Nursing processing method and device, storage medium and electronic equipment

Abstract

The embodiment of the invention discloses a nursing processing method and device, a storage medium and electronic device.The method comprises the steps that nursing request information input by a user for a nursing object is received, and nursing environment information of the nursing object is obtained, based on the nursing request information and the nursing environment information, performing scene nursing risk analysis processing on the nursing request by adopting a nursing processing large model to obtain multiple risk nursing events, and performing event disposal reasoning based on the risk nursing events to obtain a nursing event disposal plan, and monitoring a nursing scene video of the nursing object, and carrying out object nursing processing by adopting the nursing event processing plan through the nursing processing large model based on the nursing scene video.

Description

Technical Field

[0001] This specification relates to the field of computer technology, and in particular to a nursing processing method, device, storage medium, and electronic device. Background Art

[0002] In recent years, with the rapid development of computer vision, artificial intelligence, and multimodal data processing technologies, the smart home and home care sectors are undergoing unprecedented transformation. Existing technologies primarily rely on real-time video surveillance and environmental perception, requiring remote monitoring to detect and provide early warnings of object behavior and scene conditions within the home. Therefore, how to more efficiently and accurately extract meaningful information from complex environmental and behavioral data, and implement intelligent security warnings and interventions, has become a key technical challenge urgently needed in the industry. Summary of the Invention

[0003] The embodiments of this specification provide a nursing processing method, device, storage medium, and electronic device, and the technical solutions are as follows:

[0004] In a first aspect, an embodiment of the present specification provides a nursing treatment method, the method comprising:

[0005] Receiving care request information input by a user for a care object, and obtaining care environment information of the care object;

[0006] Based on the care request information and the care environment information, a care processing large model is used to perform scenario care risk analysis on the care request to obtain multiple risk care events, and event handling reasoning is performed based on each of the risk care events to obtain a care event handling plan;

[0007] The care scene video of the care object is monitored, and the care event handling plan is used to perform care processing on the object based on the care scene video through the care processing large model.

[0008] In a feasible implementation, the care request is analyzed based on the care request information and the care environment information using a care processing model to obtain a variety of risk care events, including:

[0009] Determine the care scenario context features and the user's key care demand features using a care processing large model based on the care request information and the care environment information;

[0010] Based on the care scenario context features and the user's key care demand features, a care processing large model is used to perform risk reasoning to obtain risk scenario type information and risk scenario semantic information;

[0011] Based on the risk scenario type information and the risk scenario semantic information, risk care event structuring processing is performed to obtain multiple risk care events.

[0012] In a feasible implementation, the determining of the care scenario context features and the user key care requirement features using a care processing large model based on the care request information and the care environment information includes:

[0013] Inputting the care request information and the care environment information into a care processing model, performing scene structured modeling processing on the care environment information to obtain a care scene semantic map, and using the care scene semantic map as a care scene context feature;

[0014] Key needs are extracted based on the semantic graph of the care scene and the care request information to obtain user attention intention, keyword information and attention emotional tendency information, and care needs are inferred based on the user attention intention, keyword information and attention emotional tendency information to obtain key care needs characteristics.

[0015] In a feasible implementation, the risk reasoning based on the care scenario context features and the user's key care demand features using the care processing large model to obtain risk scenario type information and risk scenario semantic information includes:

[0016] Fusing the care scenario context features and the user's key care demand features to obtain a scenario risk reasoning representation;

[0017] Risk classification processing is performed based on the scenario risk reasoning representation to obtain risk scenario type information, and scenario semantic reasoning is performed based on the risk scenario type information and the scenario risk reasoning representation to obtain risk scenario semantic information.

[0018] In a feasible implementation, the performing of event handling reasoning based on each of the risk nursing events to obtain a nursing event handling plan includes:

[0019] Determining reference intervention rules for each of the risk nursing events through the nursing processing macro model, and performing graded response reasoning based on the reference intervention rules to obtain graded response intervention measures;

[0020] The nursing risk events and the graded response intervention measures corresponding to the nursing risk events are structured through the nursing processing large model to obtain a nursing event handling plan.

[0021] In a feasible implementation, determining a reference intervention rule for each risk nursing event through the nursing processing macro model, and performing graded response reasoning based on the reference intervention rule to obtain a graded response intervention measure include:

[0022] Prioritizing each of the risk nursing events through the nursing processing macromodel to obtain a global nursing risk event set, and performing intervention rule matching on the nursing risk events in the global nursing risk event set based on a preset risk intervention library to obtain a reference intervention rule corresponding to each of the nursing risk events;

[0023] The risk scenario semantic information corresponding to the nursing risk event is obtained through the nursing processing large model, and the reference intervention rules are subjected to graded response reasoning based on the risk scenario semantic information to obtain graded response intervention measures.

[0024] In a feasible implementation, performing object care processing based on the care scene video through the care processing large model and the care event handling plan includes:

[0025] Based on the nursing scene video, the nursing processing large model is used to identify the current object behavior of the nursing object;

[0026] Performing risk behavior reasoning on the current subject's behavior based on the nursing event handling plan to obtain a risk behavior matching result;

[0027] If the risk behavior determination result is a risk behavior type, querying the behavior response intervention measures of the current subject's behavior from the care event handling plan, performing a response intervention operation on the care subject based on the behavior response intervention measures, and performing the step of monitoring the care scene video of the care subject;

[0028] If the risk behavior is determined to be a normal behavior type, the step of monitoring the care scene video of the care object is performed.

[0029] In a second aspect, an embodiment of the present specification provides a nursing processing device, the device comprising:

[0030] An information acquisition module is used to receive care request information input by a user for a care object and obtain care environment information of the care object;

[0031] A plan generation module is configured to perform scenario-based care risk analysis on the care request based on the care request information and the care environment information using a large care processing model to obtain a plurality of risk care events, and to perform event handling reasoning based on each of the risk care events to obtain a care event handling plan;

[0032] The care processing module is used to monitor the care scene video of the care object, and perform care processing on the object based on the care scene video through the care processing large model and the care event handling plan.

[0033] In a feasible implementation, the care request is analyzed based on the care request information and the care environment information using a care processing model to obtain a variety of risk care events, including:

[0034] Determine the care scenario context features and the user's key care demand features using a care processing large model based on the care request information and the care environment information;

[0035] Based on the care scenario context features and the user's key care demand features, a care processing large model is used to perform risk reasoning to obtain risk scenario type information and risk scenario semantic information;

[0036] Based on the risk scenario type information and the risk scenario semantic information, risk care event structuring processing is performed to obtain multiple risk care events.

[0037] In a feasible implementation, the determining of the care scenario context features and the user key care requirement features using a care processing large model based on the care request information and the care environment information includes:

[0038] Inputting the care request information and the care environment information into a care processing model, performing scene structured modeling processing on the care environment information to obtain a care scene semantic map, and using the care scene semantic map as a care scene context feature;

[0039] Key needs are extracted based on the semantic graph of the care scene and the care request information to obtain user attention intention, keyword information and attention emotional tendency information, and care needs are inferred based on the user attention intention, keyword information and attention emotional tendency information to obtain key care needs characteristics.

[0040] In a feasible implementation, the risk reasoning based on the care scenario context features and the user's key care demand features using the care processing large model to obtain risk scenario type information and risk scenario semantic information includes:

[0041] Fusing the care scenario context features and the user's key care demand features to obtain a scenario risk reasoning representation;

[0042] Risk classification processing is performed based on the scenario risk reasoning representation to obtain risk scenario type information, and scenario semantic reasoning is performed based on the risk scenario type information and the scenario risk reasoning representation to obtain risk scenario semantic information.

[0043] In a feasible implementation, the performing of event handling reasoning based on each of the risk nursing events to obtain a nursing event handling plan includes:

[0044] Determining reference intervention rules for each of the risk nursing events through the nursing processing macro model, and performing graded response reasoning based on the reference intervention rules to obtain graded response intervention measures;

[0045] The nursing risk events and the graded response intervention measures corresponding to the nursing risk events are structured through the nursing processing large model to obtain a nursing event handling plan.

[0046] In a feasible implementation, determining a reference intervention rule for each risk nursing event through the nursing processing macro model, and performing graded response reasoning based on the reference intervention rule to obtain a graded response intervention measure include:

[0047] Prioritizing each of the risk nursing events through the nursing processing macromodel to obtain a global nursing risk event set, and performing intervention rule matching on the nursing risk events in the global nursing risk event set based on a preset risk intervention library to obtain a reference intervention rule corresponding to each of the nursing risk events;

[0048] The risk scenario semantic information corresponding to the nursing risk event is obtained through the nursing processing large model, and the reference intervention rules are subjected to graded response reasoning based on the risk scenario semantic information to obtain graded response intervention measures.

[0049] In a feasible implementation, performing object care processing based on the care scene video through the care processing large model and the care event handling plan includes:

[0050] Based on the nursing scene video, the nursing processing large model is used to identify the current object behavior of the nursing object;

[0051] Performing risk behavior reasoning on the current subject's behavior based on the nursing event handling plan to obtain a risk behavior matching result;

[0052] If the risk behavior determination result is a risk behavior type, querying the behavior response intervention measures of the current subject's behavior from the care event handling plan, performing a response intervention operation on the care subject based on the behavior response intervention measures, and performing the step of monitoring the care scene video of the care subject;

[0053] If the risk behavior is determined to be a normal behavior type, the step of monitoring the care scene video of the care object is performed.

[0054] In a third aspect, an embodiment of this specification provides a computer storage medium, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above-mentioned method steps.

[0055] In a fourth aspect, an embodiment of this specification provides an electronic device, which may include: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0056] The beneficial effects of the technical solutions provided by some embodiments of this specification include at least:

[0057] In one or more embodiments of the present specification, the electronic device obtains care environment information based on the user's care demand information, and parses a variety of potential risk care events based on the care processing large model and generates a care event handling plan for each potential risk care event. Finally, it uses real-time care scene video monitoring combined with care event handling plans to perform hierarchical intervention, forming a complete and executable care closed loop, which not only comprehensively covers all types of risks in the scene, but also can trigger intervention in time when risks actually occur, continuously track the effects and dynamically adjust, thereby significantly improving care efficiency and safety, and providing users with intelligent and personalized care services. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0059] Figure 1 This is a flowchart of a nursing treatment method provided in an embodiment of this specification;

[0060] Figure 2 This is a schematic diagram of an interface for a user to manually input care request information provided in an embodiment of this specification;

[0061] Figure 3 This is a schematic diagram of an interface providing care scene options provided in an embodiment of this specification;

[0062] Figure 4 This is a schematic diagram of an interface of a nursing incident handling plan provided in an embodiment of this specification;

[0063] Figure 5 This is a flowchart of a scenario-based nursing risk analysis provided by an embodiment of this specification;

[0064] Figure 6 This is a flowchart of an event handling reasoning process provided by an embodiment of this specification;

[0065] Figure 7This is a flowchart of an object care process provided by an embodiment of this specification;

[0066] Figure 8 This is a structural diagram of a nursing treatment device provided in an embodiment of this specification;

[0067] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification;

[0068] Figure 10 This is a schematic diagram of the structure of the operating system and user space provided in the embodiments of this specification;

[0069] Figure 11 yes Figure 10 The architecture diagram of the Android operating system;

[0070] Figure 12 yes Figure 10 Architecture diagram of the IOS operating system. DETAILED DESCRIPTION

[0071] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the embodiments described are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this specification.

[0072] In the description of this specification, it should be understood that the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance. In the description of this specification, it should be noted that, unless otherwise expressly specified and limited, "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices. For those of ordinary skill in the art, the specific meanings of the above terms in this specification can be understood according to the specific circumstances. In addition, in the description of this specification, unless otherwise specified, "multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0073] The present specification is described in detail below with reference to specific embodiments.

[0074] In one embodiment, Figure 1 As shown, a care processing method is proposed. This method can be implemented using a computer program and can be run on a care processing device based on the von Neumann architecture. The computer program can be integrated into an application or run as a standalone tool application. The care processing device can be an electronic device, including but not limited to: a smart camera, a personal computer, a tablet computer, a handheld device, an in-vehicle device, a wearable device, a computing device, or other processing device connected to a wireless modem. Terminal devices in different networks can be called different names, such as user equipment, access terminal, subscriber unit, subscriber station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, cellular phone, cordless phone, smart home device in 5G network or future evolution network, etc.

[0075] Specifically, the nursing treatment method includes:

[0076] S102: receiving care request information input by the user for the care object, and obtaining care environment information of the care object;

[0077] Care request information: This information is provided by users through mobile apps, voice interaction, or graphical interfaces, describing their care needs. Examples include "Please watch over my child and prevent him from getting close to the hot water cup" or "Monitor the elderly for fall risks." This information includes risk concerns, the care recipient, and their behavioral preferences.

[0078] Care environment information: This refers to actual care scenario data acquired through smart home devices such as cameras, sensors, and IoT devices, including indoor layout, device distribution, temperature and humidity, and lighting conditions. This care environment information provides a reference for subsequent risk analysis.

[0079] Illustratively, after receiving the care request information input by the user, the care processing system of the electronic device (which may be a smart home system) collects current monitoring information from one or more of the following in the care scene, such as a camera, a temperature and humidity sensor, and a smart device, constructs care environment information, and completes obtaining the care environment information for the care object in the care scene;

[0080] For example: Please refer to Figure 2 , Figure 2 It is a schematic diagram of an interface in which a user manually inputs care request information. The user inputs "care for the children playing" to the intelligent service in the smart home app. At this time, the care processing system of the electronic device receives the care request information input by the user, parses the keywords "children" and "play", and obtains real-time video of the "play" area through the camera and sensors to form preliminary care environment information.

[0081] Optionally, when the user enters the care setting interface (such as the dialogue interface with the intelligent agent service), the care processing system of the electronic device loads a plurality of pre-configured common care scene options. Figure 3 As shown, Figure 3 It is a schematic diagram of an interface that provides care scene options. Figure 3 The care scene options shown in the are set based on the analysis of common family needs or the summary of care needs of the big model, covering different groups of people and scenarios. These care scene options are displayed to users, such as the "watch the baby sleep" option, the "watch the children play" option, the "supervise the children to do their homework" option, the "supervise the elderly to take medicine" option, and the "watch the pets" option. Users can directly click on one or more target care scene options (such as "watch the baby sleep"), and the one or more target care scene options are also care request information; users can also customize and enter more detailed requirements (such as "If the child turns over or cries after sleeping, please remind me"). If the user does not find a suitable option, he or she can also freely enter care needs as care request information.

[0082] S104: Based on the care request information and the care environment information, a care processing macro model is used to perform scenario care risk analysis on the care request to obtain multiple risk care events, and event handling reasoning is performed based on each of the risk care events to obtain a care event handling plan;

[0083] Care environment information: The care processing system collects environmental data from sources such as cameras and sensors, describing the device location, temperature and humidity, lighting, and possible dangerous objects or areas within the scene.

[0084] The care processing model can be derived by adapting a basic large language model (LLM) to the care processing scenario. This model is a comprehensive AI model that combines natural language processing, image recognition, multimodal fusion, and risk assessment. It can understand user needs and scenario context, analyze potential risk events, and infer response plans. Basic large language models include but are not limited to the GPT series of large models, the DeepSeek series of large models, the Tongyi Qianwen model, the Wenxin Yiyan model, and others.

[0085] Scenario-based care risk analysis and processing: The large care processing model identifies possible risk points or events in the care scenario based on user requests and environmental data, such as burn risks, fall risks, accidental ingestion risks, etc.

[0086] Multiple risk nursing events: refers to the large nursing processing model analyzing multiple specific potential risk events. Different types of risk events may exist simultaneously in the same nursing scenario, such as burn risk, fall risk, lost risk, accidental ingestion risk, electric shock risk, etc., and generating corresponding event descriptions and trigger conditions for each type of risk.

[0087] Event handling reasoning: This can be understood as inferring hierarchical response strategies and intervention measures (such as voice reminders first, mobile phone notifications, and finally automatic intervention) through the combined use of a large supervision processing model and a pre-configured rule base, user preferences, and environmental constraints.

[0088] Nursing incident handling plan: Summarize and integrate the handling strategies of various risky nursing incidents to form an "overall plan" covering the same scenario. When subsequent scene monitoring detects the occurrence of the corresponding incident, the corresponding measures in the plan can be executed.

[0089] In principle, the care request information and the care environment information (such as room layout, location of dangerous objects, etc.) are input into the care processing large model for environmental semantic analysis to obtain the overall environmental semantic analysis information of the scene. On the basis of controlling the care processing large model to parse the user's care demand information, multiple potential risk points (hot water cups, high furniture, doors and windows, etc.) are identified in combination with the environmental semantic analysis information. The object trigger conditions are determined according to the potential risk points (for example, if the potential risk point is a hot water cup, the object trigger condition can be that the child is close to the hot water cup). Based on the potential risk points and the object trigger conditions, risk care events can be combined, and so on to obtain multiple risk care events. Each risk care event may include event type (such as scalding, getting lost, falling), trigger conditions (distance threshold, motion recognition, sensor status, etc.) and preliminary risk level.

[0090] Then, based on each risk care event, event handling reasoning is performed. The care processing large model can refer to the preset rule library (such as safety standards, family preferences) and the large model can reason according to priority, user preferences and preset rules to determine the corresponding intervention measures and execution order.

[0091] Optional intervention measures include but are not limited to: voice prompts, light or sound reminders, mobile phone notifications to parents, automatic animation distraction, linked doors and windows or robot blocking, etc.

[0092] Furthermore, after completing the event handling reasoning, multiple events and their handling strategies are integrated to generate a nursing event handling plan. This nursing event handling plan covers all major risk events in the same nursing scenario and defines the trigger conditions, intervention methods, timing logic, and exit conditions for each event.

[0093] Example scenario: "Supervising children playing"

[0094] User request: A user requested in the app: "When playing in the living room, please keep your child away from the hot water cup and prevent him from opening the door to go out."

[0095] Environmental information: The system detects that "a cup of hot water with a temperature of about 60°C is placed on the coffee table in the living room", and the door and window sensor status can detect the door opening action.

[0096] Risk analysis: The large model identified two main risk events: scalding risk (child approaches a hot water cup) and getting lost risk (child opens the door and leaves the living room);

[0097] Event handling reasoning:

[0098] 1) Scalding risk management: Voice prompt "The cup is hot, don't touch it"; if the child continues to approach, the phone notifies the parent; if there is still no response, an animation automatically plays to attract the child away.

[0099] 2) Lost risk management: When the door and window sensors detect that the door is open and the child is approaching the door, a voice reminder "Don't leave the room" will be issued; if the child continues to go out, a push notification will be sent to the parents; if there is still no response from the parents, the door will be locked or an alarm will be sounded (depending on the device function).

[0100] Plan output:

[0101] Develop a comprehensive plan covering the "supervising children playing" scenario:

[0102] Risk Event 1: Burn Risk, Handling Process =…

[0103] Risk Event 2: Lost Risk, Handling Process =…

[0104] The nursing event handling plan is executed in subsequent real-time monitoring. When the corresponding event is identified, the electronic device immediately calls the corresponding handling strategy in the nursing event handling plan through the nursing processing system.

[0105] In a specific implementation scenario, such as Figure 4 As shown, Figure 4 This is a diagram of a care event handling plan interface. The user enters "supervise children playing" and executes S104 to generate a care event handling plan. Based on the user's care request and indoor environment information, the care processing model performs risk analysis and identifies multiple potential risk events. It then performs handling reasoning for each risk event, forming the following key points:

[0106] 1. Running next to the coffee table

[0107] Risk: Children may be hit by the corner of the coffee table or fall while running.

[0108] Disposal: First, a voice reminder is given: "Little boy, be careful with the corners of the coffee table, be careful not to fall." If the child continues to run around the coffee table, the system may escalate to a mobile phone notification or attempt to distract the child (such as playing music or showing animations).

[0109] 2. The scope is extended to the kitchen

[0110] Risk: If the child continues into the kitchen area, he or she may come into contact with hot water, electrical appliances, or kitchen utensils.

[0111] Handling method: Voice reminder "Don't go near the kitchen area, it's very dangerous". If the child still goes there, the caregiver will be notified via mobile phone or the lights on the scene will flash as a reminder.

[0112] 3. Get on the sofa or lie on the sofa

[0113] Risks: The sofa back or armrests are unstable and the child may fall and get injured; or there are sharp objects near the edge of the sofa.

[0114] Handling method: Voice reminder "Don't step on the sofa, don't climb over the armrest"; if the child continues to engage in risky behavior, notify the parents again or use animation to distract the child. ......

[0116] Furthermore, the user is presented with a comprehensive plan for handling childcare incidents. This plan addresses a variety of potential risk events in the "supervising children at play" scenario, listing potential triggering conditions and corresponding intervention measures for each risk event. Through a hierarchical strategy that prioritizes voice reminders, parent notifications, and automated intervention, the plan can mitigate risks promptly in most cases, providing children with a safer space and offering parents a more worry-free and reliable smart childcare service.

[0117] Optionally, the user may input a start care instruction, at which point the electronic device starts executing the care event handling plan S106;

[0118] Optionally, the user may input an adjustment instruction for the nursing event handling plan to adjust the nursing event handling plan.

[0119] S106: Monitor the care scene video of the care object, and perform care processing on the object based on the care scene video through the care processing large model and the care event handling plan.

[0120] Care scene video: refers to the environmental images obtained in real time through cameras or other video acquisition devices, covering the main areas where the care recipients move, such as the living room, bedroom, kitchen, etc.

[0121] Object care processing: When a risk event is detected, the system will execute corresponding intervention measures (voice reminders, mobile phone notifications, automatic intervention, etc.) according to the plan and continuously monitor the intervention effect.

[0122] Schematically, the care processing system of the electronic device activates the camera and obtains the care scene video, and uses the care processing large model to track the care objects (such as children, elderly people, pets) in the picture, analyze their behavior, and detect environmental changes;

[0123] The care processing model will determine whether the care object meets the triggering conditions of any risk event (such as being too close to dangerous objects, making dangerous movements, etc.). Once it is detected that the care object's movement, position or status matches the triggering conditions of a risk event in the plan, the system will enter the corresponding event handling process;

[0124] For example, if the system detects that a child is running too fast next to a coffee table, it will match the event handling plan for "risk of falling while running indoors."

[0125] According to the multi-level intervention strategy set for the risk event in the event handling plan, the system executes intervention actions in sequence;

[0126] Examples may include:

[0127] Initial reminder: Voice prompt "Run slowly, be careful not to fall!"

[0128] Upgrade notification: If the child is still running, a push notification or phone call will be sent to the parent's mobile phone;

[0129] Automatic intervention: If the parent does not respond, the system can play animations or music to distract the child, or even control robots or ambient lighting to prevent the child from continuing dangerous behavior (depending on the device's capabilities).

[0130] Furthermore, the electronic device continuously monitors the effectiveness of the intervention measures. If the risk status is lifted (such as the child stops running and stays away from the dangerous area), the handling process of the risk event is recorded and ended; if the risk status is still not lifted or a higher risk occurs, the system can continue to upgrade the intervention measures or trigger the handling plan of other events. After the intervention is completed, the electronic device records and saves the entire process (identification to trigger, execution of intervention, and final result).

[0131] In the embodiments of this specification, the electronic device obtains care environment information based on the user's care demand information, and parses a variety of potential risk care events based on the care processing large model and generates a care event handling plan for each potential risk care event. Finally, it uses real-time care scene video monitoring combined with care event handling plans to perform hierarchical intervention, forming a complete and executable care closed loop, which not only comprehensively covers various risks in the scene, but also can trigger intervention in time when risks actually occur, continuously track the effects and dynamically adjust, thereby significantly improving care efficiency and safety, and providing users with intelligent and personalized care services.

[0132] See Figure 5 , Figure 5 This is a flow chart of a scenario-based nursing risk analysis process proposed in this specification. Specifically, the following methods can be used to perform scenario-based nursing risk analysis on the nursing request based on the nursing request information and the nursing environment information using the nursing processing model to obtain multiple risk nursing events:

[0133] S202: Determine care scenario context features and user key care demand features using a care processing model based on the care request information and the care environment information;

[0134] Care scene context features: represent the overall semantic and physical state information of the current care scene, such as the layout of each area in the scene, the distribution of dangerous objects, etc.

[0135] Key user care demand characteristics: refers to the core needs extracted from user input, such as the key risk prevention information such as "hot water cup scalding" and "lost" extracted based on care request information.

[0136] Schematically, the care request information and care environment information are used as the model input of the care processing model. The static environment and dynamic environment characteristics of the scene are extracted through the care processing model to form environmental feature data, and then the environmental feature data is structured to form care scene context features such as scene layout, object location, and environmental parameters; and the user request text is semantically parsed, risk concerns and expected intervention requirements are extracted, and then integrated to form the user's key care demand characteristics.

[0137] In a feasible implementation, the determining of the care scenario context features and the user key care requirement features using a care processing large model based on the care request information and the care environment information includes:

[0138] A2: Input the care request information and the care environment information into the care processing model, perform scene structured modeling processing based on the care environment information to obtain a care scene semantic graph, and use the care scene semantic graph as the care scene context feature;

[0139] Scene structured modeling: Taking the care request information and the care environment information as reference, it is converted into a semantic graph with nodes (representing objects and areas) and edges (representing spatial relationships) to intuitively express the scene layout and object association information.

[0140] Care scene semantic graph: a structured graph representing the relationships between various elements in the current care scene (such as furniture, equipment, dangerous objects, etc.), serving as a high-level semantic expression of the scene context features.

[0141] In a schematic manner, the care request information and care environment information are input into the care processing model, and the care processing model is controlled to analyze the environmental information using image segmentation, object detection and other technologies to identify the key elements in the scene (such as coffee tables, hot water cups, doors and windows, furniture, etc.), and a scene structured model is constructed according to the spatial position, relative relationship and attributes between objects. A semantic graph of the care scene containing nodes and edges is generated, and the generated semantic graph is saved as a context feature of the care scene for subsequent risk reasoning and plan generation.

[0142] For example, in a family living room, a user enters "Keep children away from a hot water cup while playing." Environmental information detected includes the following: the location of the coffee table, the location of the hot water cup, its abnormal temperature (e.g., 60°C), the living room layout, and furniture distribution. By executing step A2, this environmental information is structured into a graph, where nodes represent the coffee table, hot water cup, window, and so on, and edges indicate their spatial relationships. The resulting "supervision scene semantic graph" intuitively demonstrates the location of the hot water cup on the coffee table and its proximity to the play area, providing rich contextual information for subsequent risk reasoning.

[0143] A4: Based on the semantic graph of the care scene and the care request information, key needs are extracted to obtain the user's attention intention, keyword information and attention emotional tendency information. Based on the user's attention intention, keyword information and attention emotional tendency information, care needs are inferred to obtain key care needs characteristics.

[0144] Key demand extraction can be understood as extracting core needs from the user's care request information, such as the type of risk of concern (scalding, falling, getting lost, etc.), the expected intervention method, etc.

[0145] User attention intent can understand the main goals and concerns expressed by Wie users in care requests, such as "preventing children from touching high-temperature objects" and "ensuring children's safe play".

[0146] Keyword information can be understood as representative words extracted from the request text, such as "hot water cup", "close", "play", etc., which are used to represent the core characteristics of the risk event.

[0147] Attention to emotional tendency information can be understood as indicating the user's emotional attitude or urgency towards the care event, such as "urgent", "high risk", etc. This information helps to determine the warning level and response priority.

[0148] Care demand reasoning can be understood as using the care processing model to perform semantic reasoning on the extracted intentions, keywords, and sentiment information to generate specific key care demand features, providing guidance for subsequent risk analysis.

[0149] Schematically, the large-scale care processing model uses the semantic graph of care scenarios and the care request information entered by the user as a reference to extract the core risks, keywords, and sentiments of the user's concern. For example, from the question "Supervise children to keep them away from a hot water cup while playing," it extracts the keywords "play," "close," and "hot water cup," and identifies the user's risk intent as "preventing burns" and the sentiment as "urgent."

[0150] Furthermore, the large care processing model infers care needs based on the extracted user attention intent, keywords, and sentiment information, generating key care need features. This care need inference process transforms qualitative information into key care needs, such as mapping "preventing a hot water cup from touching it" into the triggering conditions and expected intervention requirements for a specific risk event. These key care need features serve as an important basis for subsequent risk inference and contingency plan generation.

[0151] For example, a user request might read, "Keep children away from a hot water cup while playing." After analysis, the following information is extracted: user intent: preventing children from getting hurt by approaching a hot water cup; key information: play, approach, hot water cup; and emotional inclination: urgency, indicating a high-risk prevention need. Based on this information, the control and care processing model infers key care demand characteristics, such as "In a child play scenario, if a child is detected approaching a high-temperature area (less than 1 meter), a high-priority warning intervention should be initiated."

[0152] In this document, we use a large-scale care processing model to structure the care environment information and generate a care scenario semantic graph as the context feature. This graph is then combined with user request information to extract key risk requirements of concern to the user. Through semantic reasoning, key care requirement features are generated. These two features provide a precise scenario and requirement foundation for subsequent risk analysis and plan generation, ensuring that the care processing process can generate targeted risk intervention plans based on the user's actual needs and the actual environment.

[0153] S204: Based on the care scenario context features and the user's key care demand features, a care processing large model is used to perform risk reasoning to obtain risk scenario type information and risk scenario semantic information;

[0154] Risk scenario type information: refers to the risk category inferred based on the care scenario context and user needs, such as "scalding risk", "falling risk", "lost risk", etc.

[0155] Risk scenario semantic information: This is a semantic description and qualitative analysis of the risk scenario, such as "there is a risk of burns near a high-temperature area" or "a child may fall while running", including but not limited to risk trigger conditions and risk descriptions.

[0156] Schematically, the large-scale nursing processing model, based on a pre-built risk rule library and expert experience library, compares the contextual features obtained in step S202 with the user's demand features to identify various potential risk points in the scenario. Leveraging the large-scale nursing processing model's semantic reasoning capabilities for potential risk points, it further describes these potential risk points and generates risk scenario semantic information and risk scenario type information.

[0157] In a feasible implementation, the risk reasoning based on the care scenario context features and the user's key care demand features using the care processing large model to obtain risk scenario type information and risk scenario semantic information includes:

[0158] B2: Fusing the care scenario context features and the user's key care demand features to obtain a scenario risk reasoning representation;

[0159] Scenario risk reasoning representation: It is a comprehensive representation obtained by integrating the contextual features of the care scenario with the user's key care needs features. The scenario risk reasoning representation can simultaneously reflect the internal structure of the scenario and the user's focus, providing a basis for subsequent risk judgment.

[0160] Schematically, the semantic map of the care scene obtained by environmental modeling is used as the scene context feature and combined with the user's key care demand features. The multimodal fusion mechanism (such as feature splicing, weighted fusion or fusion network based on attention mechanism) is used to map the care scene context feature and the user's key care demand features to the same high-dimensional semantic vector space. The fusion result is the "scene risk reasoning representation", which can simultaneously reflect the structural information in the environment and the risk points that the user is concerned about.

[0161] B4: Perform risk classification processing based on the scenario risk reasoning representation to obtain risk scenario type information, and perform scenario semantic reasoning based on the risk scenario type information and the scenario risk reasoning representation to obtain risk scenario semantic information.

[0162] Schematically, risk classification is performed based on the obtained scenario risk reasoning representation to obtain risk scenario type information. Simultaneously, the risk scenario type information and the scenario risk reasoning representation are input into a semantic reasoning module (e.g., a Transformer-based decoder or generative model) through the large-scale care processing model. This allows for deeper semantic parsing of the risk scenario to obtain risk scenario semantic information, such as "In the living room, a hot water cup placed on a coffee table poses a scalding risk, especially when children are playing near this area."

[0163] In this manual, we first integrate the contextual features of the care scenario and the key care needs of the user to generate a comprehensive scenario risk reasoning representation. We then perform risk classification and semantic reasoning based on this representation to obtain risk scenario type information and risk scenario semantic information, respectively. This process ensures that the system can not only accurately determine risk categories but also generate detailed semantic descriptions, providing a solid semantic foundation for the subsequent development of risk intervention plans.

[0164] S206: Performing risk care event structuring processing based on the risk scenario type information and the risk scenario semantic information to obtain multiple risk care events:

[0165] Schematically, the risk scenario type information and risk scenario semantic information obtained in S204 are integrated and combined with the care scenario context to decompose them into multiple specific risk care events. Each risk care event is described in a unified format, usually including: event identifier, event type (such as burns, falls), trigger conditions (such as distance, motion recognition), risk level and recommended intervention measures, thereby generating multiple risk care events in a structured data format (such as JSON format). All identified risk care events can be integrated into a complete list to provide a basis for subsequent event handling reasoning.

[0166] In the embodiments of this specification, a large care processing model is first used to fuse the user's care request information with environmental information to extract the care scenario context and the user's key demand characteristics. Then, risk reasoning is used to generate risk scenario type information and detailed risk semantic descriptions. Finally, these risk information are structured to generate multiple risk care events. Each event contains specific trigger conditions, risk levels and corresponding intervention measures, forming a complete list of risk care events, which provides a comprehensive basis for subsequent intervention responses.

[0167] See Figure 6 , Figure 6 This is a flow chart of an event handling reasoning process proposed in this specification. The specific execution of the event handling reasoning based on each of the risk nursing events to obtain a nursing event handling plan can refer to the following methods:

[0168] S302: Determine reference intervention rules for each of the risky nursing events using the nursing processing macro model, and perform graded response reasoning based on the reference intervention rules to obtain graded response intervention measures;

[0169] Reference intervention rules are pre-established or learned through large models, and are standard intervention plans for different risk types. For example, for burn risks, the rules might include a voice reminder, a phone notification, and finally an automatic animation to distract the user.

[0170] Hierarchical response reasoning: This can be understood as using the care processing model to adjust and refine the reference intervention rules based on the specific risk level and trigger conditions of the risk care event, generating targeted and hierarchical intervention measures to ensure that the intervention measures can be upgraded step by step from gentle reminders to emergency interventions.

[0171] Graded response intervention measures are specific intervention plans obtained through graded response reasoning, including multiple response levels (such as primary, secondary, and advanced), which are used to be implemented in sequence when risks occur.

[0172] In schematic form, the reference intervention rules are queried through the care processing big model according to the risk type and risk level of the event. On the basis of the reference intervention rules, combined with the triggering conditions of the event (such as distance threshold, behavior recognition results, etc.), the care processing big model is used to perform hierarchical response reasoning to obtain multiple intervention measures from primary to advanced, that is, hierarchical response intervention measures, so that the hierarchical response intervention measures corresponding to each risk care event can be obtained, for example: primary: voice reminder; secondary: mobile phone push notification; advanced: automatic animation playback or triggering linkage equipment to intervene.

[0173] For example, for the "scalding risk" event, the large-scale care handling model searches for reference intervention rules based on the situation described in the risk care event, "the child is close to a hot water cup", and obtains the following: Primary measures: immediately announce "The cup is very hot, please do not touch it!" through the built-in voice of the camera; Secondary measures: if the child continues to approach, an emergency notification will be pushed through the parent's mobile phone; Advanced measures: if there is no response, a children's animation will be automatically played to divert the child's attention.

[0174] In a feasible implementation, the reference intervention rules for each risk nursing event are determined by the nursing processing macro model, and hierarchical response reasoning is performed based on the reference intervention rules to obtain hierarchical response intervention measures. The following methods can be referred to:

[0175] C2: Prioritizing each of the risk nursing events using the nursing processing macromodel to obtain a global nursing risk event set, and matching the nursing risk events in the global nursing risk event set with intervention rules based on a preset risk intervention library to obtain a reference intervention rule corresponding to each nursing risk event;

[0176] Global nursing risk event set: This is a set of all identified risk nursing events that have been prioritized. Prioritization is designed to determine which events are more urgent and require more intervention in the current scenario.

[0177] The default risk intervention library is a pre-established intervention rule database containing reference intervention rules for various risk types. For example, for the "scald risk" scenario, the default rule might be "voice reminder first, mobile notification, and finally automatic animation playback."

[0178] Reference intervention rules: These are intervention rules obtained by matching each event in the global risk event set against a pre-defined risk intervention library. These rules provide a standard basis for subsequent graded responses.

[0179] Schematically, all risky nursing events identified by the large nursing processing model are used as references. Each event is prioritized based on risk severity, trigger frequency, and scenario factors to form a global nursing risk event set. For each risk event in the global risk event set, a rule matching process is performed using a pre-set risk intervention library. By mapping risk types to pre-set rules, a reference intervention rule for each risk event is determined. This yields one or more reference intervention rules for each risk event, which serve as a reference for subsequent hierarchical response reasoning.

[0180] Assume that in the "supervising children playing" scenario, the system identifies two risk events:

[0181] Event 1: "Child near hot water cup" (risk of burns, high risk level)

[0182] Event 2: "The child may fall while running" (fall risk, medium risk level)

[0183] After priority adjustment, event 1 is determined to be more urgent. Then, the preset risk intervention library is used to match:

[0184] The reference intervention rule for event 1 is "first give a voice reminder 'the cup is very hot', then push a notification to the parent's phone, and finally automatically play an animation to divert attention";

[0185] The reference intervention rule for event 2 is "voice reminder 'Be careful', and notify parents if the situation persists."

[0186] C4: Obtain risk scenario semantic information corresponding to the care risk event through the care processing large model, and perform hierarchical response reasoning on the reference intervention rules based on the risk scenario semantic information to obtain hierarchical response intervention measures.

[0187] Hierarchical response reasoning: refers to the hierarchical design of intervention measures for each risk event based on risk scenario semantic information and reference intervention rules, forming primary, secondary and advanced response strategies.

[0188] Tiered response interventions are the final, specific interventions that include multiple levels of response. For example, the primary intervention might be just a voice prompt, the secondary might be a phone notification, and the tertiary might be an automated intervention (such as playing an animation or controlling a device).

[0189] Schematically, the reference intervention rules (obtained from C2) are combined with the semantic information of the risk scenario, and the deep semantic reasoning model is used to determine the hierarchical response of the intervention measures. According to the risk severity and trigger conditions, the corresponding risk levels are inferred:

[0190] S304: The nursing risk event and the graded response intervention measures corresponding to the nursing risk event are structured through the nursing processing macro model to obtain a nursing event handling plan.

[0191] Schematically, the detailed information of each risky nursing event (event type, triggering condition, and risk level) is mapped to the graded response intervention measures obtained in S302 to form a list of all risk events. This list is converted into a unified data format using the nursing processing macromodel, recording all key fields and corresponding intervention steps for each risk event. This integrated structured data is output as the final nursing event handling plan, which serves as the basis for subsequent real-time monitoring and intervention.

[0192] This manual first identifies reference intervention rules for each risky nursing event and uses a large model to perform hierarchical response reasoning, resulting in detailed hierarchical response intervention measures. Subsequently, each risk event is structured with its corresponding intervention measures to generate a complete nursing event response plan. This plan covers multiple potential risk events in the same scenario and develops intervention strategies for each risk event, from primary to advanced levels, providing a comprehensive and systematic basis for real-time risk monitoring and intervention.

[0193] See Figure 7 , Figure 7 This is a flowchart of a process for object care processing proposed in this specification. Specifically, the object care processing based on the care scene video through the care processing large model and the care event handling plan can be performed in the following ways:

[0194] S402: Identifying the current behavior of the care object through the care processing model based on the care scene video;

[0195] Current object behavior: refers to the actions and activities of the care object at the current moment, such as running, crawling, standing, sitting, etc.

[0196] Schematically, video data of the care scene is continuously collected, and a large care processing model is used to perform target detection and action recognition to identify the current object behavior of the care object in real time.

[0197] S404: performing risk behavior reasoning on the current subject's behavior based on the nursing event handling plan to obtain a risk behavior matching result;

[0198] Risk behavior reasoning processing: refers to comparing and reasoning the currently detected object behavior with the risk trigger conditions defined in the plan to determine whether the behavior is a risky behavior.

[0199] Risk behavior matching result: Indicates the degree of match between the current object behavior and the preset risk trigger conditions, and usually outputs the judgment result of "risk behavior" or "normal behavior".

[0200] Schematically, the current object behavior is compared with the risk triggering conditions in the nursing event handling plan. The nursing processing model performs semantic reasoning and matching on the input behavior based on the plan rules, calculates the risk matching degree, and determines whether the current object behavior meets the triggering conditions of the risk event. The risk behavior matching result is obtained, which clearly identifies whether the current behavior belongs to the risk behavior type, and is accompanied by matching degree or risk level information.

[0201] S406: If the risk behavior determination result is a risk behavior type, querying the behavior response intervention measures of the current subject's behavior from the care event handling plan, performing a response intervention operation on the care subject based on the behavior response intervention measures, and performing the step of monitoring the care scene video of the care subject;

[0202] Behavioral response interventions refer to intervention strategies set out in the caregiving incident handling plan for specific risk behaviors, such as voice reminders, mobile phone notifications, or automatic interventions.

[0203] Response intervention operations refer to the actual intervention operations performed by the system on the care recipient based on the intervention measures queried, such as through voice broadcasts, push notifications, automatic animation playback, etc.

[0204] Indicatively, when the output risk behavior matching result is "risk behavior," the system searches for the corresponding response intervention measures from the care event handling plan, executes the response intervention measures, and first implements primary intervention (such as voice reminders) according to the hierarchical response strategy defined in the plan, and continuously monitors changes in the subject's behavior. If the primary intervention fails to solve the problem, it is upgraded to secondary intervention (such as mobile phone notifications) and advanced intervention (such as automatic animation playback or other linkage operations). After the response intervention measures are executed, the system continues to monitor the care scene video to ensure that the risk status is resolved in a timely manner, and records the intervention effect for subsequent analysis and optimization.

[0205] S408: If the risk behavior is determined to be a normal behavior type, the step of monitoring the care scene video of the care object is executed.

[0206] In one or more embodiments of this specification, the current subject's behavior is detected in real time based on the video of the care scene, and the detection results are compared with the care event handling plan to perform risk behavior inference processing, thereby obtaining a risk behavior matching result. If it is determined to be a risky behavior, the system retrieves the corresponding graded response intervention measures from the plan and implements the intervention on the care subject while continuing to monitor the video; if it is determined to be normal behavior, the monitoring continues. This closed-loop process ensures that the care system can respond to potential risks in real time and automatically take appropriate intervention measures according to the plan to ensure the safety of the care subject.

[0207] The following will be combined Figure 8 , the nursing treatment device provided in the embodiment of this specification is introduced in detail. It should be noted that, Figure 8 The nursing treatment device shown is used to execute this instruction Figures 1 to 7 For the convenience of explanation, only the part related to the embodiment of this specification is shown. For the specific technical details not disclosed, please refer to this specification. Figures 1 to 7 The embodiment shown.

[0208] See Figure 8 , which shows a schematic diagram of the structure of the nursing processing device according to an embodiment of the present specification. The nursing processing device 1 can be implemented as all or part of the device through software, hardware, or a combination of both. According to some embodiments, the nursing processing device 1 includes an information acquisition module 11, a plan generation module 12, and a nursing processing module 13, which are specifically used to:

[0209] The information acquisition module 11 is used to receive the care request information input by the user for the care object and obtain the care environment information of the care object;

[0210] A plan generation module 12 is configured to perform scenario-based care risk analysis on the care request using a large care processing model based on the care request information and the care environment information to obtain a plurality of risk care events, and to perform event handling reasoning based on each of the risk care events to obtain a care event handling plan;

[0211] The care processing module 13 is used to monitor the care scene video of the care object, and perform care processing on the object based on the care scene video through the care processing large model and the care event handling plan.

[0212] In a feasible implementation, the care request is analyzed based on the care request information and the care environment information using a care processing model to obtain a variety of risk care events, including:

[0213] Determine the care scenario context features and the user's key care demand features using a care processing large model based on the care request information and the care environment information;

[0214] Based on the care scenario context features and the user's key care demand features, a care processing large model is used to perform risk reasoning to obtain risk scenario type information and risk scenario semantic information;

[0215] Based on the risk scenario type information and the risk scenario semantic information, risk care event structuring processing is performed to obtain multiple risk care events.

[0216] In a feasible implementation, the determining of the care scenario context features and the user key care requirement features using a care processing large model based on the care request information and the care environment information includes:

[0217] Inputting the care request information and the care environment information into a care processing model, performing scene structured modeling processing on the care environment information to obtain a care scene semantic map, and using the care scene semantic map as a care scene context feature;

[0218] Key needs are extracted based on the semantic graph of the care scene and the care request information to obtain user attention intention, keyword information and attention emotional tendency information, and care needs are inferred based on the user attention intention, keyword information and attention emotional tendency information to obtain key care needs characteristics.

[0219] In a feasible implementation, the risk reasoning based on the care scenario context features and the user's key care demand features using the care processing large model to obtain risk scenario type information and risk scenario semantic information includes:

[0220] Fusing the care scenario context features and the user's key care demand features to obtain a scenario risk reasoning representation;

[0221] Risk classification processing is performed based on the scenario risk reasoning representation to obtain risk scenario type information, and scenario semantic reasoning is performed based on the risk scenario type information and the scenario risk reasoning representation to obtain risk scenario semantic information.

[0222] In a feasible implementation, the performing of event handling reasoning based on each of the risk nursing events to obtain a nursing event handling plan includes:

[0223] Determining reference intervention rules for each of the risk nursing events through the nursing processing macro model, and performing graded response reasoning based on the reference intervention rules to obtain graded response intervention measures;

[0224] The nursing risk events and the graded response intervention measures corresponding to the nursing risk events are structured through the nursing processing large model to obtain a nursing event handling plan.

[0225] In a feasible implementation, determining a reference intervention rule for each risk nursing event through the nursing processing macro model, and performing graded response reasoning based on the reference intervention rule to obtain a graded response intervention measure include:

[0226] Prioritizing each of the risk nursing events through the nursing processing macromodel to obtain a global nursing risk event set, and performing intervention rule matching on the nursing risk events in the global nursing risk event set based on a preset risk intervention library to obtain a reference intervention rule corresponding to each of the nursing risk events;

[0227] The risk scenario semantic information corresponding to the nursing risk event is obtained through the nursing processing large model, and the reference intervention rules are subjected to graded response reasoning based on the risk scenario semantic information to obtain graded response intervention measures.

[0228] In a feasible implementation, performing object care processing based on the care scene video through the care processing large model and the care event handling plan includes:

[0229] Based on the nursing scene video, the nursing processing large model is used to identify the current object behavior of the nursing object;

[0230] Performing risk behavior reasoning on the current subject's behavior based on the nursing event handling plan to obtain a risk behavior matching result;

[0231] If the risk behavior determination result is a risk behavior type, querying the behavior response intervention measures of the current subject's behavior from the care event handling plan, performing a response intervention operation on the care subject based on the behavior response intervention measures, and performing the step of monitoring the care scene video of the care subject;

[0232] If the risk behavior is determined to be a normal behavior type, the step of monitoring the care scene video of the care object is performed.

[0233] It should be noted that the aforementioned embodiments of the nursing care device, when executing the nursing care method, only illustrate the division of the aforementioned functional modules. In actual applications, the aforementioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the nursing care device and the nursing care method embodiments provided in the aforementioned embodiments are based on the same concept. The implementation process is detailed in the method embodiments and will not be repeated here.

[0234] The serial numbers of the embodiments in this specification are for description only and do not represent the advantages or disadvantages of the embodiments.

[0235] The embodiment of this specification also provides a computer storage medium, which can store multiple instructions, and the instructions are suitable for being loaded and executed by a processor as described above. Figures 1 to 7 The detailed implementation process of the nursing treatment method in the embodiment shown can be found in Figures 1 to 7 The detailed description of the illustrated embodiment will not be repeated here.

[0236] This specification also provides a computer program product, which stores at least one instruction, and the at least one instruction is loaded and executed by the processor as described above. Figures 1 to 7 The detailed implementation process of the nursing treatment method in the embodiment shown can be found in Figures 1 to 7 The detailed description of the illustrated embodiment will not be repeated here.

[0237] Please refer to Figure 9 , which shows a block diagram of the structure of an electronic device provided by an exemplary embodiment of this specification. The electronic device described in this specification may include one or more of the following components: a processor 110, a memory 120, an input device 130, an output device 140, and a bus 150. The processor 110, the memory 120, the input device 130, and the output device 140 may be connected via the bus 150.

[0238] The processor 110 may include one or more processing cores. The processor 110 utilizes various interfaces and circuits to connect various components within the electronic device. It executes instructions, programs, code sets, or instruction sets stored in the memory 120, as well as accesses data stored in the memory 120, to perform various functions of the electronic device and process data. Optionally, the processor 110 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor 110 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem handles wireless communications. It is understood that the modem may not be integrated into the processor 110 and may be implemented separately via a communications chip.

[0239] The memory 120 may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory 120 includes a non-transitory computer-readable storage medium. The memory 120 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 120 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the following various method embodiments, etc. The operating system may be an Android system, including a system deeply developed based on the Android system, an IOS system developed by Apple, including a system deeply developed based on the IOS system or other systems. The data storage area may also store data created by the electronic device during use, such as a phone book, audio and video data, chat record data, etc.

[0240] See also Figure 10As shown, the memory 120 can be divided into operating system space and user space. The operating system runs in the operating system space, and native and third-party applications run in the user space. In order to ensure that different third-party applications can achieve better operating results, the operating system allocates corresponding system resources to different third-party applications. However, the requirements for system resources in different application scenarios in the same third-party application are also different. For example, in the local resource loading scenario, the third-party application has higher requirements for disk reading speed; in the animation rendering scenario, the third-party application has higher requirements for GPU performance. The operating system and the third-party application are independent of each other, and the operating system often cannot perceive the current application scenario of the third-party application in a timely manner, resulting in the operating system being unable to perform targeted system resource adaptation according to the specific application scenario of the third-party application.

[0241] In order for the operating system to distinguish the specific application scenarios of third-party applications, it is necessary to open up data communication between third-party applications and the operating system so that the operating system can obtain the current scenario information of third-party applications at any time, and then perform targeted system resource adaptation based on the current scenario.

[0242] Taking the Android operating system as an example, the programs and data stored in the memory 120 are as follows: Figure 11As shown, the memory 120 may store a Linux kernel layer 320, a system runtime library layer 340, an application framework layer 360, and an application layer 380. The Linux kernel layer 320, the system runtime library layer 340, and the application framework layer 360 belong to the operating system space, and the application layer 380 belongs to the user space. The Linux kernel layer 320 provides underlying drivers for various hardware components of electronic devices, such as display drivers, audio drivers, camera drivers, Bluetooth drivers, Wi-Fi drivers, power management, etc. The system runtime library layer 340 provides major feature support for the Android system through some C / C++ libraries. For example, the SQLite library provides database support, the OpenGL / ES library provides 3D drawing support, and the Webkit library provides browser kernel support. The system runtime library layer 340 also provides the Android runtime library (Android runtime), which mainly provides some core libraries that allow developers to write Android applications using the Java language. The application framework layer 360 provides various APIs that may be used when building applications. Developers can also use these APIs to build their own applications, such as activity management, window management, view management, notification management, content provider management, package management, call management, resource management, and location management. The application layer 380 runs at least one application. These applications can be native applications that come with the operating system, such as contacts, SMS, clock, and camera applications, or third-party applications developed by third-party developers, such as games, instant messaging programs, and photo enhancement programs.

[0243] Taking the operating system as the IOS system as an example, the programs and data stored in the memory 120 are as follows: Figure 12As shown, the IOS system includes: a core operating system layer 420 (Core OS layer), a core service layer 440 (Core Services layer), a media layer 460 (Media layer), and a touchable layer 480 (Cocoa Touch Layer). The core operating system layer 420 includes the operating system kernel, drivers, and underlying program frameworks. These underlying program frameworks provide functions closer to the hardware for use by the program framework located in the core service layer 440. The core service layer 440 provides system services and / or program frameworks required by applications, such as the foundation framework, account framework, advertising framework, data storage framework, network connection framework, geographic location framework, motion framework, etc. The media layer 460 provides applications with audio-visual interfaces, such as graphics and image-related interfaces, audio technology-related interfaces, video technology-related interfaces, and wireless playback (AirPlay) interfaces for audio and video transmission technologies. The touchable layer 480 provides various commonly used interface-related frameworks for application development. The touchable layer 480 is responsible for user touch interaction operations on electronic devices. For example, local notification service, remote push service, advertising framework, game tool framework, message user interface (UI) framework, user interface UIKit framework, map framework, etc.

[0244] exist Figure 12 Among the frameworks shown, those relevant to most applications include, but are not limited to, the Foundation framework in the core services layer 440 and the UIKit framework in the touchable layer 480. The Foundation framework provides many basic object classes and data types, offering fundamental system services for all applications and having nothing to do with the UI. The classes provided by the UIKit framework are the foundational UI class library for creating touch-based user interfaces. iOS applications can use the UIKit framework to provide their UIs, providing the application infrastructure for building user interfaces, drawing, handling user interaction events, responding to gestures, and so on.

[0245] Among them, the method and principle of implementing data communication between third-party applications and the operating system in the IOS system can be referred to the Android system, and this manual will not go into details here.

[0246] Among them, the input device 130 is used to receive input instructions or data, and the input device 130 includes but is not limited to a keyboard, a mouse, a camera, a microphone or a touch device. The output device 140 is used to output instructions or data, and the output device 140 includes but is not limited to a display device and a speaker. In one example, the input device 130 and the output device 140 can be combined, and the input device 130 and the output device 140 are touch screen displays, which are used to receive touch operations on or near the user using any suitable objects such as fingers and touch pens, and to display the user interface of each application. The touch screen display is usually provided on the front panel of the electronic device. The touch screen display can be designed as a full screen, a curved screen or a special-shaped screen. The touch screen display can also be designed as a combination of a full screen and a curved screen, or a combination of a special-shaped screen and a curved screen, which is not limited in the embodiments of this specification.

[0247] In addition, those skilled in the art will understand that the structures of the electronic devices shown in the above figures do not limit the electronic devices. The electronic devices may include more or fewer components than shown, or may combine certain components, or arrange the components differently. For example, the electronic devices may also include radio frequency circuits, input units, sensors, audio circuits, wireless fidelity (WiFi) modules, power supplies, Bluetooth modules, and other components, which are not described in detail here.

[0248] In the embodiments of this specification, the execution entity of each step can be the electronic device described above. Optionally, the execution entity of each step is the operating system of the electronic device. The operating system can be Android, iOS, or other operating systems, and this embodiment of this specification does not limit this.

[0249] The electronic device of the embodiment of this specification may further be equipped with a display device, and the display device may be any device capable of realizing a display function, such as a cathode ray tube display (CR), a light-emitting diode display (LED), an electronic ink screen, a liquid crystal display (LCD), a plasma display panel (PDP), etc. The user may use the display device on the electronic device to view displayed text, images, videos and other information. The electronic device may be a smart phone, a tablet computer, a gaming device, an AR (Augmented Reality) device, a car, a data storage device, an audio playback device, a video playback device, a notebook, a desktop computing device, a wearable device such as an electronic watch, electronic glasses, an electronic helmet, an electronic bracelet, an electronic necklace, electronic clothing and the like.

[0250] exist Figure 9 In the electronic device shown, the processor 110 may be configured to call an application stored in the memory 120 and specifically perform the following operations:

[0251] Receive care request information input by a user for a care object and obtain care environment information of the care object; perform scenario care risk analysis on the care request using a large care processing model based on the care request information and the care environment information to obtain multiple risk care events; and perform event handling reasoning based on each of the risk care events to obtain a care event handling plan;

[0252] The care scene video of the care object is monitored, and the care event handling plan is used to perform care processing on the object based on the care scene video through the care processing large model.

[0253] In a feasible implementation, the care request is analyzed based on the care request information and the care environment information using a care processing model to obtain a variety of risk care events, including:

[0254] Determine the care scenario context features and the user's key care demand features using a care processing large model based on the care request information and the care environment information;

[0255] Based on the care scenario context features and the user's key care demand features, a care processing large model is used to perform risk reasoning to obtain risk scenario type information and risk scenario semantic information;

[0256] Based on the risk scenario type information and the risk scenario semantic information, risk care event structuring processing is performed to obtain multiple risk care events.

[0257] In a feasible implementation, the determining of the care scenario context features and the user key care requirement features using a care processing large model based on the care request information and the care environment information includes:

[0258] Inputting the care request information and the care environment information into a care processing model, performing scene structured modeling processing on the care environment information to obtain a care scene semantic map, and using the care scene semantic map as a care scene context feature;

[0259] Key needs are extracted based on the semantic graph of the care scene and the care request information to obtain user attention intention, keyword information and attention emotional tendency information, and care needs are inferred based on the user attention intention, keyword information and attention emotional tendency information to obtain key care needs characteristics.

[0260] In a feasible implementation, the risk reasoning based on the care scenario context features and the user's key care demand features using the care processing large model to obtain risk scenario type information and risk scenario semantic information includes:

[0261] Fusing the care scenario context features and the user's key care demand features to obtain a scenario risk reasoning representation;

[0262] Risk classification processing is performed based on the scenario risk reasoning representation to obtain risk scenario type information, and scenario semantic reasoning is performed based on the risk scenario type information and the scenario risk reasoning representation to obtain risk scenario semantic information.

[0263] In a feasible implementation, the performing of event handling reasoning based on each of the risk nursing events to obtain a nursing event handling plan includes:

[0264] Determining reference intervention rules for each of the risk nursing events through the nursing processing macro model, and performing graded response reasoning based on the reference intervention rules to obtain graded response intervention measures;

[0265] The nursing risk events and the graded response intervention measures corresponding to the nursing risk events are structured through the nursing processing large model to obtain a nursing event handling plan.

[0266] In a feasible implementation, determining a reference intervention rule for each risk nursing event through the nursing processing macro model, and performing graded response reasoning based on the reference intervention rule to obtain a graded response intervention measure include:

[0267] Prioritizing each of the risk nursing events through the nursing processing macromodel to obtain a global nursing risk event set, and performing intervention rule matching on the nursing risk events in the global nursing risk event set based on a preset risk intervention library to obtain a reference intervention rule corresponding to each of the nursing risk events;

[0268] The risk scenario semantic information corresponding to the nursing risk event is obtained through the nursing processing large model, and the reference intervention rules are subjected to graded response reasoning based on the risk scenario semantic information to obtain graded response intervention measures.

[0269] In a feasible implementation, performing object care processing based on the care scene video through the care processing large model and the care event handling plan includes:

[0270] Based on the nursing scene video, the nursing processing large model is used to identify the current object behavior of the nursing object;

[0271] Performing risk behavior reasoning on the current subject's behavior based on the nursing event handling plan to obtain a risk behavior matching result;

[0272] If the risk behavior determination result is a risk behavior type, querying the behavior response intervention measures of the current subject's behavior from the care event handling plan, performing a response intervention operation on the care subject based on the behavior response intervention measures, and performing the step of monitoring the care scene video of the care subject;

[0273] If the risk behavior is determined to be a normal behavior type, the step of monitoring the care scene video of the care object is performed.

[0274] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware through a computer program. The program can be stored in a computer-readable storage medium, and when executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory, or a random access memory.

[0275] The above disclosure is only a preferred embodiment of this specification, and certainly cannot be used to limit the scope of rights of this specification. Therefore, equivalent changes made according to the claims of this specification are still within the scope covered by this specification.

Claims

1. A nursing treatment method, characterized in that: The method comprises: Receiving care request information input by a user for a care object, and obtaining care environment information of the care object; Based on the care request information and the care environment information, a care processing large model is used to perform scenario care risk analysis on the care request to obtain multiple risk care events, and event handling reasoning is performed based on each of the risk care events to obtain a care event handling plan; The care scene video of the care object is monitored, and the care event handling plan is used to perform care processing on the object based on the care scene video through the care processing large model.

2. The method according to claim 1, wherein the step of performing scenario-based care risk analysis on the care request using a large care processing model based on the care request information and the care environment information to obtain multiple risk care events includes: Determine the care scenario context features and the user's key care demand features using a care processing large model based on the care request information and the care environment information; Based on the care scenario context features and the user's key care demand features, a care processing large model is used to perform risk reasoning to obtain risk scenario type information and risk scenario semantic information; Based on the risk scenario type information and the risk scenario semantic information, risk care event structuring processing is performed to obtain multiple risk care events.

3. The method according to claim 2, wherein determining the care scenario context features and the user's key care requirement features using a care processing macro model based on the care request information and the care environment information comprises: Inputting the care request information and the care environment information into a care processing model, performing scene structured modeling processing on the care environment information to obtain a care scene semantic map, and using the care scene semantic map as a care scene context feature; Key needs are extracted based on the semantic graph of the care scene and the care request information to obtain user attention intention, keyword information and attention emotional tendency information, and care needs are inferred based on the user attention intention, keyword information and attention emotional tendency information to obtain key care needs characteristics.

4. The method according to claim 2, wherein the step of performing risk reasoning based on the care scenario context features and the user's key care requirement features using a large care processing model to obtain risk scenario type information and risk scenario semantic information comprises: Fusing the care scenario context features and the user's key care demand features to obtain a scenario risk reasoning representation; Risk classification processing is performed based on the scenario risk reasoning representation to obtain risk scenario type information, and scenario semantic reasoning is performed based on the risk scenario type information and the scenario risk reasoning representation to obtain risk scenario semantic information.

5. The method according to claim 1, wherein the step of performing event handling reasoning based on each of the risk nursing events to obtain a nursing event handling plan comprises: Determining reference intervention rules for each of the risk nursing events through the nursing processing macro model, and performing graded response reasoning based on the reference intervention rules to obtain graded response intervention measures; The nursing risk events and the graded response intervention measures corresponding to the nursing risk events are structured through the nursing processing large model to obtain a nursing event handling plan.

6. The method according to claim 5, wherein determining a reference intervention rule for each risk nursing event using the nursing treatment macro model, and performing graded response reasoning based on the reference intervention rule to obtain a graded response intervention measure comprises: Prioritizing each of the risk nursing events through the nursing processing macromodel to obtain a global nursing risk event set, and performing intervention rule matching on the nursing risk events in the global nursing risk event set based on a preset risk intervention library to obtain a reference intervention rule corresponding to each of the nursing risk events; The risk scenario semantic information corresponding to the nursing risk event is obtained through the nursing processing large model, and the reference intervention rules are subjected to graded response reasoning based on the risk scenario semantic information to obtain graded response intervention measures.

7. The method according to claim 1, wherein performing subject care processing based on the care scene video through the care processing large model and the care event handling plan comprises: Based on the nursing scene video, the nursing processing large model is used to identify the current object behavior of the nursing object; Performing risk behavior reasoning on the current subject's behavior based on the nursing event handling plan to obtain a risk behavior matching result; If the risk behavior determination result is a risk behavior type, querying the behavior response intervention measures of the current subject's behavior from the care event handling plan, performing a response intervention operation on the care subject based on the behavior response intervention measures, and performing the step of monitoring the care scene video of the care subject; If the risk behavior is determined to be a normal behavior type, the step of monitoring the care scene video of the care object is performed.

8. A nursing treatment device, characterized in that: The device comprises: An information acquisition module is used to receive care request information input by a user for a care object and obtain care environment information of the care object; A plan generation module is configured to perform scenario-based care risk analysis on the care request based on the care request information and the care environment information using a large care processing model to obtain a plurality of risk care events, and to perform event handling reasoning based on each of the risk care events to obtain a care event handling plan; The care processing module is used to monitor the care scene video of the care object, and perform care processing on the object based on the care scene video through the care processing large model and the care event handling plan.

9. A computer storage medium, characterized in that The computer storage medium stores a plurality of instructions, which are suitable for being loaded by a processor and executing the method steps according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method steps according to any one of claims 1 to 7.

Images