Intelligent control method and device for heating equipment based on user action sensing

Abstract

The application discloses a kind of based on user action induction heating equipment intelligent management and control method and device, the method includes: when detecting that there is target user in the management and control scene corresponding to heating equipment, the action data of target user in management and control scene is collected;Analysis action data, obtain the multiple action nodes of target user in management and control scene and the node information of target user at each action node;According to all node information, judge whether there is target node satisfying preset heating control condition in all action nodes;When judging that there is target node satisfying heating control condition in all action nodes, according to the node information corresponding to target node, generate heating control parameter for heating equipment, and adjust the heating output of heating equipment according to heating control parameter.It can be seen that the present application can improve the intelligent degree of heating, improve the real-time control accuracy of heating.

Description

Technical Field

[0001] This invention relates to the field of heating control technology, and in particular to an intelligent control method and device for heating equipment based on user motion sensing. Background Technology

[0002] With the development and popularization of intelligent technologies, these technologies are beginning to enter users' lives, with smart homes being one such application. Simultaneously, smart home applications are increasingly incorporating personalized user needs and enabling the interconnection of multiple subsystems related to home life, such as security, lighting control, curtain control, smart appliances, and indoor heating, to achieve intelligent integration and control, thereby bringing users a completely new home living experience. Indoor heating, in particular, supplies heat to the indoor environment to maintain a certain temperature, creating comfortable living conditions.

[0003] However, in the field of indoor smart heating, the level of intelligence is currently insufficient, limited to control based on users' timed and temperature-controlled needs. This results in significant energy consumption and unnecessary energy waste during actual intelligent control. Furthermore, this type of smart heating cannot adapt to users' real-time adjustment needs, leading to a poor user experience. Therefore, it is crucial to provide a method to improve the intelligence level and real-time control accuracy of existing heating systems, addressing their low level of intelligence and inability to meet users' real-time heating requirements. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method and device for intelligent control of heating equipment based on user action sensing, which can improve the level of intelligence of heating and improve the accuracy of real-time control of heating.

[0005] To address the aforementioned technical problems, the first aspect of this invention discloses an intelligent control method for heating equipment based on user motion sensing, the method comprising:

[0006] When a target user is detected in the control scenario corresponding to the heating equipment, action data of the target user in the control scenario is collected.

[0007] By analyzing the action data, multiple action nodes of the target user in the control scenario and node information of the target user at each action node are obtained;

[0008] Based on all the node information, determine whether there is a target node among all the action nodes that meets the preset heating control conditions;

[0009] When it is determined that there is a target node among all the action nodes that meets the heating control conditions, heating control parameters for the heating equipment are generated according to the node information corresponding to the target node, and the heating output of the heating equipment is adjusted according to the heating control parameters.

[0010] As an optional implementation, in the first aspect of the present invention, analyzing the action data to obtain multiple action nodes of the target user in the control scenario and node information of the target user at each action node includes:

[0011] Based on the action data, multiple action nodes in which the target user stays in the control scenario for a longer than a preset duration are identified, and node data corresponding to each action node is extracted from the action data, using each action node as a benchmark.

[0012] Based on the user profile of the target user, a tracking model for the target user is generated, the tracking model including multiple tracking points corresponding to the user profile;

[0013] By combining the tracking model to analyze each piece of node data, the model tracking information of the target user at each action node is obtained, which serves as the node information of the target user at each action node;

[0014] The model tracking information includes the model movement trajectory, model posture, and model dwell time of the tracking model at each action node.

[0015] As an optional implementation, in the first aspect of the present invention, the step of combining the tracking model to analyze each piece of node data to obtain the model tracking information of the target user at each action node includes:

[0016] For each action node, the starting position of the tracking model recorded at that action node is determined based on the node data corresponding to that action node;

[0017] Using the model's starting position as a base point, determine all model movement information of the tracking model at that action node; all model movement information includes the model movement trajectory, model dwell time, and model posture;

[0018] The model pose is matched with a preset action database to obtain the target action pose that matches the model pose in the action database and its corresponding pose information.

[0019] The model movement trajectory, model dwell time, target action posture and corresponding posture information are determined as the model tracking information of the action node;

[0020] The model movement trajectory corresponding to all the aforementioned action nodes is determined in the following way:

[0021] For each action node, the element coordinate movement information of the tracking element in the action node within a unit tracking time is determined, using a preset tracking element as the unit.

[0022] Based on the coordinate movement information of all the elements, a trajectory diagram corresponding to the tracked element is drawn to obtain the model movement trajectory as the action node;

[0023] The preset tracking elements include the overall tracking model or all individual tracking points.

[0024] As an optional implementation, in the first aspect of the present invention, determining whether there is a target node among all the action nodes that meets the preset heating control conditions based on all the node information includes:

[0025] Based on all the node information, the state information of the target user at each action node is determined. The state information includes static information and / or dynamic information. The static information includes the target user's current user state, which includes one of the following: sleep state, leisure and entertainment state, exercise state, bathing state, and work state. The dynamic information is the information recorded when the target user switches between two different user states. Each user state corresponds to a heating control temperature of a heating device.

[0026] When the status information includes the static information, it is determined whether there is a target state in the user status corresponding to each action node that matches the preset adjustment state that needs to be executed for heating control; if so, the action node corresponding to the target state is determined to be a target node that meets the preset heating control conditions.

[0027] The adjustment states include the sleep resting state, the exercise state, and the bathing state;

[0028] When the status information includes the dynamic information, determine whether there is a temperature difference node among all the action nodes where the temperature difference between the heating control temperatures corresponding to the two currently switched user states is greater than the preset temperature difference; if so, determine that the temperature difference node is the target node that meets the preset heating control conditions.

[0029] As an optional implementation, in the first aspect of the present invention, generating heating control parameters for the heating equipment based on the node information corresponding to the target node includes:

[0030] When the node information corresponding to the target node only includes the static information, a first control parameter for the heating equipment is generated based on the target heating control temperature corresponding to the target state, the current scene temperature of the management and control scenario, the equipment operating parameters of the heating equipment, and the heat loss data of the management and control scenario, and is used as the heating control parameter.

[0031] When the node information corresponding to the target node includes the dynamic information, the temperature of the control scenario before the target user switches the user state is obtained, and the temperature difference between the two user states currently switched by the target user is obtained.

[0032] A second control parameter for the heating equipment is generated based on the temperature before switching, the temperature difference, the equipment operating parameters, and the heat loss data, and serves as the heating control parameter.

[0033] As an optional implementation, in the first aspect of the present invention, after adjusting the heating output of the heating equipment according to the heating control parameters, the method further includes:

[0034] Based on the node information of the target user at each action node, and combined with the historical data of the target user's daily routine in the control scenario, the action prediction information of the target user is determined. The action prediction information includes the predicted dwell time of the target user at the target node, the predicted mobile node of the target user, and the predicted user status of the target user.

[0035] Determine whether the action prediction information meets the heating control conditions. When it is determined that the action prediction information meets the heating control conditions, generate prediction control parameters for the predicted movement node based on the action prediction information. When the target user is detected to move to the predicted movement node, adjust the heating output of the heating equipment based on the prediction control parameters.

[0036] Wherein, the predicted moving node is a node where the probability of the target user moving from the target node to a certain node is higher than a preset first calculated probability; the predicted user state is a state where the probability of the target user switching from the current user state to a certain user state is higher than a preset second calculated probability.

[0037] As an optional implementation, in the first aspect of the present invention, determining whether the action prediction information meets the heating control conditions includes:

[0038] Determine the heating control temperature corresponding to the predicted mobile node, and denot it as the temperature to be controlled;

[0039] Calculate the temperature difference between the temperature to be controlled and the adjusted temperature of the controlled scenario, and record it as the predicted temperature difference. The adjusted temperature is the temperature of the controlled scenario after adjusting the heating output of the heating equipment according to the heating control parameters.

[0040] Based on the activity data, determine the user state corresponding to when the target user moves to the predicted movement node, and record it as the predicted user state;

[0041] When the predicted temperature difference is greater than the preset temperature difference, and or, the predicted user state belongs to the adjustment state, then it is determined that the action prediction information meets the heating control conditions.

[0042] And, the step of generating prediction control parameters for the predicted mobile node based on the action prediction information includes:

[0043] Based on the predicted temperature difference, the predicted user status, the dwell time, and the heat loss data of the control scenario, predictive control parameters for the heating equipment are generated.

[0044] A second aspect of this invention discloses an intelligent control device for heating equipment based on user motion sensing, the device comprising:

[0045] The data acquisition module is used to collect the action data of the target user in the control scenario when the presence of the target user in the control scenario corresponding to the heating equipment is detected.

[0046] The analysis module is used to analyze the action data to obtain multiple action nodes of the target user in the control scenario and node information of the target user at each action node;

[0047] The first judgment module is used to determine, based on all the node information, whether there is a target node among all the action nodes that meets the preset heating control conditions;

[0048] The generation module is used to generate heating control parameters for the heating equipment based on the node information corresponding to the target node when the first judgment module determines that there is a target node among all the action nodes that meets the heating control conditions.

[0049] The adjustment module is used to adjust the heating output of the heating equipment according to the heating control parameters.

[0050] As an optional implementation, in a second aspect of the present invention, the method by which the analysis module analyzes the action data to obtain multiple action nodes of the target user in the control scenario and node information of the target user at each action node specifically includes:

[0051] Based on the action data, multiple action nodes in which the target user stays in the control scenario for a longer than a preset duration are identified, and node data corresponding to each action node is extracted from the action data, using each action node as a benchmark.

[0052] Based on the user profile of the target user, a tracking model for the target user is generated, the tracking model including multiple tracking points corresponding to the user profile;

[0053] By combining the tracking model to analyze each piece of node data, the model tracking information of the target user at each action node is obtained, which serves as the node information of the target user at each action node;

[0054] The model tracking information includes the model movement trajectory, model posture, and model dwell time of the tracking model at each action node.

[0055] As an optional implementation, in a second aspect of the present invention, the method by which the analysis module analyzes each piece of node data in conjunction with the tracking model to obtain the model tracking information of the target user at each action node specifically includes:

[0056] For each action node, the starting position of the tracking model recorded at that action node is determined based on the node data corresponding to that action node;

[0057] Using the model's starting position as a base point, determine all model movement information of the tracking model at that action node; all model movement information includes the model movement trajectory, model dwell time, and model posture;

[0058] The model pose is matched with a preset action database to obtain the target action pose that matches the model pose in the action database and its corresponding pose information.

[0059] The model movement trajectory, model dwell time, target action posture and corresponding posture information are determined as the model tracking information of the action node;

[0060] The model movement trajectory corresponding to all the aforementioned action nodes is determined in the following way:

[0061] For each action node, the element coordinate movement information of the tracking element in the action node within a unit tracking time is determined, using a preset tracking element as the unit.

[0062] Based on the coordinate movement information of all the elements, a trajectory diagram corresponding to the tracked element is drawn to obtain the model movement trajectory as the action node;

[0063] The preset tracking elements include the overall tracking model or all individual tracking points.

[0064] As an optional implementation, in a second aspect of the present invention, the method by which the first determining module determines whether there is a target node among all the action nodes that meets the preset heating control conditions based on all the node information specifically includes:

[0065] Based on all the node information, the state information of the target user at each action node is determined. The state information includes static information and / or dynamic information. The static information includes the target user's current user state, which includes one of the following: sleep state, leisure and entertainment state, exercise state, bathing state, and work state. The dynamic information is the information recorded when the target user switches between two different user states. Each user state corresponds to a heating control temperature of a heating device.

[0066] When the status information includes the static information, it is determined whether there is a target state in the user status corresponding to each action node that matches the preset adjustment state that needs to be executed for heating control; if so, the action node corresponding to the target state is determined to be a target node that meets the preset heating control conditions.

[0067] The adjustment states include the sleep resting state, the exercise state, and the bathing state;

[0068] When the status information includes the dynamic information, determine whether there is a temperature difference node among all the action nodes where the temperature difference between the heating control temperatures corresponding to the two currently switched user states is greater than the preset temperature difference; if so, determine that the temperature difference node is the target node that meets the preset heating control conditions.

[0069] As an optional implementation, in a second aspect of the present invention, the method by which the generation module generates heating control parameters for the heating equipment based on the node information corresponding to the target node specifically includes:

[0070] When the node information corresponding to the target node only includes the static information, a first control parameter for the heating equipment is generated based on the target heating control temperature corresponding to the target state, the current scene temperature of the management and control scenario, the equipment operating parameters of the heating equipment, and the heat loss data of the management and control scenario, and is used as the heating control parameter.

[0071] When the node information corresponding to the target node includes the dynamic information, the temperature of the control scenario before the target user switches the user state is obtained, and the temperature difference between the two user states currently switched by the target user is obtained.

[0072] A second control parameter for the heating equipment is generated based on the temperature before switching, the temperature difference, the equipment operating parameters, and the heat loss data, and serves as the heating control parameter.

[0073] As an optional implementation, in a second aspect of the invention, the apparatus further includes:

[0074] The determination module is used to determine the action prediction information of the target user based on the node information of the target user at each action node and the historical activity data of the target user in the control scenario after the adjustment module adjusts the heating output of the heating equipment according to the heating control parameters. The action prediction information includes the predicted dwell time of the target user at the target node, the predicted movement node of the target user, and the predicted user status of the target user.

[0075] The second judgment module is used to determine whether the action prediction information meets the heating control conditions;

[0076] The generation module is further configured to generate predictive control parameters for the predicted moving node based on the action prediction information when the second judgment module determines that the action prediction information meets the heating control conditions.

[0077] The adjustment module is also used to adjust the heating output of the heating equipment according to the prediction control parameters when the target user is detected to have moved to the predicted movement node.

[0078] Wherein, the predicted moving node is a node where the probability of the target user moving from the target node to a certain node is higher than a preset first calculated probability; the predicted user state is a state where the probability of the target user switching from the current user state to a certain user state is higher than a preset second calculated probability.

[0079] As an optional implementation, in a second aspect of the present invention, the method by which the second determining module determines whether the action prediction information meets the heating control conditions specifically includes:

[0080] Determine the heating control temperature corresponding to the predicted mobile node, and denot it as the temperature to be controlled;

[0081] Calculate the temperature difference between the temperature to be controlled and the adjusted temperature of the controlled scenario, and record it as the predicted temperature difference. The adjusted temperature is the temperature of the controlled scenario after adjusting the heating output of the heating equipment according to the heating control parameters.

[0082] Based on the activity data, determine the user state corresponding to when the target user moves to the predicted movement node, and record it as the predicted user state;

[0083] When the predicted temperature difference is greater than the preset temperature difference, and or, the predicted user state belongs to the adjustment state, then it is determined that the action prediction information meets the heating control conditions.

[0084] Furthermore, the method by which the generation module generates prediction control parameters for the predicted moving node based on the action prediction information specifically includes:

[0085] Based on the predicted temperature difference, the predicted user status, the dwell time, and the heat loss data of the control scenario, predictive control parameters for the heating equipment are generated.

[0086] A third aspect of the present invention discloses another intelligent control device for heating equipment based on user motion sensing, the device comprising:

[0087] Memory containing executable program code;

[0088] A processor coupled to the memory;

[0089] The processor calls the executable program code stored in the memory to execute the intelligent control method for heating equipment based on user motion sensing disclosed in the first aspect of the present invention.

[0090] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute the intelligent control method for heating equipment based on user motion sensing disclosed in the first aspect of the present invention.

[0091] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0092] This invention provides an intelligent control method for heating equipment based on user action sensing. The method includes: when a target user is detected in the control scenario corresponding to the heating equipment, collecting action data of the target user in the control scenario; analyzing the action data to obtain multiple action nodes of the target user in the control scenario and node information of the target user at each action node; determining, based on all node information, whether there is a target node among all action nodes that meets preset heating control conditions; when it is determined that there is a target node among all action nodes that meets the heating control conditions, generating heating control parameters for the heating equipment based on the node information corresponding to the target node, and adjusting the heating output of the heating equipment according to the heating control parameters. As can be seen, the implementation of this invention establishes an intelligent heating control process based on user action sensing. When a target user is detected in the scene where the heating equipment is located, the system can automatically collect and analyze the target user's action data in the controlled scene, using that target user as the tracking target. Based on the obtained node information, the system compares and judges according to preset heating control conditions. If it is determined that the node information meets the heating control conditions, the corresponding heating control parameters are generated and executed. In other words, this invention achieves real-time intelligent control of the heating equipment through the collection and analysis of target user action data. This improves the intelligence of heating equipment control while enhancing the real-time performance of the control and the adaptability and accuracy of the current heating control with the target user's current state (action data). Attached Figure Description

[0093] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0094] Figure 1 This is a flowchart illustrating an intelligent control method for heating equipment based on user motion sensing, as disclosed in an embodiment of the present invention.

[0095] Figure 2 This is a flowchart illustrating another intelligent control method for heating equipment based on user motion sensing disclosed in an embodiment of the present invention.

[0096] Figure 3 This is a schematic diagram of the structure of an intelligent control device for heating equipment based on user motion sensing, as disclosed in an embodiment of the present invention.

[0097] Figure 4 This is a schematic diagram of another intelligent control device for heating equipment based on user motion sensing disclosed in an embodiment of the present invention;

[0098] Figure 5 This is a schematic diagram of the structure of another intelligent control device for heating equipment based on user motion sensing disclosed in an embodiment of the present invention. Detailed Implementation

[0099] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0100] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or end that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or ends.

[0101] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0102] This invention discloses an intelligent control method and device for heating equipment based on user motion sensing. It establishes an intelligent heating control process based on user motion sensing. When a target user is detected in the scene where the heating equipment is located, the system automatically collects and analyzes the target user's motion data within the controlled scene, using this target user as the tracking target. Based on the obtained node information, it compares and judges according to preset heating control conditions. If the node information is determined to meet the heating control conditions, the corresponding heating control parameters are generated and executed. In other words, this invention achieves real-time intelligent control of the heating equipment through the collection and analysis of target user motion data. This improves the intelligence of heating equipment control while enhancing the real-time performance of the control and the adaptability and accuracy of the current heating control to the target user's current state (motion data). Detailed explanations follow.

[0103] Example 1

[0104] Please see Figure 1 , Figure 1 This is a flowchart illustrating an intelligent control method for heating equipment based on user motion sensing, as disclosed in an embodiment of the present invention. Figure 1 The described intelligent control method for heating equipment based on user motion sensing can be applied to intelligent control devices for heating equipment based on user motion sensing, and the embodiments of this invention are not limited thereto. Figure 1 As shown, the intelligent control method for heating equipment based on user motion sensing can include the following operations:

[0105] 101. When a target user is detected in the control scenario corresponding to the heating equipment, collect the target user's action data in the control scenario.

[0106] In this embodiment of the invention, the heating equipment may be equipped with a first sensor for scanning / sensing users, used to scan and detect whether a target user exists in the controlled scenario where the heating equipment is located; optionally, the heating equipment may also be equipped with a second sensor, used to control the second sensor to track and record data of the target user after the first sensor determines that a target user has been detected.

[0107] In this embodiment of the invention, the first sensor and the second sensor can be the same sensor, that is, the functions of the two are integrated on the same sensor; or they can be two different sensors; the first sensor and the second sensor can be configured on the heating equipment, or they can be installed independently in the control scenario.

[0108] When at least one of the first and second sensors is installed independently in the control scenario, a corresponding data interaction link is established between the two sensors and the heating equipment, enabling the transmission of control commands and the interaction of data.

[0109] 102. Analyze the action data to obtain multiple action nodes of the target user in the control scenario and the node information of the target user at each action node.

[0110] In this embodiment of the invention, the motion data detected by sensors is relatively messy and needs to be classified, analyzed, and organized by the backend system. Simultaneously, this embodiment also requires extracting the necessary target data (multiple motion nodes and node information for each motion node) from the complex motion data; this facilitates further data analysis and organization based on each motion node.

[0111] 103. Based on all node information, determine whether there is a target node among all action nodes that meets the preset heating control conditions.

[0112] In this embodiment of the invention, heating control conditions are set to determine whether heating output adjustment of heating equipment is required; after determining the node information, the heating control conditions are used as the judgment standard to compare and judge whether subsequent heating output adjustment is required.

[0113] 104. When it is determined that there is a target node among all action nodes that meets the heating control conditions, heating control parameters for the heating equipment are generated according to the node information corresponding to the target node, and the heating output of the heating equipment is adjusted according to the heating control parameters.

[0114] It is evident that implementation Figure 1 The described intelligent control method for heating equipment based on user motion sensing establishes an intelligent heating control process. When a target user is detected in the scene where the heating equipment is located, the system can automatically collect and analyze the target user's motion data within the controlled scene, using that target user as the tracking target. Based on the obtained node information, the system compares and judges the data according to preset heating control conditions. If the node information is determined to meet the heating control conditions, the corresponding heating control parameters are generated and executed. In other words, this invention achieves real-time intelligent control of the heating equipment through the collection and analysis of target user motion data. This improves the intelligence of heating equipment control while enhancing the real-time performance of the control and the adaptability and accuracy of the current heating control to the target user's current state (motion data).

[0115] In an optional embodiment, step 102, which analyzes action data to obtain multiple action nodes of the target user in the control scenario and node information of the target user at each action node, specifically includes the following methods:

[0116] Based on the action data, identify multiple action nodes where the target user stays in the controlled scenario for a longer period than the preset duration, and extract the node data corresponding to each action node from the action data based on each action node.

[0117] Based on the user profile of the target user, a tracking model is generated for the target user. The tracking model includes multiple tracking points corresponding to the user profile.

[0118] By combining the tracking model to analyze each node data, the model tracking information of the target user at each action node is obtained, which serves as the node information of the target user at each action node;

[0119] The model tracking information includes the model's movement trajectory, pose, and dwell time at each action node.

[0120] In this optional embodiment, the method for determining multiple action nodes where the target user's dwell time in the controlled scenario exceeds a preset dwell time based on action data specifically includes:

[0121] The control scenario is divided into multiple sub-scenarios, and each sub-scenarios corresponds to a preset action node of a target user.

[0122] Collect the dwell time of the target user in each sub-scenario, which includes continuous dwell time and / or intermittent cumulative dwell time;

[0123] Identify multiple action nodes where the target user's stay time in the controlled scenario exceeds the preset stay time from the stay time corresponding to all sub-scenes.

[0124] In this optional embodiment, the continuous dwell time specifically refers to the continuous dwell time of the target user in the sub-scene within a unit detection time (e.g., within 5 minutes), and the target user does not leave the sub-scene during the timekeeping period; the cumulative dwell time includes the sum of the target user's cumulative continuous dwell time in the sub-scene and the departure time; for example, if the target user stays in sub-scene A for 10 minutes, goes to sub-scene B for 1 minute, and then returns to sub-scene A for 20 minutes, then the cumulative dwell time includes the target user's cumulative dwell time in sub-scene A of 30 minutes, and the time information of leaving for 1 minute in the 11th minute. Further, based on this cumulative dwell time illustrated in the example, sub-scene A can be determined as an action node, while the target user's dwell time in sub-scene B is less than the preset dwell time (e.g., 5 minutes) in 1 minute, indicating that sub-scene B cannot be determined as an action node.

[0125] In this optional embodiment, when classifying and organizing the action data, the action data can be extracted based on a preset dwell time. Specifically, the control scenario can be divided into four nodes: A, B, C, and D, with each node corresponding to a defined range. When organizing the action data, the analysis is based on the dwell time of the target user at each node, such as setting the preset dwell time to 2 minutes. In a real scenario, if the target user stays at node A for 10 minutes, then passes through node B with a recorded dwell time of 10 seconds, and then passes through node C and stays at node C for more than 30 minutes, then the identified action nodes are node A and node C. The selection of the action nodes is not limited in this optional embodiment.

[0126] In this optional embodiment, when the backend system generates a tracking model based on the user's profile, it can establish a three-dimensional modeling space based on the control scene; the tracking model of the target user is a portrait model in the three-dimensional modeling space; the portrait model can be a proportionally transformed model corresponding to the user's profile, or it can be a node model composed of a few simple tracking nodes.

[0127] Optionally, when the tracking model is a node model, only a few points of the user's outline can be selected as tracking points; for example, three tracking points can be selected to represent the location of the user's head; 2-4 tracking points can be selected to represent the user's limbs; and 4-8 tracking points can be used to represent the user's torso. This simplifies the setting of tracking points and reduces the amount of data that needs to be processed later. The number of tracking points can be increased or decreased according to the actual application, and this embodiment of the invention does not limit it.

[0128] As can be seen, in this optional embodiment, when analyzing action data, multiple action nodes are obtained based on a preset dwell time. This division of action nodes filters out some data that does not meet the conditions (dwell time does not exceed the preset dwell time), which helps to reduce the amount of data processing and the interference of irrelevant data. Furthermore, through further analysis of the tracking model duration and information of the target user, the node information of the target user at each action node is accurately obtained, which improves the accuracy and reliability of the determination of the node information.

[0129] In this optional embodiment, the method of combining the tracking model to analyze each node data to obtain the model tracking information of the target user at each action node specifically includes:

[0130] For each action node, the starting position of the tracking model recorded at that action node is determined based on the node data corresponding to that action node;

[0131] Using the model's starting position as the base point, determine all model movement information at that action node; all model movement information includes the model's movement trajectory, model dwell time, and model pose;

[0132] The model pose is matched with the preset action database to obtain the target action pose that matches the model pose in the action database and its corresponding pose information.

[0133] The model movement trajectory, model dwell time, target action posture and its corresponding posture information are determined as the model tracking information for this action node;

[0134] The model movement trajectory corresponding to all action nodes is determined in the following way:

[0135] For each action node, using a preset tracking element as the unit, determine the element coordinate movement information of the tracking element at the action node within a unit tracking time.

[0136] Based on the coordinate movement information of all elements, draw and track the trajectory diagram corresponding to the elements to obtain the model movement trajectory as the action node;

[0137] The preset tracking elements include the overall tracking model or all individual tracking points.

[0138] As explained above, the tracking model can be a holistic model corresponding to the profile of the target user, or it can be simplified and broken down into multiple tracking points.

[0139] As can be seen, in this optional embodiment, when actually combining the tracking model to analyze node data, the steps are refined to include recording the model's starting position, determining the model's movement trajectory, the model's dwell time, and the model's posture; then, the target's action posture and its posture information are matched through the action database, which improves the accuracy and richness of the determined model tracking information; in addition, when determining the model's movement trajectory, at least two types of trajectory diagrams can be drawn (overall tracking model, single tracking point), which enriches the means of drawing trajectory diagrams, and the intuitive trajectory diagram drawing improves the convenience of users viewing movement information.

[0140] In another optional embodiment, step 104, which determines whether there is a target node among all action nodes that meets the preset heating control conditions based on all node information, specifically includes:

[0141] Based on all node information, determine the target user's status information at each action node. The status information includes static information and / or dynamic information. Static information includes the target user's current user status, which may include one of the following: sleep / resting, leisure / entertainment, exercise, bathing, or working. Dynamic information is the information recorded when the target user switches between two different user statuses. Each user status corresponds to the heating control temperature of a heating device.

[0142] In this optional embodiment, it should be noted that the sleep resting state can refer to the user's current state of sleep and rest, which can be a nap or deep sleep; the leisure and entertainment state includes watching TV, playing games, watching movies, using a mobile phone, or even doing housework or cooking; the exercise state refers to the state corresponding to the user's current fitness exercise; the bathing state can refer to the user's state during bathing, the state corresponding to the user within 20 minutes after bathing, etc., and the embodiments of the present invention do not limit it.

[0143] In this optional embodiment, when the status information includes static information, it is determined whether there is a target status in the user status corresponding to each action node that matches the preset adjustment status that needs to be executed for heating control; if so, the action node corresponding to the target status is determined to be a target node that meets the preset heating control conditions.

[0144] Among them, the regulation state includes the sleep resting state, the exercise state, and the bathing state;

[0145] When the status information includes dynamic information, determine whether there is a temperature difference node among all action nodes whose temperature difference between the heating control temperatures corresponding to the two currently switched user states is greater than the preset temperature difference; if so, determine the temperature difference node as the target node that meets the preset heating control conditions.

[0146] In this optional embodiment, multiple adjustment states requiring heating regulation can be pre-set, such as a sleep / rest state. In this state, the heating equipment needs to adjust its heating output to improve the user's sleep experience. Similarly, in other states, when the target user is exercising, their body temperature generally rises, and the heating equipment can intelligently reduce its heating output to avoid the user's discomfort due to increased body temperature and unchanged heating output. After half an hour or an hour of exercise, the target user's body temperature begins to drop, and the previously reduced heating output needs to be intelligently increased. Both the bathing and exercise states involve fluctuations in the target user's body temperature, requiring intelligent adjustments from the heating equipment.

[0147] In this optional embodiment, when the status information includes dynamic information, the setting of the temperature difference between the two user states refers to the above description of the change in the target user's body temperature during exercise, and will not be repeated in this embodiment of the invention.

[0148] As can be seen, in this optional embodiment, both static and dynamic information judgment conditions are set, which improves the detail of the heating control conditions. This enables the appropriate judgment to be made when the heating control conditions are used as a benchmark, improving the accuracy of the judgment condition setting and also helping to improve the accuracy of the target node determined by the action node screening based on the judgment conditions.

[0149] In yet another optional embodiment, the method of generating heating control parameters for the heating equipment based on the node information corresponding to the target node specifically includes:

[0150] When the node information corresponding to the target node only includes static information, the first control parameter for the heating equipment is generated based on the target heating control temperature corresponding to the target state, the current scene temperature of the acquired control scene, the equipment operating parameters of the heating equipment, and the heat loss data of the control scene, and is used as the heating control parameter.

[0151] When the node information corresponding to the target node includes dynamic information, obtain the temperature of the control scenario before the target user switches user status, and the temperature difference between the two user statuses currently switched by the target user.

[0152] Based on the temperature, temperature difference, equipment operating parameters, and heat loss data before switching, a second set of control parameters for the heating equipment is generated and used as the heating control parameters.

[0153] As can be seen, in this optional embodiment, a scheme for generating heating control parameters for different node information is set, which can generate heating control parameters for both static and dynamic information, making the preliminary consideration scheme for generating heating control parameters richer and more accurate; this is conducive to improving the accuracy and reliability of the generated heating control parameters.

[0154] Example 2

[0155] Please see Figure 2 , Figure 2 This is a flowchart illustrating another intelligent control method for heating equipment based on user motion sensing disclosed in an embodiment of the present invention. Figure 2 The described intelligent control method for heating equipment based on user motion sensing can be applied to intelligent control devices for heating equipment based on user motion sensing, and the embodiments of this invention are not limited thereto. Figure 2 As shown, the intelligent control method for heating equipment based on user motion sensing can include the following operations:

[0156] 201. When a target user is detected in the control scenario corresponding to the heating equipment, collect the target user's action data in the control scenario.

[0157] 202. Analyze the action data to obtain multiple action nodes of the target user in the control scenario and the node information of the target user at each action node.

[0158] 203. Based on all node information, determine whether there is a target node among all action nodes that meets the preset heating control conditions.

[0159] 204. When it is determined that there is a target node among all action nodes that meets the heating control conditions, heating control parameters for the heating equipment are generated according to the node information corresponding to the target node, and the heating output of the heating equipment is adjusted according to the heating control parameters.

[0160] For further descriptions of steps 201-204 in this embodiment of the invention, please refer to the other specific descriptions of steps 101-104 in Embodiment 1. These descriptions will not be repeated in this embodiment of the invention.

[0161] 205. Based on the node information of the target user at each action node, and combined with the historical data of the target user's daily routine in the control scenario, determine the target user's action prediction information.

[0162] In this embodiment of the invention, the action prediction information includes the predicted dwell time of the target user at the target node, the predicted mobile node of the target user, and the predicted user status of the target user.

[0163] 206. Determine whether the motion prediction information meets the heating control conditions. When it is determined that the motion prediction information meets the heating control conditions, generate prediction control parameters for the predicted moving node based on the motion prediction information.

[0164] 207. When the target user is detected to have moved to the predicted movement node, the heating output of the heating equipment is adjusted according to the predicted control parameters.

[0165] In this embodiment of the invention, the predicted mobile node is a node whose probability of the target user moving from the target node to a certain node is higher than a preset first calculated probability; the predicted user state is a state in which the probability of the target user switching from the current user state to a certain user state is higher than a preset second calculated probability.

[0166] It is evident that implementation Figure 2 The described intelligent control method for heating equipment based on user motion sensing sets up a motion prediction mechanism for target users. This mechanism can intelligently combine user activity data to extract corresponding motion prediction information, thereby enabling the comparison and judgment of heating control conditions, and the generation and execution of predictive control parameters after the judgment is passed. The setting of this motion prediction mechanism is beneficial to improving the adjustment response speed of heating equipment parameters to a certain extent.

[0167] In an optional embodiment, the method for determining whether the action prediction information meets the heating control conditions in step 206 specifically includes:

[0168] Determine the heating control temperature corresponding to the predicted moving node, and denot it as the temperature to be controlled;

[0169] Calculate the temperature difference between the temperature to be controlled and the adjusted temperature of the control scenario, and record it as the predicted temperature difference. The adjusted temperature is the temperature of the control scenario after the heating output of the heating equipment is adjusted according to the heating control parameters.

[0170] Based on the activity schedule data, determine the user state corresponding to the target user when it moves to the predicted movement node, and record it as the predicted user state.

[0171] If the predicted temperature difference is greater than the preset temperature difference, and or if the predicted user state belongs to the adjustment state, then the action prediction information is determined to meet the heating control conditions.

[0172] Furthermore, the specific methods for generating predictive control parameters for the predicted mobile node based on the action prediction information in step 206 above include:

[0173] Based on the predicted temperature difference, predicted user status, dwell time, and heat loss data of the heating equipment operation parameters management scenario, predictive control parameters for the heating equipment are generated.

[0174] As can be seen, in this optional embodiment, when generating predictive control parameters, the requirements for comparing and judging heating control conditions mentioned above can be referenced to determine the temperature to be controlled, calculate the predicted temperature difference, and determine the predicted user temperature, thereby comparing it with the heating control conditions, improving the accuracy of comparing the target user's action prediction information with the heating control conditions, as well as the accuracy and reliability of the subsequent generation of predictive control parameters.

[0175] Example 3

[0176] Please see Figure 3 , Figure 3 This is a schematic diagram of a user-motion sensing-based intelligent control device for heating equipment, as disclosed in an embodiment of the present invention. The user-motion sensing-based intelligent control device for heating equipment can be a user-motion sensing-based intelligent control terminal, device, system, or server. The server can be a local server, a remote server, or a cloud server (also known as a cloud-based server). When the server is not a cloud server, it can communicate with the cloud server; this embodiment of the present invention does not impose any limitations. Figure 3 As shown, the intelligent control device for heating equipment based on user motion sensing may include a data acquisition module 301, an analysis module 302, a first judgment module 303, a generation module 304, and an adjustment module 305, wherein:

[0177] The data acquisition module 301 is used to collect the action data of the target user in the control scenario when the existence of the target user in the control scenario corresponding to the heating equipment is detected.

[0178] Analysis module 302 is used to analyze action data to obtain multiple action nodes of the target user in the control scenario and node information of the target user at each action node;

[0179] The first judgment module 303 is used to determine, based on all node information, whether there is a target node among all action nodes that meets the preset heating control conditions.

[0180] The generation module 304 is used to generate heating control parameters for the heating equipment based on the node information corresponding to the target node when the first judgment module 303 determines that there is a target node among all action nodes that meets the heating control conditions.

[0181] The adjustment module 305 is used to adjust the heating output of the heating equipment according to the heating control parameters.

[0182] It is evident that implementation Figure 3 The described intelligent control device for heating equipment based on user motion sensing establishes an intelligent heating control process based on user motion sensing. When a target user is detected in the scene where the heating equipment is located, the device can automatically collect and analyze the target user's motion data in the controlled scene, using that target user as the tracking target. Based on the obtained node information, the device compares and judges according to preset heating control conditions. If it is determined that the node information meets the heating control conditions, the corresponding heating control parameters are generated and executed. In other words, this invention achieves real-time intelligent control of heating equipment through the collection and analysis of target user motion data, improving the intelligence of heating equipment control while enhancing the real-time performance of control and the adaptability and accuracy of the current heating control with the target user's current state (motion data).

[0183] In an optional embodiment, the analysis module 302 analyzes the action data to obtain multiple action nodes of the target user in the control scenario and the node information of the target user at each action node. Specifically, this includes:

[0184] Based on the action data, identify multiple action nodes where the target user stays in the controlled scenario for a longer period than the preset duration, and extract the node data corresponding to each action node from the action data based on each action node.

[0185] Based on the user profile of the target user, a tracking model is generated for the target user. The tracking model includes multiple tracking points corresponding to the user profile.

[0186] By combining the tracking model to analyze each node data, the model tracking information of the target user at each action node is obtained, which serves as the node information of the target user at each action node;

[0187] The model tracking information includes the model's movement trajectory, pose, and dwell time at each action node.

[0188] As can be seen, in this optional embodiment, when analyzing action data, multiple action nodes are obtained based on a preset dwell time. This division of action nodes filters out some data that does not meet the conditions (dwell time does not exceed the preset dwell time), which helps to reduce the amount of data processing and the interference of irrelevant data. Furthermore, through further analysis of the tracking model duration and information of the target user, the node information of the target user at each action node is accurately obtained, which improves the accuracy and reliability of the determination of the node information.

[0189] In this optional embodiment, the analysis module 302 combines the tracking model to analyze each node data to obtain the model tracking information of the target user at each action node. Specifically, this includes:

[0190] For each action node, the starting position of the tracking model recorded at that action node is determined based on the node data corresponding to that action node;

[0191] Using the model's starting position as the base point, determine all model movement information at that action node; all model movement information includes the model's movement trajectory, model dwell time, and model pose;

[0192] The model pose is matched with the preset action database to obtain the target action pose that matches the model pose in the action database and its corresponding pose information.

[0193] The model movement trajectory, model dwell time, target action posture and its corresponding posture information are determined as the model tracking information for this action node;

[0194] The model movement trajectory corresponding to all action nodes is determined in the following way:

[0195] For each action node, using a preset tracking element as the unit, determine the element coordinate movement information of the tracking element at the action node within a unit tracking time.

[0196] Based on the coordinate movement information of all elements, draw and track the trajectory diagram corresponding to the elements to obtain the model movement trajectory as the action node;

[0197] The preset tracking elements include the overall tracking model or all individual tracking points.

[0198] As can be seen, in this optional embodiment, when actually combining the tracking model to analyze node data, the steps are refined to include recording the model's starting position, determining the model's movement trajectory, the model's dwell time, and the model's posture; then, the target's action posture and its posture information are matched through the action database, which improves the accuracy and richness of the determined model tracking information; in addition, when determining the model's movement trajectory, at least two types of trajectory diagrams can be drawn (overall tracking model, single tracking point), which enriches the means of drawing trajectory diagrams, and the intuitive trajectory diagram drawing improves the convenience of users viewing movement information.

[0199] In another optional embodiment, the first judgment module 303 determines whether there is a target node among all action nodes that meets the preset heating control conditions based on all node information. Specifically, this includes:

[0200] Based on all node information, determine the target user's status information at each action node. The status information includes static information and / or dynamic information. Static information includes the target user's current user status, which may include one of the following: sleep / resting, leisure / entertainment, exercise, bathing, or working. Dynamic information is the information recorded when the target user switches between two different user statuses. Each user status corresponds to the heating control temperature of a heating device.

[0201] When the status information includes static information, determine whether there is a target status in the user status corresponding to each action node that matches the preset adjustment status that needs to be executed for heating control; if so, determine that the action node corresponding to the target status is the target node that meets the preset heating control conditions.

[0202] Among them, the regulation state includes the sleep resting state, the exercise state, and the bathing state;

[0203] When the status information includes dynamic information, determine whether there is a temperature difference node among all action nodes whose temperature difference between the heating control temperatures corresponding to the two currently switched user states is greater than the preset temperature difference; if so, determine the temperature difference node as the target node that meets the preset heating control conditions.

[0204] As can be seen, in this optional embodiment, both static and dynamic information judgment conditions are set, which improves the detail of the heating control conditions. This enables the appropriate judgment to be made when the heating control conditions are used as a benchmark, improving the accuracy of the judgment condition setting and also helping to improve the accuracy of the target node determined by the action node screening based on the judgment conditions.

[0205] In another optional embodiment, the generation module 304 generates heating control parameters for the heating equipment based on the node information corresponding to the target node, specifically including the following methods:

[0206] When the node information corresponding to the target node only includes static information, the first control parameter for the heating equipment is generated based on the target heating control temperature corresponding to the target state, the current scene temperature of the acquired control scene, the equipment operating parameters of the heating equipment, and the heat loss data of the control scene, and is used as the heating control parameter.

[0207] When the node information corresponding to the target node includes dynamic information, obtain the temperature of the control scenario before the target user switches user status, and the temperature difference between the two user statuses currently switched by the target user.

[0208] Based on the temperature, temperature difference, equipment operating parameters, and heat loss data before switching, a second set of control parameters for the heating equipment is generated and used as the heating control parameters.

[0209] As can be seen, in this optional embodiment, a scheme for generating heating control parameters for different node information is set, which can generate heating control parameters for both static and dynamic information, making the preliminary consideration scheme for generating heating control parameters richer and more accurate; this is conducive to improving the accuracy and reliability of the generated heating control parameters.

[0210] In another alternative embodiment, such as Figure 4 As shown, the device also includes a determining module 306 and a second judging module 307, wherein:

[0211] The determination module 306 is used to determine the action prediction information of the target user based on the node information of the target user at each action node and the historical data of the target user's daily life in the control scenario after the adjustment module 305 adjusts the heating output of the heating equipment according to the heating control parameters. The action prediction information includes the predicted dwell time of the target user at the target node, the predicted movement node of the target user, and the predicted user status of the target user.

[0212] The second judgment module 307 is used to determine whether the action prediction information meets the heating control conditions.

[0213] The generation module 304 is also used to generate predictive control parameters for the predicted moving node based on the action prediction information when the second judgment module 307 determines that the action prediction information meets the heating control conditions.

[0214] The adjustment module 305 is also used to adjust the heating output of the heating equipment according to the prediction control parameters when the target user is detected to have moved to the predicted movement node.

[0215] Among them, the predicted mobile node is a node where the probability of the target user moving from the target node to a certain node is higher than the preset first calculated probability; the predicted user state is a state where the probability of the target user switching from the current user state to a certain user state is higher than the preset second calculated probability.

[0216] As can be seen, in this optional embodiment, a motion prediction mechanism for target users is set up, which can intelligently combine users' work and rest data to extract corresponding action prediction information, thereby realizing the comparison and judgment of heating control conditions, and the generation and execution of prediction control parameters after the judgment is passed; the setting of this motion prediction mechanism is conducive to improving the adjustment response speed of heating equipment parameters to a certain extent.

[0217] In yet another optional embodiment, the second judgment module 307 determines whether the action prediction information meets the heating control conditions in the following specific ways:

[0218] Determine the heating control temperature corresponding to the predicted moving node, and denot it as the temperature to be controlled;

[0219] Calculate the temperature difference between the temperature to be controlled and the adjusted temperature of the control scenario, and record it as the predicted temperature difference. The adjusted temperature is the temperature of the control scenario after the heating output of the heating equipment is adjusted according to the heating control parameters.

[0220] Based on the activity schedule data, determine the user state corresponding to the target user when it moves to the predicted movement node, and record it as the predicted user state.

[0221] If the predicted temperature difference is greater than the preset temperature difference, and or if the predicted user state belongs to the adjustment state, then the action prediction information is determined to meet the heating control conditions.

[0222] Furthermore, the specific methods by which the generation module 304 generates predictive control parameters for the predicted moving node based on the action prediction information include:

[0223] Based on the predicted temperature difference, predicted user status, dwell time, and heat loss data of the heating equipment operation parameters management scenario, predictive control parameters for the heating equipment are generated.

[0224] As can be seen, in this optional embodiment, when generating predictive control parameters, the requirements for comparing and judging heating control conditions mentioned above can be referenced to determine the temperature to be controlled, calculate the predicted temperature difference, and determine the predicted user temperature, thereby comparing it with the heating control conditions, improving the accuracy of comparing the target user's action prediction information with the heating control conditions, as well as the accuracy and reliability of the subsequent generation of predictive control parameters.

[0225] Example 4

[0226] Please see Figure 5 , Figure 5 This is a schematic diagram of another intelligent control device for heating equipment based on user motion sensing disclosed in an embodiment of the present invention. Figure 5 As shown, the intelligent control device for heating equipment based on user motion sensing may include:

[0227] Memory 401 storing executable program code;

[0228] Processor 402 coupled to memory 401;

[0229] The processor 402 calls the executable program code stored in the memory 401 to execute the steps in the intelligent control method for heating equipment based on user action sensing described in Embodiment 1 or Embodiment 2 of the present invention.

[0230] Example 5

[0231] This invention discloses a computer storage medium storing computer instructions. When these computer instructions are invoked, they are used to execute the steps in the intelligent control method for heating equipment based on user motion sensing described in Embodiment 1 or Embodiment 2 of this invention.

[0232] Example 6

[0233] This invention discloses a computer program product, which includes a non-transitory computer storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps in the intelligent control method for heating equipment based on user action sensing described in Embodiment 1 or Embodiment 2.

[0234] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0235] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0236] Finally, it should be noted that the intelligent control method and device for heating equipment based on user motion sensing disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent control of heating equipment based on user motion sensing, characterized in that, The method includes: When a target user is detected in the control scenario corresponding to the heating equipment, action data of the target user in the control scenario is collected. By analyzing the action data, multiple action nodes of the target user in the control scenario and node information of the target user at each action node are obtained; Based on all the node information, determine whether there is a target node among all the action nodes that meets the preset heating control conditions; When it is determined that there is a target node among all the action nodes that meets the heating control conditions, heating control parameters for the heating equipment are generated according to the node information corresponding to the target node, and the heating output of the heating equipment is adjusted according to the heating control parameters. The step of determining whether there is a target node among all the action nodes that meets the preset heating control conditions based on all the node information includes: Based on all the node information, the state information of the target user at each action node is determined. The state information includes static information and dynamic information. The static information includes the target user's current user state, which includes one of the following: sleep state, leisure and entertainment state, exercise state, bathing state, and work state. The dynamic information is the information recorded when the target user switches between two different user states. Each user state corresponds to a heating control temperature of a heating device. When the status information includes the static information, it is determined whether there is a target state in the user status corresponding to each action node that matches the preset adjustment state that needs to be executed for heating control; if so, the action node corresponding to the target state is determined to be a target node that meets the preset heating control conditions. The adjustment states include the sleep resting state, the exercise state, and the bathing state; When the status information includes the dynamic information, determine whether there is a temperature difference node among all the action nodes where the temperature difference between the heating control temperatures corresponding to the two currently switched user states is greater than the preset temperature difference; if so, determine that the temperature difference node is the target node that meets the preset heating control conditions.

2. The intelligent control method for heating equipment based on user motion sensing according to claim 1, characterized in that, The analysis of the action data yields multiple action nodes of the target user in the control scenario, as well as node information of the target user at each action node, including: Based on the action data, multiple action nodes in which the target user stays in the control scenario for a longer than a preset duration are identified, and node data corresponding to each action node is extracted from the action data based on each action node. Based on the user profile of the target user, a tracking model for the target user is generated, the tracking model including multiple tracking points corresponding to the user profile; By combining the tracking model to analyze each piece of node data, the model tracking information of the target user at each action node is obtained, which serves as the node information of the target user at each action node; The model tracking information includes the model movement trajectory, model posture, and model dwell time of the tracking model at each action node.

3. The intelligent control method for heating equipment based on user motion sensing according to claim 2, characterized in that, The step of combining the tracking model to analyze each piece of node data to obtain the model tracking information of the target user at each action node includes: For each action node, the starting position of the tracking model recorded at that action node is determined based on the node data corresponding to that action node; Using the model's starting position as a base point, determine all model movement information of the tracking model at that action node; all model movement information includes the model movement trajectory, model dwell time, and model posture; The model pose is matched with a preset action database to obtain the target action pose that matches the model pose in the action database and its corresponding pose information. The model movement trajectory, model dwell time, target action posture and corresponding posture information are determined as the model tracking information of the action node; The model movement trajectory corresponding to all the aforementioned action nodes is determined in the following way: For each action node, the element coordinate movement information of the tracking element in the action node within a unit tracking time is determined using a preset tracking element as the unit. Based on the coordinate movement information of all the elements, a trajectory diagram corresponding to the tracked element is drawn to obtain the model movement trajectory as the action node; The preset tracking elements include the overall tracking model or all individual tracking points.

4. The intelligent control method for heating equipment based on user motion sensing according to claim 1, characterized in that, The step of generating heating control parameters for the heating equipment based on the node information corresponding to the target node includes: When the node information corresponding to the target node includes the static information, a first control parameter for the heating equipment is generated based on the target heating control temperature corresponding to the target state, the current scene temperature of the management and control scenario, the equipment operating parameters of the heating equipment, and the heat loss data of the management and control scenario, and is used as the heating control parameter. When the node information corresponding to the target node includes the dynamic information, the temperature of the control scenario before the target user switches the user state is obtained, and the temperature difference between the two user states currently switched by the target user is obtained. A second control parameter is generated for the heating equipment based on the temperature before switching, the temperature difference, the equipment operating parameters, and the heat loss data, and serves as the heating control parameter.

5. The intelligent control method for heating equipment based on user motion sensing according to claim 1, characterized in that, After adjusting the heating output of the heating equipment according to the heating control parameters, the method further includes: Based on the node information of the target user at each action node, and combined with the historical data of the target user's daily routine in the control scenario, the action prediction information of the target user is determined. The action prediction information includes the predicted dwell time of the target user at the target node, the predicted mobile node of the target user, and the predicted user status of the target user. Determine whether the action prediction information meets the heating control conditions. When it is determined that the action prediction information meets the heating control conditions, generate prediction control parameters for the predicted movement node based on the action prediction information. When the target user is detected to move to the predicted movement node, adjust the heating output of the heating equipment based on the prediction control parameters. Wherein, the predicted moving node is a node where the probability of the target user moving from the target node to a certain node is higher than a preset first calculated probability; the predicted user state is a state where the probability of the target user switching from the current user state to a certain user state is higher than a preset second calculated probability.

6. The intelligent control method for heating equipment based on user motion sensing according to claim 5, characterized in that, The step of determining whether the action prediction information meets the heating control conditions includes: Determine the heating control temperature corresponding to the predicted mobile node, and denot it as the temperature to be controlled; Calculate the temperature difference between the temperature to be controlled and the adjusted temperature of the controlled scenario, and record it as the predicted temperature difference. The adjusted temperature is the temperature of the controlled scenario after adjusting the heating output of the heating equipment according to the heating control parameters. Based on the activity data, determine the user state corresponding to when the target user moves to the predicted movement node, and record it as the predicted user state; When the predicted temperature difference is greater than the preset temperature difference, and or, the predicted user state belongs to the adjustment state, then it is determined that the action prediction information meets the heating control conditions. And, the step of generating prediction control parameters for the predicted mobile node based on the action prediction information includes: Based on the predicted temperature difference, the predicted user status, the dwell time, and the heat loss data of the control scenario, predictive control parameters for the heating equipment are generated.

7. A smart control device for heating equipment based on user motion sensing, characterized in that, The device is used to execute the intelligent control method for heating equipment based on user motion sensing as described in any one of claims 1-6, and the device comprises: The data acquisition module is used to collect the action data of the target user in the control scenario when the presence of the target user in the control scenario corresponding to the heating equipment is detected. The analysis module is used to analyze the action data to obtain multiple action nodes of the target user in the control scenario and node information of the target user at each action node; The first judgment module is used to determine, based on all the node information, whether there is a target node among all the action nodes that meets the preset heating control conditions; The generation module is used to generate heating control parameters for the heating equipment based on the node information corresponding to the target node when the first judgment module determines that there is a target node among all the action nodes that meets the heating control conditions. The adjustment module is used to adjust the heating output of the heating equipment according to the heating control parameters.

8. A smart control device for heating equipment based on user motion sensing, characterized in that, The device includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent control method for heating equipment based on user action sensing as described in any one of claims 1-6.

9. A computer storage medium, characterized in that, The computer storage medium stores computer instructions, which, when invoked, are used to execute the intelligent control method for heating equipment based on user motion sensing as described in any one of claims 1-6.

Images