the first subject through the subject behavior;

[0279] An operation execution module 930, configured to execute a care feedback operation matching the care demand of the subject, wherein the care feedback operation is used to respond to the subject's behavior;

[0280] The data generation module 940 is used to generate nursing log data based on the subject nursing data, and the nursing log data is used to record the subject historical behavior of the first subject.

[0281] In some embodiments, the subject care data includes at least one of the following data:

[0282] Subject action data, the subject action data being used to indicate an action performed by the first subject in the physical environment;

[0283] Subject expression data, the subject expression data is used to indicate the facial expression of the first subject;

[0284] Subject sound data, where the subject sound data is used to indicate the sound emitted by the first subject in the physical environment.

[0285] In some embodiments, the subject care data includes subject action data, subject expression data and subject voice data; the data processing module 920 is used to:

[0286] Analyzing the subject action data to obtain the action risk state of the first subject;

[0287] Analyzing the subject expression data to obtain the emotion type of the first subject;

[0288] Analyzing the subject voice data to obtain the voice type of the first subject;

[0289] A subject care need of the first subject is determined based on the action risk state of the first subject, the emotion type of the first subject, and the voice type of the first subject.

[0290] In some embodiments, the data processing module 920 is used to:

[0291] Determine, according to the current growth stage of the first subject, a first weight corresponding to the action risk state of the first subject, a second weight corresponding to the emotion type of the first subject, and a third weight corresponding to the voice type of the first subject;

[0292] Based on the first weight, the second weight and the third weight, the action risk state, the emotion type and the sound type are analyzed from the dimensions of safety care needs, psychological care needs and physiological care needs, respectively, to obtain a first need score, a second need score and a third need score; the first need score is used to characterize the probability that the first subject has a safety care need, the second need score is used to characterize the probability that the first subject has a psychological care need, and the third need score is used to characterize the probability that the first subject has a physiological care need;

[0293] A subject care need of the first subject is determined based on the first need score, the second need score, and the third need score.

[0294] In some embodiments, the operation execution module 930 is used to:

[0295] Determining demand prompt content based on the subject care demand, wherein the demand prompt content is used to prompt the subject care demand of the first subject;

[0296] A demand prompting operation for the demand prompting content is performed as the nursing feedback operation.

[0297] In some embodiments, the nursing terminal is installed in a physical environment including the first subject; the operation execution module 930 is used to:

[0298] Acquire environmental data corresponding to the physical environment including the first subject;

[0299] When the environmental data indicates that there is a second subject within a preset range of the first subject, determining voice prompt information as the demand prompt content based on the subject's care demand, the voice prompt information is used to indicate the voice played by the care terminal;

[0300] When the environmental data indicates that there is no second subject within the preset range of the first subject, a remote prompt message is determined as the demand prompt content based on the subject's care needs, and the remote prompt message is used to indicate the prompt message sent by the care terminal to the first terminal.

[0301] In some embodiments, the operation execution module 930 is used to:

[0302] Determine a device operation instruction based on the subject care demand, the device operation instruction is used to control the care terminal to perform a care interaction operation, and the care interaction operation is used to meet the subject care demand of the first subject;

[0303] The nursing interaction operation is performed according to the device operation instruction as the nursing feedback operation.

[0304] In some embodiments, the operation execution module 930 is used to:

[0305] Determine a robot control instruction based on the subject's care needs, wherein the robot control instruction is used to control the care robot;

[0306] Execute a first control operation corresponding to the robot control instruction as the nursing feedback operation.

[0307] In some embodiments, the operation execution module 930 is used to:

[0308] Determine voice control content and action control content based on the subject's care needs, the voice control content is used to instruct the voice played by the care robot, and the action control content is used to instruct the action performed by the care robot;

[0309] The robot control instruction is determined based on the voice control content and the action control content.

[0310] In some embodiments, the operation execution module 930 is used to:

[0311] Obtaining interactive feedback information corresponding to the first subject in a historical time period, where the historical time period refers to a time period in which the nursing robot performs the first control operation, and the interactive feedback information is used to characterize a state of the first subject in the historical time period in which the nursing robot performs the first control operation;

[0312] Adjusting the robot control instructions based on the interactive feedback information;

[0313] A second control operation is performed according to the adjusted robot control instruction.

[0314] In some embodiments, the data generation module 940 is used to:

[0315] In the case where the subject care data indicates that the first subject performs a preset behavior, target behavior data is acquired to generate the care log data, where the target behavior data refers to data collected when the first subject performs the preset behavior.

[0316] In summary, the nursing device provided by the embodiment of the present application, after collecting the subject nursing data of the subject in the physical environment, will analyze the subject nursing data to determine the demand information expressed by the subject through behavior, so that the device can perform nursing feedback operations that match the subject's needs. On the one hand, the device can automatically collect and analyze the subject's nursing data, and perform corresponding nursing feedback operations, reducing labor costs and improving nursing efficiency; on the other hand, by determining the needs expressed by the subject's behavior, the device can avoid blind nursing feedback, so that the nursing feedback operation matches the actual needs of the subject, reducing invalid or erroneous nursing feedback operations, improving nursing accuracy, and helping to improve nursing quality. In addition, the device can also generate a nursing log by analyzing the subject's nursing data, thereby automatically recording the subject's behavioral performance at different time nodes. Relevant personnel can quickly understand the subject's situation through the nursing log, improving the efficiency of human-computer interaction.

[0317] An embodiment of the present application also provides a computer device, which includes: a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by the processor to implement the care methods provided by the above-mentioned method embodiments.

[0318] For example, Fig.10 1 is a schematic diagram of the structure of a computer device provided by an exemplary embodiment of the present application. Optionally, the computer device can be implemented as the nursing terminal described above.

[0319] The computer device 1000 includes a central processing unit (CPU) 1001, a system memory 1004 including a random access memory (RAM) 1002 and a read-only memory (ROM) 1003, and a system bus 1005 connecting the system memory 1004 and the central processing unit 1001. The computer device 1000 also includes a basic input / output system (I / O system) 1006 for facilitating information transmission between various components in the computer device, and a large-capacity storage device 1007 for storing an operating system 1013, application programs 1014, and other program modules 1015.

[0320] The basic input / output system 1006 includes a display 1008 for displaying information and an input device 1009 such as a mouse and a keyboard for user inputting information. The display 1008 and the input device 1009 are connected to the central processing unit 1001 through an input / output controller 1010 connected to the system bus 1005. The basic input / output system 1006 may also include an input / output controller 1010 for receiving and processing inputs from a plurality of other devices such as a keyboard, a mouse, or an electronic stylus. Similarly, the input / output controller 1010 also provides output to a display screen, a printer, or other types of output devices.

[0321] The mass storage device 1007 is connected to the central processing unit 1001 via a mass storage controller (not shown) connected to the system bus 1005. The mass storage device 1007 and its associated computer readable storage medium provide non-volatile storage for the computer device 1000. That is, the mass storage device 1007 may include a computer readable storage medium (not shown) such as a hard disk or a compact disc read-only memory (CD-ROM) drive.

[0322] Without loss of generality, the computer-readable storage medium may include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer-readable storage instructions, data structures, program modules or other data. Computer storage media include RAM, ROM, Erasable Programmable Read Only Memory (EPROM), Electronically Erasable Programmable Read-Only Memory (EEPROM), flash memory or other solid-state storage devices, CD-ROM, Digital Versatile Disc (DVD) or other optical storage, cassettes, tapes, disk storage or other magnetic storage devices. Of course, those skilled in the art will know that the computer storage medium is not limited to the above. The above-mentioned system memory 1004 and mass storage device 1007 can be collectively referred to as memory.

[0323] The memory stores one or more programs, and the one or more programs are configured to be executed by one or more central processing units 1001. The one or more programs contain instructions for implementing the above-mentioned method embodiments. The central processing unit 1001 executes the one or more programs to implement the methods provided by the above-mentioned various method embodiments.

[0324] According to various embodiments of the present application, the computer device 1000 can also be connected to a remote computer device on a network through a network such as the Internet. That is, the computer device 1000 can be connected to the network 1012 through the network interface unit 1011 connected to the system bus 1005, or the network interface unit 1011 can be used to connect to other types of networks or remote computer device systems (not shown).

[0325] The memory also includes one or more programs, which are stored in the memory and include steps executed by a computer device in the method provided in the embodiment of the present application.

[0326] A computer-readable storage medium is also provided in an embodiment of the present application, in which at least one instruction, at least one program, code set or instruction set is stored. When the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor of a computer device, the care method provided by the above-mentioned method embodiments is implemented.

[0327] The present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the nursing method provided by each of the above method embodiments.

[0328] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned readable storage medium may be a read-only memory, a disk or an optical disk, etc.

[0329] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent switching, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A nursing method, characterized in that: The method comprises: Collecting subject care data of the first subject, the subject care data including data collected by a collection component from a physical environment containing the first subject, the subject care data being used to characterize subject behavior generated by the first subject's activities in the physical environment; Determining a subject care demand of the first subject based on the subject care data, wherein the subject care demand refers to a feedback demand expressed by the first subject through the subject behavior; executing a care feedback operation that matches the care needs of the subject, wherein the care feedback operation is used to respond to the subject's behavior; Nursing log data is generated based on the subject nursing data, and the nursing log data is used to record the subject historical behavior of the first subject.

2. The method according to claim 1, characterized in that The subject care data includes at least one of the following data: Subject action data, the subject action data being used to indicate an action performed by the first subject in the physical environment; Subject expression data, the subject expression data is used to indicate the facial expression of the first subject; Subject sound data, where the subject sound data is used to indicate the sound emitted by the first subject in the physical environment.

3. The method according to claim 1, characterized in that: The subject care data includes subject action data, subject expression data and subject voice data; The determining the subject care requirement of the first subject based on the subject care data includes: Analyzing the subject action data to obtain the action risk state of the first subject; Analyzing the subject expression data to obtain the emotion type of the first subject; Analyzing the subject voice data to obtain the voice type of the first subject; A subject care need of the first subject is determined based on the action risk state of the first subject, the emotion type of the first subject, and the voice type of the first subject.

4. The method according to claim 3, characterized in that The determining of the subject care requirement of the first subject based on the action risk state of the first subject, the emotion type of the first subject, and the voice type of the first subject includes: Determine, according to the current growth stage of the first subject, a first weight corresponding to the action risk state of the first subject, a second weight corresponding to the emotion type of the first subject, and a third weight corresponding to the voice type of the first subject; Based on the first weight, the second weight and the third weight, the action risk state, the emotion type and the sound type are analyzed from the dimensions of safety care needs, psychological care needs and physiological care needs, respectively, to obtain a first need score, a second need score and a third need score; the first need score is used to characterize the probability that the first subject has a safety care need, the second need score is used to characterize the probability that the first subject has a psychological care need, and the third need score is used to characterize the probability that the first subject has a physiological care need; A subject care need of the first subject is determined based on the first need score, the second need score, and the third need score.

5. The method according to any one of claims 1 to 4, characterized in that: The performing of the care feedback operation matching the care needs of the subject includes: Determining demand prompt content based on the subject care demand, wherein the demand prompt content is used to prompt the subject care demand of the first subject; A demand prompting operation on the demand prompting content is performed as the nursing feedback operation.

6. The method according to claim 5, characterized in that The method is executed by a care terminal installed in a physical environment including the first subject; The determining of demand prompt content based on the subject's care demand includes: Acquire environmental data corresponding to the physical environment including the first subject; When the environmental data indicates that there is a second subject within a preset range of the first subject, determining voice prompt information as the demand prompt content based on the subject's care demand, the voice prompt information is used to indicate the voice played by the care terminal; When the environmental data indicates that there is no second subject within the preset range of the first subject, a remote prompt message is determined as the demand prompt content based on the subject's care needs, and the remote prompt message is used to indicate the prompt message sent by the care terminal to the first terminal.

7. The method according to any one of claims 1 to 4, characterized in that: Executed by the nursing terminal; The performing of the care feedback operation matching the care needs of the subject includes: Determine a device operation instruction based on the subject care demand, the device operation instruction is used to control the care terminal to perform a care interaction operation, and the care interaction operation is used to meet the subject care demand of the first subject; The nursing interaction operation is performed according to the device operation instruction as the nursing feedback operation.

8. The method according to any one of claims 1 to 4, characterized in that: Performed by care robots; The performing of the care feedback operation matching the care needs of the subject includes: Determine a robot control instruction based on the subject's care needs, wherein the robot control instruction is used to control the care robot; Execute a first control operation corresponding to the robot control instruction as the nursing feedback operation.

9. The method according to claim 8, characterized in that The determining of the robot control instructions based on the subject care requirements includes: Determine voice control content and action control content based on the subject's care needs, the voice control content is used to instruct the voice played by the care robot, and the action control content is used to instruct the action performed by the care robot; The robot control instruction is determined based on the voice control content and the action control content.

10. The method according to claim 8, characterized in that After executing the first control operation corresponding to the robot control instruction as the nursing feedback operation, the method further includes: Obtaining interactive feedback information corresponding to the first subject in a historical time period, where the historical time period refers to a time period in which the nursing robot performs the first control operation, and the interactive feedback information is used to characterize a state of the first subject in the historical time period in which the nursing robot performs the first control operation; Adjusting the robot control instructions based on the interactive feedback information; A second control operation is performed according to the adjusted robot control instruction.

11. The method according to any one of claims 1 to 4, characterized in that: The generating of nursing log data based on the subject nursing data comprises: In the case where the subject care data indicates that the first subject performs a preset behavior, target behavior data is acquired to generate the care log data, where the target behavior data refers to data collected when the first subject performs the preset behavior.

12. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor to implement the care method according to any one of claims 1 to 11.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one computer program, and the at least one computer program is loaded and executed by a processor to implement the care method according to any one of claims 1 to 11.

14. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the care method according to any one of claims 1 to 11.

Images