Electric lying furniture control method and equipment based on intelligent agent and storage medium

Abstract

The invention discloses an intelligent agent-based electric lying furniture control method, equipment and a storage medium, and belongs to the technical field of electric furniture. The method comprises the following steps: receiving environment information of a data sensing agent, and / or receiving user context information of a user agent, constructing event information of a user according to the environment information and / or user context data, obtaining an agent service chain in a service workflow library according to the event information and based on preset rule information, and obtaining a service workflow of the user based on the agent service chain. And calling the function module intelligent body to execute the control action of the electric lying furniture. According to the method, the corresponding control strategies are organized and executed according to the real-time states and personalized contexts of different users, and the fitting degree of the electric lying furniture and the user service is remarkably improved.

Description

Technical Field

[0001] This application relates to the field of electric furniture technology, and in particular to a control method, device and storage medium for electric reclining furniture based on an intelligent agent. Background Technology

[0002] In related technologies, the intelligent control of electric reclining furniture such as smart beds or smart sofas often relies on preset fixed scene modes or simple conditional triggering rules. For example, after the preset time is reached or the user's sleep command is received, the system executes a fixed, pre-programmed control process, such as uniformly adjusting the bed posture, starting the heating, or activating the sleep aid mode.

[0003] However, static control methods based on fixed rules have control logic tightly coupled with specific hardware functions, resulting in software function iterations being limited by the hardware architecture. Simultaneously, data and services between different devices are isolated, making it difficult to achieve user-intent-centric cross-device collaboration. Furthermore, their underlying software is often monolithic, lacking system flexibility and unable to dynamically combine and schedule services on demand based on real-time perceived user status and personalized needs.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of this application is to provide a control method, device and storage medium for electric reclining furniture based on intelligent agents, which aims to solve the technical problem that the control logic of electric reclining furniture is difficult to meet the personalized needs of users.

[0006] To achieve the above objectives, this application provides a method for controlling electrically operated reclining furniture based on an intelligent agent, the method comprising the following steps: Receive environmental information from the data-sensing intelligent agent, and / or receive user context information from the user intelligent agent; Based on the environmental information and / or the user context data, construct the user's event information; Based on the event information and preset rule information, the intelligent agent service chain is obtained from the service workflow library; Based on the aforementioned intelligent agent service chain, the functional module intelligent agent is invoked to execute the control actions of the electric reclining furniture.

[0007] In one embodiment, after the step of invoking the functional module intelligent agent to execute the control action of the electric reclining furniture based on the intelligent agent service chain, the method further includes: Obtain the action execution result of at least one of the control actions returned by the intelligent agent of the functional module, and / or the user's reaction information based on the control actions; The service execution result and / or the reaction information are compared with the target parameters, and the corresponding instruction template is selected from the instruction template library based on the comparison result. Fill the key data from the service execution result into the selected instruction template to generate the target control instruction; The target control command is sent to the device control agent.

[0008] In one embodiment, before the step of constructing the user's event information based on the environmental information and / or the user context data, the method further includes: The system acquires the user's physiological signal data collected by the data-sensing intelligent agent and sends the user's physiological signal data to the sleep stage recognition intelligent agent. The sleep stage identification agent extracts features from the physiological signal data to obtain the user's sleep characteristics. Based on a preset sleep stage model, pattern recognition is performed on the user's sleep characteristics to obtain the user's sleep stage. Update the user's sleep stage to the user's context information.

[0009] In one embodiment, the step of constructing the user's event information based on the environmental information and / or the user context data further includes: Based on the environmental information and / or the user context data, the user's temperature regulation needs are determined; Invoke the thermal comfort calculation agent, and transmit the environmental data and the user context data to the thermal comfort calculation agent; The thermal comfort calculation agent's heat dissipation model is used to calculate the heat compensation amount obtained from the user's heat dissipation and the environmental heat exchange based on the environmental data and the user context data. Add the heat compensation amount to the event information.

[0010] In one embodiment, the step of obtaining the agent service chain from the service workflow library based on the event information and preset rule information includes: Analyze the event information to determine the event type and the target body region associated with the event; Based on the user profile in the user context information, obtain user health information and user preference information; By combining the user's health information, user preference information, time type, and / or target body region, a search query is constructed; Based on the search query, the agent service chain is matched in the service workflow library.

[0011] In one embodiment, the step of invoking the functional module intelligent agent to execute the control actions of the electric reclining furniture based on the intelligent agent service chain includes: Based on the intelligent agent service chain, determine the intelligent agent to be invoked, and the device driver information corresponding to the intelligent agent to be invoked; Based on the device driver information, generate device control commands; The device control command is sent to the intelligent agent to be invoked, so that the intelligent agent to be invoked drives the target device to perform the control action of the electric reclining furniture based on the device driving information.

[0012] In one embodiment, the step of obtaining the agent service chain from the service workflow library based on the event information and preset rule information further includes: Based on the event information and the user context data, determine the user's needs information; Based on the user demand information, select at least one functional module intelligent agent; Based on the functional information of the functional module intelligent agent, the dependency relationship of the functional module intelligent agent is determined; Based on the dependencies and the user requirements information, the execution order of the functional module agents is determined; Based on the execution order, construct the agent service chain corresponding to the functional module agent.

[0013] In one embodiment, before the steps of receiving environmental information of the data-aware intelligent agent and / or receiving user context information of the user intelligent agent, the method further includes: Receive user historical behavior data and environmental regulation records reported by the data-sensing intelligent agent; Feature extraction is performed on the user's historical behavior data and the environmental adjustment records to obtain the user's environmental preference features; The environmental preference features are input into a pre-trained behavior prediction model to obtain the predicted behavior features of the user within the target time period. Update the user profile in the user context information based on the predicted behavioral characteristics and / or the environmental preference characteristics.

[0014] In addition, to achieve the above objectives, this application also provides an agent-based electric reclining furniture control device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the agent-based electric reclining furniture control method described above.

[0015] In addition, to achieve the above objectives, this application also provides a storage medium, which is a computer-readable storage medium, and stores a computer program thereon. When the computer program is executed by a processor, it implements the steps of the agent-based electric reclining furniture control method described above.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: This application constructs event information that accurately represents the user's real-time state by receiving and fusing environmental information from data-aware intelligent agents and contextual information from user intelligent agents. Then, based on preset rules, it obtains matching intelligent agent service chains from the service workflow library and executes control actions by calling functional module intelligent agents. Through the combination mechanism of event-driven and dynamic service chains at the software level, electric reclining furniture can organize and execute corresponding control strategies according to the real-time state and personalized context of different users. This realizes the transformation from single fixed control to personalized dynamic regulation, significantly improving the intelligence level of the system and the fit of user services. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating the first embodiment of the intelligent agent-based control method for electric reclining furniture of this application; Figure 2 This is a flowchart illustrating the second embodiment of the intelligent agent-based electric reclining furniture control method of this application; Figure 3 This is a flowchart illustrating the third embodiment of the intelligent agent-based electric reclining furniture control method of this application; Figure 4 This is a schematic diagram of the structure of an agent-based electric reclining furniture control device in the hardware operating environment of the embodiment of this application.

[0020] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0022] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of this application embodiment is: receiving environmental information of the data-sensing intelligent agent, and / or receiving user context information of the user intelligent agent; constructing user event information based on the environmental information and / or user context data; obtaining the intelligent agent service chain from the service workflow library based on the event information and preset rule information; and calling the functional module intelligent agent to execute the control actions of the electric reclining furniture based on the intelligent agent service chain.

[0024] Existing technologies for intelligent control of electric reclining furniture, such as smart beds or smart sofas, largely rely on preset fixed scene patterns or simple conditional triggering rules. For example, upon reaching a preset time or receiving a user's sleep command, the system executes a fixed, pre-programmed control process, such as uniformly adjusting the bed's posture, activating heating, or turning on a sleep aid mode. However, this static control method based on fixed rules tightly couples its control logic with specific hardware functions, resulting in software function iterations being limited by the hardware architecture. Simultaneously, data and services between different devices are isolated, making it difficult to achieve user-intent-centric cross-device collaboration. Furthermore, the underlying software is often monolithic, lacking system flexibility and unable to dynamically combine and schedule services on demand based on real-time perceived user status and personalized needs.

[0025] This application constructs event information that accurately represents the user's real-time state by receiving and fusing environmental information from data-aware intelligent agents and contextual information from user intelligent agents. Then, based on preset rules, it obtains matching intelligent agent service chains from the service workflow library and executes control actions by calling functional module intelligent agents. Through the combination mechanism of event-driven and dynamic service chains at the software level, electric reclining furniture can autonomously and flexibly organize and execute corresponding control strategies according to the real-time state and personalized context of different users. This realizes the transformation from single fixed control to personalized dynamic regulation, significantly improving the intelligence level of the system and the fit of user services.

[0026] To better understand the above technical solutions, exemplary embodiments of this application will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of this application and to fully convey the scope of this application to those skilled in the art.

[0027] It should be noted that the executing entity in this embodiment can be a furniture control system, or a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of achieving the above functions, or an intelligent agent-based electric reclining furniture control device, etc. This embodiment does not specifically limit it. The following uses a furniture control system as an example to describe this embodiment and the following embodiments.

[0028] Based on this, embodiments of this application provide a method for controlling electrically operated reclining furniture based on an intelligent agent, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the intelligent agent-based control method for electric reclining furniture in this application.

[0029] In this embodiment, the intelligent agent-based electric reclining furniture control method includes steps S10~S40: Step S10: Receive environmental information from the data-sensing agent and / or receive user context information from the user agent; In this embodiment, user context information includes user profiles, user health information, and / or user preference information, which are used to enable the furniture control system to understand the user's personalized needs. The furniture control system establishes a complete foundation for user environment and state perception through multi-source data acquisition and fusion technology. The data perception agent, acting as a hardware abstraction layer, is responsible for collecting raw data from various sensors and performing preliminary processing, while the user agent continuously learns user behavior patterns to build dynamically updated user profiles. These two agents together constitute the system's perception foundation, providing data support for subsequent intelligent decision-making.

[0030] It's important to note that the furniture control system architecture includes multiple functionally decoupled dedicated agents. For example, the data perception agent is responsible for unified access and management of data from standard mattress sensors, environmental sensors, and user input, and for preprocessing and standardization. The user profiling agent manages the user's static data (underlying medical conditions, preferences), learns user behavior patterns, and dynamically outputs the user's current health context. The sleep stage identification agent, as a microservice, is invoked to analyze real-time physiological data and return sleep stage results. The thermal comfort calculation agent integrates a heat dissipation model, combines environmental data and user profiles, and calculates the required heat compensation. The decision scheduling agent, acting as the system's "brain," does not directly process data but, according to predetermined strategies and workflows, invokes, coordinates, and organizes the services of the aforementioned agents. For instance, upon receiving a user's sleep signal, it sequentially invokes the user profiling agent to obtain preferences, the sleep stage identification agent to obtain the current stage, and the thermal comfort calculation agent to obtain the target temperature, finally generating control commands. The device control agent receives instructions from the decision scheduling agent and converts them into drive signals for standard hardware, such as mattress zone heating film, air conditioner, and humidifier.

[0031] Specifically, the decision-making agent first sends a data request instruction to the data-aware agent via a distributed message middleware. This instruction includes metadata descriptions of the required data type and constraints on acquisition parameters. Upon receiving the request, the data-aware agent invokes the corresponding sensor hardware, including temperature sensors, humidity sensors, mattress pressure sensors, and motion sensors, through the device driver layer to collect raw physical signals. The collected raw data undergoes filtering and noise reduction processing by the signal conditioning module, and is then converted into structured environmental data objects by the feature extraction module. These environmental data objects are encapsulated in a unified JSON-LD format, containing metadata such as data source, timestamp, numerical range, and confidence level. Simultaneously, the decision-making agent initiates a context query request to the user agent through the user data interface. The user agent retrieves the user's static profile and dynamic behavioral data from its knowledge graph. The static profile includes basic medical history, medication usage, and physiological parameter thresholds, while the dynamic behavioral data includes recent sleep patterns, activity patterns, and preference settings. The user agent uses time-series data analysis algorithms to identify user behavior trends and predicts the user's current state using a hidden Markov model. All this data is integrated into a multi-dimensional user context object.

[0032] Optionally, the furniture control system can employ an asynchronous data stream processing architecture. The data-aware agent continuously publishes environmental data to specific topics on the message bus, while the user agent periodically pushes updated user context to user data topics. The decision-making agent subscribes to these topics to obtain the latest data in real time, while setting data quality checkpoints to identify and correct outliers. This publish-subscribe model ensures data timeliness and consistency while reducing system coupling. It should be noted that existing smart home products suffer from data silos, preventing user-centric cross-device collaborative services between different devices. By establishing a unified data access and management mechanism, with the data-aware agent responsible for unified access and management of data from standard mattress sensors, environmental sensors, and user input, and performing preprocessing and standardization, data isolation is effectively broken down.

[0033] Step S20: Construct the user's event information based on environmental information and / or user context data; In this embodiment, the furniture control system transforms raw sensory data into event representations with clear semantics, enabling intelligent decision-making. The event information is a standardized data structure that encapsulates changes in the environment or user state, including semantic interpretations and contextual relationships, providing precise input for subsequent service chain selection.

[0034] Specifically, the decision-making agent first performs multi-dimensional correlation analysis on the received environmental information and user context data, including three sub-steps: temporal alignment, spatial correlation, and semantic annotation. In temporal alignment, the system synchronizes data from different sources according to a unified time benchmark, eliminating time deviations caused by different collection frequencies. In spatial correlation, for data with location attributes, such as temperature readings of different areas of a mattress, the system establishes a regional correlation model through spatial indexing. In semantic annotation, the system uses a predefined domain ontology to semantically annotate the data, giving the original data clear business meaning. After completing data correlation, the decision-making agent calls the rule inference engine to match the correlated data with predefined event triggering conditions. The conditions are represented using production rules, including various types such as simple threshold rules, composite logic rules, and temporal pattern rules. When a matching rule is found, the decision-making agent instantiates the corresponding event object, which contains attributes such as event type, severity, scope of impact, timeliness, and processing priority. Finally, the decision-making agent publishes the generated event object through the event bus and records it in the event log for subsequent analysis and optimization.

[0035] Optionally, the system also incorporates machine learning techniques to enhance the accuracy of event recognition. The decision agent inputs environmental information and user context data into a trained event classification model, built on a deep neural network capable of recognizing complex nonlinear patterns. The model outputs a probability distribution for different event types. The decision agent combines rule-based reasoning with the model output to determine the final event type and attributes. This hybrid approach significantly improves the recall and accuracy of event recognition. For example, when the user profiling agent indicates that a user is diabetic and the data perception agent detects that the foot area temperature is below a set threshold, the decision scheduling agent can accurately construct the corresponding event information, creating conditions for triggering a high-priority service chain.

[0036] For example, the system determines the user's temperature adjustment needs based on the environmental information and / or the user context data, invokes the thermal comfort calculation agent, and transmits the environmental data and the user context data to the thermal comfort calculation agent. Through the thermal dissipation model of the thermal comfort calculation agent, the system calculates the heat compensation amount obtained by the user's heat dissipation and the heat exchange with the environment based on the environmental data and the user context data, and adds the heat compensation amount to the event information.

[0037] Step S30: Based on the event information and preset rule information, obtain the agent service chain from the service workflow library; In this embodiment, the decision-making agent needs to map event information into specific service execution plans. By establishing a dynamic mapping mechanism between events and service chains, the system can flexibly select the most suitable service combination scheme for different user states and environmental conditions, thereby achieving personalized services.

[0038] As an optional implementation, the decision scheduling agent dynamically combines services, receives event messages, and selects a matching service chain from a pre-set service workflow library based on the event type and user profile data; it then sequentially invokes each agent involved in the service chain. The furniture control system parses event information to determine the event type and the target body region associated with the event. Based on the user profile in the user context information, it obtains user health information and user preference information. Combining the user health information, user preference information, the time type, and / or the target body region, it constructs a retrieval formula. Based on this retrieval formula, it matches intelligent agent service chains from the service workflow library.

[0039] Specifically, after receiving event information, the decision-making agent first performs event parsing and feature extraction. This process includes event type identification, key parameter extraction, and contextual analysis. Event type identification determines the basic category of the event, such as environmental anomalies, changes in user status, or equipment malfunctions. Key parameter extraction extracts core elements affecting service selection from the event information, such as temperature deviation values, user sleep stages, or device identifiers. Contextual analysis associates the current event with historical events, user profiles, and environmental states to form a complete decision context. After completing event parsing, the decision-making agent uses multidimensional retrieval technology to search for matching service chains in the service workflow library. The service workflow library uses a graph database to store service chain templates. Each template contains a set of nodes and a set of edges. Nodes represent specific functional agents, and edges represent data flow and control flow relationships. The retrieval process uses a content-based matching algorithm, comprehensively considering multiple dimensions such as event type, user profile, environmental state, and device availability, to calculate the matching degree between each service chain template and the current scenario, and selects the template with the highest matching degree as the execution basis.

[0040] As an alternative implementation, the decision-making agent can also select agents from various functional modules based on event information to form an agent service chain. The decision-making agent determines user requirements based on event information and user context data. Based on these requirements, it selects at least one functional module agent, determines the dependencies between these agents based on their functional information, and then determines the execution order of the functional module agents based on these dependencies and the user requirements. Finally, based on this execution order, it constructs the agent service chain corresponding to each functional module agent.

[0041] Specifically, the decision-making agent first selects a group of core functional module agents from the agent registry center based on event information and user needs. Then, it analyzes the functional and data dependencies between agents and generates temporary service chains based on graph programming algorithms. After verification, the newly generated service chains can be saved to the service workflow library for use in subsequent similar scenarios, realizing the system's self-learning and adaptive capabilities.

[0042] It should be noted that the decision scheduling agent's working method includes monitoring changes in user status and environment, and dynamically combining different agent service chains based on different events. For example, when the user profiling agent indicates that the user is diabetic and the data perception agent detects that the foot area temperature is below a set threshold, the decision scheduling agent will trigger a high-priority service chain, prioritizing the invocation of the device control agent to increase the foot heating power, rather than executing a global average heating strategy.

[0043] Step S40: Based on the intelligent agent service chain, call the functional module intelligent agent to execute the control actions of the electric reclining furniture.

[0044] In this embodiment, the furniture control system, based on a service chain definition, coordinates the orderly execution of multiple functional agents to achieve precise control of the electric reclining furniture. This involves multiple stages, including service orchestration, task scheduling, exception handling, and result aggregation, thus realizing the system's collaborative execution capabilities.

[0045] Specifically, the decision-making agent first instantiates the selected service chain, allocating execution resources and setting input parameters for each agent node. During instantiation, the decision-making agent builds an execution plan based on the dependencies in the service chain definition, determining the execution order and data transmission path for each agent. For service chains with parallel branches, the decision-making agent creates multiple execution threads and ensures data consistency through a synchronization mechanism. After instantiation, the decision-making agent sequentially calls each functional agent according to the execution plan. During the call, the decision-making agent sends execution commands to the target agent through the service gateway, containing necessary input parameters and execution constraints. After each agent completes its processing, it returns the result to the decision-making agent, which uses the output of the previous agent as the input of the next agent according to the service chain definition, forming a processing pipeline. Throughout the execution process, the decision-making agent continuously monitors the execution status of each agent and handles anomalies such as timeouts and failures, including retry, replacement, or overall rollback strategies.

[0046] Optionally, the system employs a distributed transaction mechanism to ensure the atomicity and consistency of service chain execution. Before starting to execute a service chain, the decision-making agent registers a global transaction with the transaction manager, and the execution of each agent is treated as a branch of the transaction. Once all agents have successfully executed, the decision-making agent commits the global transaction, ensuring that all operations take effect simultaneously. If any agent fails, the decision-making agent rolls back the entire transaction, guaranteeing the consistency of the system state.

[0047] It's important to note that the decision-making and scheduling agent, acting as the system's brain, invokes, coordinates, and organizes the services of multiple agents according to predetermined strategies and workflows. For example, upon receiving a user's sleep signal, it sequentially invokes the user profiling agent to obtain preferences, the sleep stage identification agent to obtain the current stage, and the thermal comfort calculation agent to obtain the target temperature, finally generating control commands. This architecture allows services to iterate rapidly and be combined on demand, with each agent capable of independent upgrades and optimizations, giving the entire system continuous evolution capabilities.

[0048] As an optional implementation, the furniture control system determines the intelligent agent to be invoked and the corresponding device driver information based on the intelligent agent service chain. Based on the device driver information, it generates device control instructions and sends the device control instructions to the intelligent agent to be invoked, so that the intelligent agent to be invoked drives the target device to perform control actions of the electric reclining furniture based on the device driver information.

[0049] As an alternative implementation, the device control agent maintains a device driver library. Through different driver plugins, hardware devices of different brands and protocols, such as a standard mattress, air conditioner A, and humidifier B, are abstracted into a unified temperature and humidity control interface. After the decision-making and scheduling agent issues commands, the device control agent is responsible for translating them into the specific device's control protocol, such as infrared, Wi-Fi, or Zigbee commands. This achieves interface standardization, rather than hardware homogenization.

[0050] This application embodiment receives and integrates environmental information from data-aware intelligent agents and contextual information from user intelligent agents to construct event information that accurately represents the user's real-time state. Then, based on preset rules, it obtains matching intelligent agent service chains from the service workflow library and calls functional module intelligent agents to execute control actions. Through the combination mechanism of event-driven and dynamic service chains at the software level, the electric reclining furniture can autonomously and flexibly organize and execute corresponding control strategies according to the real-time state and personalized context of different users. This realizes the transformation from single fixed control to personalized dynamic regulation, significantly improving the system's intelligence level and the fit of user services.

[0051] Based on the same inventive concept, this application also provides a second embodiment, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the intelligent agent-based electric reclining furniture control method of this application.

[0052] In this embodiment, the agent-based electric reclining furniture control method further includes steps S51-S54: Step S51: Obtain the action execution result of at least one control action returned by the functional module intelligent agent, and / or the user's reaction information based on the control action; Step S52: Compare the service execution results and / or response information with the target parameters, and select the corresponding instruction template from the instruction template library based on the comparison results; Step S53: Fill the key data from the service execution result into the selected instruction template to generate the target control instruction; Step S54: Send the target control command to the device control agent.

[0053] In this embodiment, the decision-making agent receives execution status reports from various functional module agents via an asynchronous message queue. These reports include instruction execution status data returned by the device control agent, such as the actual power value of the heating unit and specific parameters like the motor rotation angle. Simultaneously, the data sensing agent collects feedback information such as changes in user physiological indicators. This data collectively constitutes a complete view of the system feedback. Dynamic adjustment of the control strategy is achieved based on a multi-dimensional evaluation algorithm. The decision-making agent calculates the similarity between the received feedback data and a preset target parameter range. For example, it inputs indicators such as the deviation between the actual temperature and the target temperature, and the user's heart rate change trend, into the evaluation model. Based on the deviation level, it matches the most suitable adjustment strategy from an instruction template library. This library uses a hierarchical classification structure to store instruction templates for different scenarios. Data binding technology is used to dynamically fill key parameters into the instruction templates. The decision-making agent parses the variable placeholders in the templates, extracts the corresponding values ​​from the feedback data, and replaces them. For example, it fills the corresponding field of the temperature control instruction with the calculated new temperature value, ensuring the accuracy and real-time nature of the generated instructions. The decision-making agent transmits the optimized instructions to the device control agent through a secure communication protocol and establishes an acknowledgment mechanism to monitor the delivery status of the instructions. For critical instructions, the device control agent is required to return an execution acknowledgment signal, thus forming a complete control closed loop.

[0054] This embodiment introduces a multi-source feedback and instruction optimization mechanism, enabling the system to dynamically adjust the control strategy based on the actual execution effect, effectively improving control accuracy and system adaptability, and realizing the upgrade from open-loop control to intelligent closed-loop control.

[0055] Since the system described in Embodiment 2 of this application is a system used to implement the method of Embodiment 1 of this application, those skilled in the art can understand the specific structure and variations of the system based on the method described in Embodiment 1 of this application, and therefore will not be described again here. All systems used in the method of Embodiment 1 of this application fall within the scope of protection of this application.

[0056] Based on the same inventive concept, this application also provides a third embodiment, referring to... Figure 3 , Figure 3 This is a flowchart illustrating the third embodiment of the intelligent agent-based electric reclining furniture control method of this application.

[0057] In this embodiment, the agent-based electric reclining furniture control method further includes steps S11-S14: Step S11: Receive user historical behavior data and environmental adjustment records reported by the data-sensing intelligent agent; Step S12: Extract features from the user's historical behavior data and the environmental adjustment records to obtain the user's environmental preference features; Step S13: Input the environmental preference features into the pre-trained behavior prediction model to obtain the predicted behavior features of the user within the target time period; Step S14: Update the user profile in the user context information based on the predicted behavioral features and / or the environmental preference features.

[0058] In this embodiment, the decision-making agent periodically collects historical user behavior data recorded by the data-sensing agent through a data interface. This includes time-series data such as sleep time distribution, turning frequency statistics, and commonly used temperature settings, as well as operation logs such as environmental adjustment records and humidity adjustment records. This data is stored in a distributed database in time-series format to ensure data integrity and traceability. Meaningful patterns are extracted from the raw data using feature engineering methods. The decision-making agent applies a sliding window algorithm to segment the time-series data, calculates statistical features such as mean, variance, and extreme values ​​for each time period using statistical analysis methods, and identifies user behavior patterns in different scenarios using clustering algorithms. Finally, it generates feature vectors representing user preferences, such as preferred nighttime temperature ranges and humidity adjustment tendencies before waking up.

[0059] Based on machine learning-based behavior prediction, the decision-making agent inputs feature vectors into a pre-trained neural network model. This model analyzes time dependencies and scene association patterns in historical data to output the user's expected behavior within a specific time period. For example, it predicts the user's sensitivity to temperature changes after entering deep sleep or the intensity of their need for localized heating in the latter half of the night. The prediction results are represented as a probability distribution indicating the likelihood of different behaviors occurring. To achieve dynamic updates to the user profile, the decision-making agent integrates newly discovered preference features and prediction results with existing user profiles. A weight update algorithm adjusts the confidence levels of various parameters in the profile, assigning higher weights to frequently occurring patterns. Simultaneously, a time decay factor reduces the impact of outdated data, ensuring that the profile always reflects the user's latest characteristics.

[0060] Optionally, the furniture control system can also acquire the user's physiological signal data collected by the data sensing agent, and send the user's physiological signal data to the sleep stage recognition agent. The sleep stage recognition agent extracts features from the physiological signal data to obtain the user's sleep characteristics, performs pattern recognition on the user's sleep characteristics based on the preset sleep stage model, obtains the user's sleep stage, and updates the user's sleep stage to the user's context information.

[0061] It's important to note that the computationally intensive sleep staging algorithm is encapsulated as a standalone microservice accessible via a network API—the sleep staging identification agent. Other agents, such as the decision-making and scheduling agent, do not need to concern themselves with its internal model structure; they simply send standardized data packets to it and retrieve the staging results. This allows the algorithm model to be independently upgraded and replaced, such as from the L model to a more advanced model, without affecting other parts of the system.

[0062] This embodiment establishes a user behavior prediction and profile update mechanism, enabling the system to anticipate user needs and optimize service strategies in advance. This provides accurate user context support for intelligent decision-making and significantly improves the system's forward-looking and personalized service level.

[0063] Since the system described in Embodiment 2 of this application is a system used to implement the method of Embodiment 1 of this application, those skilled in the art can understand the specific structure and variations of the system based on the method described in Embodiment 1 of this application, and therefore will not be described again here. All systems used in the method of Embodiment 1 of this application fall within the scope of protection of this application.

[0064] This application provides an agent-based electric reclining furniture control device, the device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the agent-based electric reclining furniture control method of the above embodiment 1.

[0065] The following is for reference. Figure 4 This document illustrates a structural schematic diagram of an agent-based electric reclining furniture control device suitable for implementing embodiments of this application. The agent-based electric reclining furniture control device in this application embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The illustrated agent-based electric reclining furniture control device is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0066] like Figure 4As shown, the agent-based electric reclining furniture control device may include a processing unit 1001 (e.g., a core processor, graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the agent-based electric reclining furniture control device. The processing unit 1001, the ROM 1002, and the RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the agent-based motorized reclining furniture control device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows an agent-based motorized reclining furniture control device with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0067] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0068] The agent-based electric reclining furniture control device provided in this application, employing the agent-based electric reclining furniture control method described in the above embodiments, can solve the technical problem that the control logic of electric reclining furniture is difficult to meet the personalized needs of users. Compared with the prior art, the beneficial effects of the agent-based electric reclining furniture control device provided in this application are the same as those of the agent-based electric reclining furniture control method provided in the above embodiments, and other technical features in this agent-based electric reclining furniture control device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0069] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0070] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0071] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the agent-based electric reclining furniture control method in the above embodiments.

[0072] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, radio frequency (RF), etc., or any suitable combination thereof.

[0073] The aforementioned computer-readable storage medium may be included in an agent-based electric reclining furniture control device; or it may exist independently and not assembled into an agent-based electric reclining furniture control device.

[0074] The aforementioned computer-readable storage medium carries one or more programs. When the aforementioned one or more programs are executed by the agent-based electric reclining furniture control device, the agent-based electric reclining furniture control device: receives environmental information of the data sensing agent and / or receives user context information of the user agent; constructs user event information based on the environmental information and / or user context data; obtains the agent service chain from the service workflow library based on the event information and preset rule information; and calls the functional module agent to perform the control actions of the electric reclining furniture based on the agent service chain.

[0075] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0076] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0077] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0078] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., computer programs) for executing the above-described agent-based electric reclining furniture control method. This solves the technical problem that the control logic of electric reclining furniture is difficult to meet the personalized needs of users. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the agent-based electric reclining furniture control method provided in the above embodiments, and will not be repeated here.

[0079] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for controlling electrically operated reclining furniture based on an intelligent agent, characterized in that, The method includes the following steps: Receive environmental information from the data-sensing intelligent agent, and / or receive user context information from the user intelligent agent; Based on the environmental information and / or the user context data, construct the user's event information; Based on the event information and preset rule information, the intelligent agent service chain is obtained from the service workflow library; Based on the aforementioned intelligent agent service chain, the functional module intelligent agent is invoked to execute the control actions of the electric reclining furniture.

2. The method as described in claim 1, characterized in that, After the step of calling the functional module intelligent agent to execute the control actions of the electric reclining furniture based on the intelligent agent service chain, the method further includes: Obtain the action execution result of at least one of the control actions returned by the intelligent agent of the functional module, and / or the user's reaction information based on the control actions; The service execution result and / or the reaction information are compared with the target parameters, and the corresponding instruction template is selected from the instruction template library based on the comparison result. Fill the key data from the service execution result into the selected instruction template to generate the target control instruction; The target control command is sent to the device control agent.

3. The method as described in claim 1, characterized in that, Before the step of constructing the user's event information based on the environmental information and / or the user context data, the method further includes: The system acquires the user's physiological signal data collected by the data-sensing intelligent agent and sends the user's physiological signal data to the sleep stage recognition intelligent agent. The sleep stage identification agent extracts features from the physiological signal data to obtain the user's sleep characteristics. Based on a preset sleep stage model, pattern recognition is performed on the user's sleep characteristics to obtain the user's sleep stage. Update the user's sleep stage to the user's context information.

4. The method as described in claim 1, characterized in that, The step of constructing the user's event information based on the environmental information and / or the user context data further includes: Based on the environmental information and / or the user context data, the user's temperature regulation needs are determined; Invoke the thermal comfort calculation agent, and transmit the environmental data and the user context data to the thermal comfort calculation agent; The thermal comfort calculation agent's heat dissipation model is used to calculate the heat compensation amount obtained from the user's heat dissipation and the environmental heat exchange based on the environmental data and the user context data. Add the heat compensation amount to the event information.

5. The method as described in claim 1, characterized in that, The step of obtaining the agent service chain from the service workflow library based on the event information and preset rule information includes: Analyze the event information to determine the event type and the target body region associated with the event; Based on the user profile in the user context information, obtain user health information and user preference information; By combining the user's health information, user preference information, time type, and / or target body region, a search query is constructed; Based on the search query, the agent service chain is matched in the service workflow library.

6. The method as described in claim 1, characterized in that, The step of invoking the functional module intelligent agent to execute the control actions of the electric reclining furniture based on the intelligent agent service chain includes: Based on the intelligent agent service chain, determine the intelligent agent to be invoked, and the device driver information corresponding to the intelligent agent to be invoked; Based on the device driver information, generate device control commands; The device control command is sent to the intelligent agent to be invoked, so that the intelligent agent to be invoked drives the target device to perform the control action of the electric reclining furniture based on the device driving information.

7. The method as described in claim 1, characterized in that, The step of obtaining the agent service chain from the service workflow library based on the event information and preset rule information further includes: Based on the event information and the user context data, determine the user's needs information; Based on the user demand information, select at least one functional module intelligent agent; Based on the functional information of the functional module intelligent agent, the dependency relationship of the functional module intelligent agent is determined; Based on the dependencies and the user requirements information, the execution order of the functional module agents is determined; Based on the execution order, construct the agent service chain corresponding to the functional module agent.

8. The method as described in claim 1, characterized in that, Before the steps of receiving environmental information of the data-sensing intelligent agent and / or receiving user context information of the user intelligent agent, the method further includes: Receive user historical behavior data and environmental regulation records reported by the data-sensing intelligent agent; Feature extraction is performed on the user's historical behavior data and the environmental adjustment records to obtain the user's environmental preference features; The environmental preference features are input into a pre-trained behavior prediction model to obtain the predicted behavior features of the user within the target time period. Update the user profile in the user context information based on the predicted behavioral characteristics and / or the environmental preference characteristics.

9. A control device for electric reclining furniture based on an intelligent agent, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the agent-based electric reclining furniture control method as described in any one of claims 1 to 8.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the agent-based electric reclining furniture control method as described in any one of claims 1 to 8.

Images