Intelligent furniture linkage control method and system based on space-time perception technology

By constructing and analyzing the scene space of smart furniture and combining user feedback data, the problem of insufficient handling of the interactive relationship between furniture status and user behavior of smart furniture systems is solved, and accurate identification and personalized control of user intentions is achieved, and users are enhanced Experience and satisfaction.

CN119087828AInactive Publication Date: 2024-12-06ZHEJIANG SUNON FURNITURE MFG

Patent Information

Application Number
CN202411589487.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-08
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing smart furniture system's handling of furniture status, user behavior and interactive relationships between time and space environments is not accurate enough, resulting in the linkage control being not intelligent enough, and the inability to effectively use user feedback data for optimization, resulting in low user experience and satisfaction.

Method used

By constructing the first scene space and the second scene space, combining user feedback data for spatial ghosting and slicing, obtaining intention calibration factors, building a scene response model, integrating furniture status, linkage data, user behavior and intention calibration factors, realizing the Accurate identification and personalized control of user intentions.

Benefits of technology

It realizes accurate identification of users' true intentions and personalized furniture linkage control, improves user experience and satisfaction, enhances the intelligent and dynamic response capabilities of the system, and meets the multiple needs of users.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119087828A_ABST
    Figure CN119087828A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent furniture linkage control method and system based on a space-time perception technology, and belongs to the field of information processing, and the method comprises the following steps: S1, constructing a first scene space based on furniture state data, furniture linkage data and user behavior data; s2, the first scene space responds to user feedback data to construct a second scene space; s3, performing space ghosting operation according to the first scene space and the second scene space to obtain a space gap; performing slicing processing on the spatial gap to obtain an intention calibration factor; s4, constructing a scene response model according to the furniture state information, the furniture linkage data, the intention calibration factor and the user behavior data; and S5, the scene response model responds to the user spatio-temporal data to obtain a furniture linkage control strategy. According to the scheme, accurate, dynamic and intelligent control over the intelligent furniture is achieved by deeply analyzing the user behavior intention, the furniture state and the change of the space-time environment, and the use experience and the satisfaction degree of the user are greatly improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a smart furniture linkage control method and system based on time-space perception technology. Background Art

[0002] With the rapid development of smart home technology, furniture is no longer just a traditional item for use, but has gradually incorporated more intelligent functions. Users' demand for intelligent furniture is also growing, and they expect furniture to automatically adjust and control according to their own behavior, habits, and changes in the space-time environment. However, most existing smart furniture systems are controlled based on preset scene modes or simple user instructions, lacking in-depth understanding of users' real behavioral intentions and dynamic response capabilities.

[0003] In existing smart home control methods, the complex interactive relationship between furniture status, user behavior and spatiotemporal environment is often ignored, resulting in the linkage control of furniture being not precise and intelligent enough. In addition, existing control methods also fail to effectively use user feedback data to optimize and calibrate control strategies, resulting in a deviation between the linkage effect of furniture and user expectations.

[0004] The above information disclosed in the Background section is only for enhancement of understanding of the background of the present application and therefore it may contain information that does not constitute the prior art that is already known to a person of ordinary skill in the art. Summary of the invention

[0005] In order to solve the problem of low degree of intelligent control of furniture in the prior art, the present invention proposes a smart furniture linkage control method and system based on time-space perception technology; by collecting furniture status data, furniture linkage data and user behavior data, a first scene space reflecting the real user intention is constructed, and this space is adjusted in combination with user feedback data to form a second scene space reflecting the predicted user intention, and the two scene spaces are analyzed to obtain the intention calibration factor, and then according to the furniture status data, furniture linkage data, user behavior data and the intention calibration factor and the construction of the scene response model, the user's real intention can be more accurately identified and a personalized furniture linkage control solution can be obtained, and the precise, dynamic and intelligent control of smart furniture is achieved by in-depth analysis of user behavior intentions, furniture status and changes in the time-space environment, which greatly improves the user experience and satisfaction.

[0006] In a first aspect, a technical solution provided in an embodiment of the present invention is a smart furniture linkage control method based on time-space perception technology, comprising the following steps: S1. Construct the first scene space based on furniture status data, furniture linkage data and user behavior data; S2, the first scene space constructs a second scene space in response to user feedback data; S3, performing a spatial ghosting operation according to the first scene space and the second scene space to obtain a spatial gap; and obtaining an intention calibration factor by slicing the spatial gap; S4, building a scenario response model based on furniture status information, furniture linkage data, intention calibration factor, and user behavior data; S5. The scene response model obtains a furniture linkage control strategy in response to the user's spatiotemporal data.

[0007] In this solution, by constructing the first scene space and responding to user feedback to construct the second scene space, the user's behavior and needs are initially captured and understood, and dynamic adjustments can be made based on the user's specific behavior and feedback. Not only the furniture status and linkage data are considered, but also the user's behavior data is fully integrated. Secondly, the intention calibration factor is obtained through spatial ghosting operation and slicing processing, and the system further improves the recognition accuracy of user intentions. This enables the system to more accurately grasp the user's real needs, thereby providing more personalized services; on this basis, a scene response model is constructed, which integrates multiple information such as furniture status, linkage data, user behavior, and intention calibration factors, and realizes accurate recognition and rapid response to user needs. This makes the furniture linkage control not only more in line with the user's actual needs and expectations, but also significantly improves the system's practicality and user satisfaction; further, the model can respond to the user's spatiotemporal data, that is, it can be dynamically adjusted according to the user's location, time and other information. This feature enables the furniture linkage control to not only take into account the user's behavior, but also fully integrate the user's environment and time factors, achieving more comprehensive and intelligent control, and bringing users a more comfortable, convenient and intelligent home life experience.

[0008] Preferably, the step of constructing the first scene space based on furniture status data, furniture linkage data and user behavior data comprises the following steps: S11, extracting historical behavior features of real behavior intentions, and constructing historical behavior sections of historical behavior features on time slices; S12, characterize the historical behavior section by furniture type, furniture spatiotemporal characteristics, and furniture behavior characteristics to obtain the historical scene behavior section; S13. Construct a first scene space corresponding to the real behavior intention based on the historical scene behavior section on the time slice.

[0009] In this solution, by extracting the historical behavior features of the real behavior intention and constructing the historical behavior sections of the historical behavior features on the time slice, the historical behavior patterns of users can be analyzed more carefully, not only considering the overall trend of user behavior, but also going deep into the specific time nodes, so that the understanding of user behavior is more comprehensive and accurate; further, the user behavior is closely linked to the specific attributes and status of the furniture, and the historical behavior sections are characterized by furniture type, furniture spatiotemporal characteristics, and furniture behavior characteristics to obtain historical scene behavior sections, so that the system can more accurately understand the interactive relationship between users and furniture in different scenarios; the first scene space corresponding to the real behavior intention is constructed according to the historical scene behavior section on the time slice, realizing the mapping from abstract user behavior features to specific scene space, which can better adapt to the changing needs of different users, different environments and different times, and provide more flexible and intelligent furniture linkage control services.

[0010] Preferably, furniture status data is constructed according to furniture type and furniture behavior characteristics; and furniture linkage data is constructed according to furniture type and furniture spatiotemporal characteristics.

[0011] Preferably, the first scene space constructs a second scene space in response to user feedback data, comprising the following steps: S21, obtaining the user's predicted behavior intention according to the behavior recognition model, and constructing a behavior deviation vector between the predicted behavior intention and the actual behavior intention according to the user feedback data; S22. Reconstruct the first scene space in sections based on the behavior deviation vector to obtain a second scene space.

[0012] In this solution, the user's predicted behavioral intention is obtained through the behavior recognition model, and compared with the actual feedback data of the user, to construct a behavior deviation vector between the predicted behavioral intention and the real behavioral intention, which can capture the deviation between the user's intention and the prediction of the behavior recognition model in real time, providing a basis for immediate adjustment of the system. Furthermore, based on the behavior deviation vector, the first scene space is reconstructed in section to generate the second scene space, realizing dynamic optimization of the scene space and ensuring that the system can more accurately reflect the user's real needs and intentions. As the user's behavior continues to change, the system can continuously adjust the scene space to keep pace with the user's needs; among them, the basic principle of the behavior recognition model is based on computer vision technology, which realizes the recognition and classification of different behaviors by extracting and analyzing the features in images and videos. It is a conventional model in the field of machine vision and will not be repeated here.

[0013] Preferably, the step of reconstructing the first scene space based on the behavior deviation vector to obtain the second scene space comprises the following steps: S221, determining the vector depth of the behavior deviation vector according to the overlap degree of the correlation indicator factors of the predicted behavior intention and the actual behavior intention; S222, determining the vector content of the behavior deviation vector according to the deviation amount of the correlation indicator factor between the predicted behavior intention and the actual behavior intention; S223: Reconstruct the first scene space in sections based on the vector depth and the vector content to obtain a second scene space.

[0014] In this scheme, the vector depth of the behavior deviation vector is determined by considering the overlap of the associated indicator factors (such as furniture type overlap index, time synchronization index, and behavior feature similarity index) of the predicted behavior intention and the real behavior intention. This process enables the system to quantify the degree of behavior deviation more accurately. The introduction of vector depth provides a more accurate adjustment basis for subsequent spatial reconstruction; the vector content of the behavior deviation vector is determined according to the deviation of the associated indicator factors, which not only pays attention to the existence of the deviation, but also deeply analyzes the specific content and direction of the deviation, so that the system can more comprehensively understand the inconsistency between user behavior and predicted behavior, and provides rich information support for subsequent correction work. The vector depth represents the degree or magnitude of the deviation between the predicted behavior intention and the real behavior intention, which can be calculated based on the overlap of the associated indicator factors. The higher the overlap, the smaller the vector depth may be, indicating a lighter degree of deviation; conversely, the lower the overlap, the larger the vector depth may be, indicating a heavier degree of deviation; the vector content contains the specific content and direction information of the deviation. Each dimension corresponds to the deviation of an associated indicator factor. For example, the deviations calculated on the furniture type coincidence index, the time synchronization index, and the behavior feature similarity index can constitute the dimensions of the vector content.

[0015] Preferably, the step of performing cross-sectional reconstruction on the first scene space based on the vector depth and the vector content to obtain the second scene space comprises the following steps: S2231, extracting the historical scene behavior section of the first scene space, and correcting the furniture linkage data in the historical scene behavior section according to the vector depth; S2232, performing secondary correction on the furniture state data of the corrected historical scene behavior section according to the vector content to obtain the target scene behavior section; S2233. Construct a second scene space corresponding to the predicted behavior intention based on the target scene behavior section on the time slice.

[0016] In this solution, by extracting the historical scene behavior section of the first scene space and making a correction to the furniture linkage data based on the vector depth, the furniture linkage relationship in the scene can be accurately adjusted to make it more consistent with the user's real behavioral intentions; on the basis of the first correction, the furniture status data of the corrected historical scene behavior section is corrected for the second time according to the vector content, which further refines the correction work and ensures the comprehensive optimization of the furniture status data, making the second scene space closer to the user's actual needs and expectations. The system can adjust the scene space in real time as the user's behavioral intentions change, ensuring the synchronization and consistency between the scene space and the user's behavior. This application improves the efficiency and accuracy of scene space reconstruction through a phased correction strategy (primary correction and secondary correction) and a construction method based on time slicing. The second scene space finally constructed is more consistent with the user's real behavioral intentions and needs, and improves the user's experience and satisfaction in the smart home environment.

[0017] Preferably, performing a spatial ghosting operation on the first scene space and the second scene space to obtain a spatial gap; and obtaining an intended calibration factor by slicing the spatial gap comprises the following steps: S31, performing a spatiotemporal alignment operation on the first scene space and the second scene space according to the spatiotemporal features, extracting the aligned scene behavior sections of the first scene space and the second scene space in sequence according to the slice scale of the time slice, and performing feature deduplication processing to determine the spatial gap; S32, determining a slice scale, and sequentially slicing the space gaps according to the slice scale to obtain an intended calibration factor; The slice scale includes time scale, space scale, furniture type scale and behavior characteristic scale; The intention calibration factor includes a furniture state calibration factor determined according to a time scale and a behavior characteristic scale, and a furniture type calibration factor determined according to a space scale and a furniture type scale.

[0018] In this solution, the first scene space and the second scene space are aligned in time and space through the time and space features, and the scene behavior section is extracted according to the slice scale of the time slice, and then the feature deduplication processing is performed, so that the difference between the two scene spaces, that is, the spatial gap, can be accurately identified, providing accurate basic data for the subsequent intention calibration; the slice scale includes the time scale, the space scale, the furniture type scale and the behavior feature scale. The slice processing of these four dimensions makes the analysis of the spatial gap more comprehensive and in-depth; through slices of different scales, the subtle differences and potential laws hidden in the spatial gap can be revealed; by slicing the spatial gap, this technical means can extract the intention calibration factor, and the extraction of the intention calibration factor helps the system to understand the user's real intention and needs more accurately, including the furniture state calibration factor and the furniture type calibration factor; these calibration factors are the key bridge connecting the first scene space and the second scene space, providing strong support for the subsequent intention calibration and space optimization; by comparing the furniture state and behavior characteristics in the first scene space and the second scene space, the system can identify the user's potential needs and preferences, thereby providing more personalized services and experiences.

[0019] Preferably, the step of constructing a scenario response model according to furniture status information, furniture linkage data, intention calibration factor, and user behavior data comprises the following steps: S41, sequentially obtaining furniture state information, furniture linkage data, user behavior data, and intention calibration factors corresponding to the scene behavior section according to the slice scale of the time slice; S42, using furniture status information, furniture linkage data, intention calibration factor, and user behavior data as feature vectors of a support vector machine model to train it and construct a scene response model.

[0020] In this scheme, the furniture state information, furniture linkage data, user behavior data and intention calibration factors corresponding to the scene behavior section are systematically obtained through the slice scale of time slices, ensuring that the key information required to build the scene response model is fully and accurately integrated; the integrated furniture state information, furniture linkage data, intention calibration factors and user behavior data are trained as feature vectors using the support vector machine model, which can efficiently mine the potential associations and rules between these data, thereby building an accurate scene response model. The constructed scene response model can intelligently adjust and optimize the furniture state, linkage relationship, etc. based on the actual behavior and needs of the user, significantly improving the accuracy and intelligence level of the scene response, so that the smart home system can better meet the personalized needs of the user. Through the introduction of the intention calibration factor, the scene response model can perceive the changes in the user's intention in real time and dynamically adjust the scene accordingly. This enhances the system's adaptive ability and ensures that the smart home environment always keeps pace with the user's behavior and needs; users can feel the system's accurate understanding and response to their behavior, thereby enhancing the interactivity and satisfaction with the system.

[0021] Preferably, the scene response model obtains the furniture linkage control strategy in response to the user's spatiotemporal data, comprising the following steps: Detect whether the user behavior pattern in the user's spatiotemporal data matches the linkage control trigger factor. If so, extract the temporal feature information and spatial feature information in the user's spatiotemporal data and combine them with the scene response model to obtain real-time furniture status information and real-time furniture linkage data; use the furniture status information and real-time furniture linkage data as the furniture linkage control strategy; otherwise, do nothing; Among them, the correlation under the corresponding user behavior pattern is constructed according to the linkage duration and usage frequency of each piece of furniture, and the state values ​​corresponding to the two pieces of furniture with the largest correlation are selected as the joint control trigger factor for starting the model.

[0022] In this scheme, by detecting whether the user behavior pattern in the user's spatiotemporal data matches the linkage control trigger factor, as the key premise for triggering the furniture linkage control strategy, the current behavior intention and needs of the user can be intelligently identified, ensuring that the system can accurately respond to the user's operation. When the user behavior pattern matches the linkage control trigger factor, the system can extract the temporal feature information and spatial feature information in the user's spatiotemporal data in real time, and obtain the real-time furniture status information and furniture linkage data in combination with the scene response model, so that the system can quickly grasp the furniture status and user behavior in the current scene and make accurate furniture linkage control strategies; further, by constructing the correlation under the corresponding user behavior pattern according to the linkage duration and usage frequency of each piece of furniture, and selecting the state values ​​corresponding to the two pieces of furniture with the largest correlation as the linkage control trigger factor for the model to start, the trigger mechanism of furniture linkage is optimized, so that the system can more sensitively perceive the changes in user behavior and trigger linkage control at the right time, thereby improving the response speed and accuracy of the system. In summary, this technical means realizes the intelligent and precise control of the smart home system through strategies such as intelligent identification of user behavior patterns, real-time acquisition of furniture status information and linkage data, and accurate formulation of furniture linkage control strategies. In this process, the furniture linkage trigger mechanism was optimized, the stability and reliability of the system were enhanced, and users were provided with a smoother and more natural smart home experience.

[0023] In a second aspect, a technical solution provided in an embodiment of the present invention is a smart furniture linkage control system, comprising: The first construction module: constructs the first scene space based on furniture status data, furniture linkage data and user behavior data; A second construction module: the first scene space constructs a second scene space in response to user feedback data; Analysis module: performing a spatial ghosting operation on the first scene space and the second scene space to obtain a spatial gap; and obtaining an intention calibration factor by slicing the spatial gap; Generation module: builds a scenario response model based on furniture status information, furniture linkage data, intention calibration factors, and user behavior data; Execution module: The scene response model obtains the furniture linkage control strategy in response to the user's spatiotemporal data.

[0024] In a third aspect, a technical solution provided in an embodiment of the present invention is an electronic device, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the steps of the smart furniture linkage control method based on time and space perception technology are implemented.

[0025] In a fourth aspect, a technical solution provided in an embodiment of the present invention is a storage medium, in which computer executable instructions are stored. When the computer executable instructions are loaded and executed by a processor, the steps of the smart furniture linkage control method based on time-space perception technology are implemented.

[0026] The present invention has at least the following beneficial effects: (1) This application realizes intelligent response and control of smart home scenes by constructing a scene response model and combining user spatiotemporal data, furniture status information, furniture linkage data and intention calibration factors. It can accurately identify user behavior patterns and needs, adjust furniture status and linkage relationships in real time, and provide a personalized and smooth smart home experience. (2) This application detects the matching of user behavior patterns and linkage control trigger factors in user spatiotemporal data, and uses a support vector machine model to train feature vectors, thereby achieving accurate recognition and matching of user intentions, enabling the system to quickly understand the user's operating intentions and trigger the corresponding furniture linkage control strategy at the appropriate time, thereby improving the system's response speed and accuracy; (3) The technical solution optimizes the layout of the scene space and the furniture linkage mechanism through spatiotemporal alignment operations, slicing processing, and extraction of intent calibration factors. It can make fine adjustments to the type, status, and position of furniture according to the actual needs and preferences of users, while optimizing the linkage relationship between furniture, making the scene space more in line with user expectations and needs, thereby improving the overall performance and user experience of the smart home system.

[0027] The above invention content is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Other features, objects and advantages of the present invention will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for the purpose of illustrating preferred embodiments and are not to be considered as limiting the present invention. Also, the same reference symbols are used throughout the drawings to represent the same parts.

[0029] Figure 1 This is a flow chart of the intelligent furniture linkage control method based on time-space perception technology of the present invention.

[0030] Figure 2 A flow chart is generated for the first scene space of the present invention.

[0031] Figure 3A flow chart is generated for the second scene space of the present invention.

[0032] Figure 4 It is a schematic diagram of the structure of the intelligent furniture linkage control system of the present invention. DETAILED DESCRIPTION

[0033] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific implementation method described herein is only an optimal embodiment of the present invention, which is only used to explain the present invention and does not limit the scope of protection of the present invention. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0034] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the operations (or steps) as sequential processes, many of the operations (or steps) therein can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the drawings; the process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0035] Embodiment 1, like Figure 1 As shown, the intelligent furniture linkage control method based on time-space perception technology includes the following steps: S1. Construct the first scene space based on furniture status data, furniture linkage data and user behavior data.

[0036] Specifically, Figure 2 As shown, S1 includes the following steps: S11, extracting historical behavior features of real behavior intentions, and constructing historical behavior sections of historical behavior features on time slices; S12, characterize the historical behavior section by furniture type, furniture spatiotemporal characteristics, and furniture behavior characteristics to obtain the historical scene behavior section; S13. Construct a first scene space corresponding to the real behavior intention based on the historical scene behavior section on the time slice.

[0037] Furthermore, furniture status data is constructed according to furniture type and furniture behavior characteristics; furniture linkage data is constructed according to furniture type and furniture spatiotemporal characteristics.

[0038] In this embodiment, by extracting the historical behavior features of the real behavior intention and constructing the historical behavior sections of the historical behavior features on the time slice, the historical behavior patterns of the users can be analyzed in more detail, not only considering the overall trend of the user behavior, but also going deep into the specific time nodes, so that the understanding of the user behavior is more comprehensive and accurate; further, the user behavior is closely linked to the specific attributes and status of the furniture, and the historical behavior sections are characterized by the furniture type, furniture spatiotemporal characteristics, and furniture behavior characteristics to obtain the historical scene behavior sections, so that the system can more accurately understand the interactive relationship between the user and the furniture in different scenarios; the first scene space corresponding to the real behavior intention is constructed according to the historical scene behavior sections on the time slice, realizing the mapping from abstract user behavior features to specific scene spaces, which can better adapt to the changing needs of different users, different environments and different times, and provide more flexible and intelligent furniture linkage control services.

[0039] As an example description of this embodiment, first, collect the user's behavior data in the past period of time, such as the time of turning on and off the lights, the frequency of using the TV, the movement path between the living room and the bedroom, etc. These data are subdivided into multiple time slices, each of which represents the user's behavior characteristics in a short period of time. As time goes by, the system continuously updates and accumulates these behavior characteristics, forming a series of continuous historical behavior sections. These sections are like a "time film" about user behavior, which can clearly show the user's activity patterns and habits in each time period.

[0040] Then, on each historical behavior section, the system will depict specific scenes based on the type of furniture (such as electric sofas, electric tables and chairs, TVs, smart sweeping robots, electric curtains, etc.), spatiotemporal characteristics (such as the location of furniture, movement trajectory, etc.), and behavioral characteristics (such as the use status of furniture, linkage relationships, etc.). For example, when a user sits on an electric sofa to watch TV at night, the system will record that the TV is in the playing state and the user on the electric sofa remains still. At the same time, it will also take into account the possible fine-tuning of the sofa due to the user's sitting posture (such as changes in the tilt angle). In addition, the system will also analyze the linkage relationship between furniture. For example, when the user turns on the TV, the electric curtains may automatically close to reduce the interference of external light; as the user's behavior changes and time passes, the system continuously updates and enriches these historical scene behavior sections. These sections are like vivid pictures, presenting the user's real life scenes in the system.

[0041] Finally, after accumulating enough historical scene behavior sections, the system will construct the first scene space corresponding to the real behavior intention based on these sections. This space is a virtual but highly realistic user life scene, which contains information such as the user's activity mode in different time periods, the use status of furniture, and linkage relationships. When the user's behavior intention changes, the system can quickly adjust the furniture status and linkage relationship in the first scene space to ensure that the scene is consistent with the user's actual needs. For example, when the user moves from the living room to the bedroom, the system will automatically adjust the furniture status in the bedroom (such as turning on the bedside lamp, closing the curtains, etc.) and update the first scene space to reflect this change.

[0042] S2. The first scene space constructs a second scene space in response to user feedback data.

[0043] Specifically, Figure 3 As shown, S2 includes the following steps: S21, obtaining the user's predicted behavior intention according to the behavior recognition model, and constructing a behavior deviation vector between the predicted behavior intention and the actual behavior intention according to the user feedback data; S22. Reconstruct the first scene space in sections based on the behavior deviation vector to obtain a second scene space.

[0044] In this solution, the user's predicted behavioral intention is obtained through the behavior recognition model, and compared with the actual feedback data of the user, to construct a behavior deviation vector between the predicted behavioral intention and the real behavioral intention, which can capture the deviation between the user's intention and the prediction of the behavior recognition model in real time, providing a basis for immediate adjustment of the system. Furthermore, based on the behavior deviation vector, the first scene space is reconstructed in section to generate the second scene space, realizing dynamic optimization of the scene space and ensuring that the system can more accurately reflect the user's real needs and intentions. As the user's behavior continues to change, the system can continuously adjust the scene space to keep pace with the user's needs; among them, the basic principle of the behavior recognition model is based on computer vision technology, which realizes the recognition and classification of different behaviors by extracting and analyzing the features in images and videos. It is a conventional model in the field of machine vision and will not be repeated here.

[0045] Furthermore, the cross-sectional reconstruction of the first scene space based on the behavior deviation vector to obtain the second scene space comprises the following steps: S221, determining the vector depth of the behavior deviation vector according to the overlap degree of the correlation indicator factors of the predicted behavior intention and the actual behavior intention; S222, determining the vector content of the behavior deviation vector according to the deviation amount of the correlation indicator factor between the predicted behavior intention and the actual behavior intention; S223: Reconstruct the first scene space in sections based on the vector depth and the vector content to obtain a second scene space.

[0046] In this embodiment, the vector depth of the behavior deviation vector is determined by considering the overlap of the associated index factors (for example, furniture type overlap index, time synchronization index, and behavior feature similarity index) of the predicted behavior intention and the real behavior intention. This process enables the system to more accurately quantify the degree of behavior deviation. The introduction of vector depth provides a more accurate adjustment basis for subsequent spatial reconstruction; the vector content of the behavior deviation vector is determined according to the deviation of the associated index factor, which not only pays attention to the existence of the deviation, but also deeply analyzes the specific content and direction of the deviation, so that the system can more comprehensively understand the inconsistency between the user behavior and the predicted behavior, and provides rich information support for subsequent correction work. The vector depth represents the degree or magnitude of the deviation between the predicted behavior intention and the real behavior intention, which can be calculated based on the overlap of the associated index factors. The higher the overlap, the smaller the vector depth may be, indicating a lighter degree of deviation; conversely, the lower the overlap, the larger the vector depth may be, indicating a heavier degree of deviation; the vector content contains the specific content and direction information of the deviation. Each dimension corresponds to the deviation of an associated index factor. For example, the deviations calculated on the furniture type coincidence index, the time synchronization index, and the behavior feature similarity index can constitute the dimensions of the vector content.

[0047] Furthermore, the cross-sectional reconstruction of the first scene space based on the vector depth and the vector content to obtain the second scene space comprises the following steps: S2231, extracting the historical scene behavior section of the first scene space, and correcting the furniture linkage data in the historical scene behavior section according to the vector depth; S2232, performing secondary correction on the furniture state data of the corrected historical scene behavior section according to the vector content to obtain the target scene behavior section; S2233. Construct a second scene space corresponding to the predicted behavior intention based on the target scene behavior section on the time slice.

[0048] As an exemplary description of this embodiment, for example, at 9 o'clock in the evening, the behavior recognition model predicts that the user will "work at night" by analyzing a series of actions such as the user entering the study, turning on the desk lamp, sitting at the desk, etc. The user actually starts using the computer, but turns on the music player at the same time, which deviates from the pure office behavior predicted by the model; based on the user feedback data, the system identifies the additional behavior of "listening to music" and constructs a behavior deviation vector between the predicted behavior (working at night) and the actual behavior (working at night + listening to music), which reflects the user's need to seek relaxation while working.

[0049] Furthermore, the correlation index factors between the prediction and the actual behavior are analyzed, such as the furniture type overlap (the desk and chair are used consistently, with a high overlap), time synchronization (all at night, good synchronization), and behavioral feature similarity (similar office actions, but with the addition of listening to music, with a medium similarity). Since the main behaviors are consistent, the vector depth is judged to be medium, indicating a moderate degree of deviation; the specific deviation is that users want a more relaxed working environment, that is, in addition to working, they can also enjoy music. Therefore, the vector content includes the specific deviation of "adding background music"; extract historical scene behavior sections, such as study lighting, desk layout, etc., and adjust the furniture linkage data according to the vector depth. For example, the scene section is corrected once, and while the desk is adequately lit, the light color temperature is fine-tuned to a softer level to suit the atmosphere of listening to music; based on the first correction, the furniture status data is refined and adjusted according to the vector content; the system automatically selects and plays the user's preferred relaxing music, and adjusts the speaker position to ensure the best auditory experience without affecting work. According to the time slice (from 9 pm to the end of the user's work), the corrected target scene behavior section is integrated to build a second scene space that is suitable for both work and leisure and relaxation. The second scene space includes appropriate lighting, comfortable seating position, and appropriate background music. Through the above description, the system can capture the difference between user behavior and prediction in real time, and make adjustments quickly to ensure that the scene space always matches the user's current needs; through the phased strategy of first correction and second correction, the system not only adjusts the overall atmosphere of the scene, but also goes deep into specific details (such as music selection and lighting adjustment), achieving highly personalized scene customization. The process of constructing a behavioral deviation vector is actually an exploration of the user's deep-seated needs, which enables the system to go beyond surface behavior and better understand the user's true intentions and expectations. Through the above concrete and dynamic descriptions, we can see that in the scenario where the user works at night, this solution not only improves the adaptability of the smart home environment, but also significantly enhances the user experience, truly realizing the "user-centric" smart space design.

[0050] S3. Perform a spatial ghosting operation on the first scene space and the second scene space to obtain a spatial gap; and obtain an intention calibration factor by slicing the spatial gap.

[0051] Specifically, S3 includes the following steps: S31, performing a spatiotemporal alignment operation on the first scene space and the second scene space according to the spatiotemporal features, extracting the aligned scene behavior sections of the first scene space and the second scene space in sequence according to the slice scale of the time slice, and performing feature deduplication processing to determine the spatial gap; S32, determining a slice scale, and sequentially slicing the space gaps according to the slice scale to obtain an intended calibration factor; The slice scale includes time scale, space scale, furniture type scale and behavior characteristic scale; The intention calibration factor includes a furniture state calibration factor determined according to a time scale and a behavior characteristic scale, and a furniture type calibration factor determined according to a space scale and a furniture type scale.

[0052] In this embodiment, the first scene space and the second scene space are aligned in time and space by using the time and space features, and the scene behavior section is extracted according to the slice scale of the time slice, and then the feature deduplication processing is performed, so that the difference between the two scene spaces can be accurately identified. Spatial gaps provide accurate basic data for subsequent intention calibration; slicing scales include time scale, space scale, furniture type scale and behavioral characteristic scale. Slicing processing in these four dimensions makes the analysis of spatial gaps more comprehensive and in-depth; through slicing at different scales, the subtle differences and potential laws hidden in the spatial gaps can be revealed; by slicing the spatial gaps, this technical means can extract intention calibration factors. The extraction of intention calibration factors helps the system to understand the user's true intentions and needs more accurately, including furniture state calibration factors and furniture type calibration factors; these calibration factors are the key bridge connecting the first scene space and the second scene space, and provide strong support for subsequent intention calibration and space optimization; by comparing the furniture states and behavioral characteristics in the first scene space and the second scene space, the system can identify the user's potential needs and preferences, thereby providing more personalized services and experiences.

[0053] As an example description of this embodiment, in the scenario where the user works at night, the first scene space (the original night office environment) and the second scene space (the office environment after behavioral deviation optimization, including background music, etc.) are first aligned according to time (such as 9 pm to 11 pm) and spatial features (such as the layout of the study), which ensures that the two are compared at the same time and space; in units of minutes (or finer time granularity, depending on the slice scale), the scene behavior sections of the two aligned scene spaces are extracted in sequence. For example, during 9:00-9:01, the first scene space may show that the user is sitting at the desk with the lights on; while the second scene space adds background music on this basis. These sections are subjected to feature deduplication processing, and the features that are added or changed due to behavioral deviation optimization (such as music playing) are identified, so as to determine the spatial gap, that is, the difference between the two scene spaces. In order to deeply analyze the spatial gap, the system sets multiple slice scales, including time scale (such as per minute), space scale (such as different areas of the study), furniture type scale (such as desk, chair, stereo) and behavioral feature scale (such as office, listening to music). Furniture state calibration factor: The system analyzes which furniture states have changed in the space gap (such as the speaker from off to on) based on the time scale and behavioral feature scale, and how these changes are associated with the user's real behavioral intention. For example, within a few minutes after the user starts working, the speaker is automatically turned on, indicating that it is in response to the user's intention to listen to music while working. Therefore, the system will extract a furniture state calibration factor for automatic adjustment of the speaker state in similar situations in the future. At the same time, the system also evaluates whether the space gap involves the replacement or adjustment of furniture types based on the space scale and furniture type scale. If there is a change in furniture type in other scenes (such as from a desk to a sofa), the system will also extract a furniture type calibration factor accordingly. Through spatiotemporal alignment and feature deduplication, the difference between the two scene spaces can be accurately identified, providing a solid foundation for the subsequent extraction of intention calibration factors. The system uses a multi-dimensional slice scale including time, space, furniture type and behavioral characteristics to ensure the comprehensiveness and accuracy of the intention calibration factor. The extracted intention calibration factor not only reflects the user's current behavioral intention, but also provides a basis for the system's future automatic adjustment, realizing the continuous optimization and personalized customization of the smart home environment.

[0054] S4. Build a scenario response model based on furniture status information, furniture linkage data, intention calibration factor, and user behavior data.

[0055] Specifically, S4 includes the following steps: S41, sequentially obtaining furniture state information, furniture linkage data, user behavior data, and intention calibration factors corresponding to the scene behavior section according to the slice scale of the time slice; S42, using furniture status information, furniture linkage data, intention calibration factor, and user behavior data as feature vectors of a support vector machine model to train it and construct a scene response model.

[0056] In this scheme, the furniture state information, furniture linkage data, user behavior data and intention calibration factors corresponding to the scene behavior section are systematically obtained through the slice scale of the time slice, ensuring that the key information required for building the scene response model is fully and accurately integrated; the integrated furniture state information, furniture linkage data, intention calibration factors and user behavior data are trained as feature vectors using the support vector machine model, which can efficiently mine the potential associations and rules between these data, thereby building an accurate scene response model; the model kernel of the scene response model is the support vector machine model, and the construction, training and reliability verification of the support vector machine model can be designed and trained by the technicians in this field according to their own knowledge, which will not be repeated here. The patent point of this application lies in the data processing process before model construction. Through the constructed scene response model, the furniture state, linkage relationship, etc. can be intelligently adjusted and optimized based on the actual behavior and needs of the user, which significantly improves the accuracy and intelligence level of the scene response, so that the smart home system can better meet the personalized needs of the user. Through the introduction of the intention calibration factor, the scene response model can perceive the changes in user intentions in real time and dynamically adjust the scene accordingly. This enhances the system's adaptive capabilities and ensures that the smart home environment always keeps pace with the user's behavior and needs; users can feel the system's accurate understanding and response to their behavior, thereby enhancing their interactivity and satisfaction with the system.

[0057] As an example description of this embodiment, for example, the time slice is set to once per hour to capture the behavior changes of users during the evening office hours. In the evening office scene, the scene behavior section may include the user sitting at the desk, using the computer, flipping through documents, getting up and walking around, etc. Each behavior section corresponds to specific furniture status information and user behavior data; including whether the desk light is turned on, whether the chair is occupied, whether the door of the bookcase is open, etc. For example, at the beginning of the evening office, the desk light and computer may be turned on at the same time, and the chair is occupied. Furniture linkage data reflects the interaction between furniture, such as when the user opens the bookcase door, the reading light on the desk may automatically brighten to provide a better reading environment. The intention calibration factor considers the impact of spatial gaps on user intentions. For example, if the user frequently walks between the desk and the bookcase, it may mean that he is looking for information. At this time, the system can automatically adjust the lighting of the bookcase to assist the user; user behavior data collected by sensors, such as the user's movement trajectory, residence time, etc. These data help analyze the user's behavioral habits and intentions. The furniture status information, furniture linkage data, intent calibration factor and user behavior data are used as feature vectors of the support vector machine model, which together constitute the data set for model input. The support vector machine model is trained using the collected data of office scenes at night. Through training, the model can learn the user's behavior patterns under different furniture states and the relationship between these patterns and user intentions. The construction of the model can comprehensively consider multiple factors (furniture status, linkage data, intent calibration factor and user behavior) to accurately identify the user's intention and respond accordingly. For example, when the model detects that the user has not moved for a long time at the desk at night and the bookcase door is not opened, it may be judged that the user is concentrating on work. At this time, the indoor temperature and lighting can be automatically adjusted to provide a comfortable office environment. When the user frequently walks between the desk and the bookcase, the model may judge that the user is looking for information. At this time, the lighting of the bookcase can be automatically brightened and relevant information recommendations can be provided.

[0058] S5. The scene response model obtains a furniture linkage control strategy in response to the user's spatiotemporal data.

[0059] Specifically, S5 includes the following steps: Detect whether the user behavior pattern in the user's spatiotemporal data matches the linkage control trigger factor. If so, extract the temporal feature information and spatial feature information in the user's spatiotemporal data and combine them with the scene response model to obtain real-time furniture status information and real-time furniture linkage data; use the furniture status information and real-time furniture linkage data as the furniture linkage control strategy; otherwise, do nothing; Among them, the correlation under the corresponding user behavior pattern is constructed according to the linkage duration and usage frequency of each piece of furniture, and the state values ​​corresponding to the two pieces of furniture with the largest correlation are selected as the joint control trigger factor for starting the model.

[0060] Furthermore, the correlation G ij The calculation formula is: ; in, G ij Indicates furniture i and furniture j The degree of correlation between T ij Indicates furniture i and furniture j The duration of linkage; T is the total observation time, F ij Indicates furniture i and furniture j Frequency of use in user behavior patterns; In this embodiment, by detecting whether the user behavior pattern in the user's spatiotemporal data matches the linkage control trigger factor, as the key premise for triggering the furniture linkage control strategy, the user's current behavior intention and needs can be intelligently identified, ensuring that the system can accurately respond to the user's operation. When the user behavior pattern matches the linkage control trigger factor, the system can extract the time feature information and space feature information in the user's spatiotemporal data in real time, and obtain real-time furniture status information and furniture linkage data in combination with the scene response model, so that the system can quickly grasp the furniture status and user behavior in the current scene and make accurate furniture linkage control strategies; further, by constructing the correlation under the corresponding user behavior pattern according to the linkage duration and usage frequency of each piece of furniture, and selecting the state values ​​corresponding to the two pieces of furniture with the largest correlation as the linkage control trigger factor for the model to start, the trigger mechanism of furniture linkage is optimized, so that the system can more sensitively perceive the changes in user behavior and trigger linkage control at the right time, thereby improving the response speed and accuracy of the system. In summary, this technical means realizes the intelligent and precise control of the smart home system through strategies such as intelligent identification of user behavior patterns, real-time acquisition of furniture status information and linkage data, and accurate formulation of furniture linkage control strategies. In this process, the furniture linkage trigger mechanism was optimized, the stability and reliability of the system were enhanced, and users were provided with a smoother and more natural smart home experience.

[0061] As an example description of this embodiment, the user usually works in the study between 8 pm and 11 pm. The study is equipped with furniture and equipment such as desks, office chairs, desk lamps, air conditioners and curtains. In order to improve the user's office comfort and efficiency, the system needs to automatically adjust the status of these furniture according to the user's spatiotemporal data; the system collects the user's behavior data through sensors and smart devices, such as the time when the user enters the study (8 pm), the time when the user sits on the office chair, the time when the desk lamp is turned on, etc., as well as spatial data, such as the user's current location (study). Identify the user's behavior pattern of entering the evening office, which usually includes a series of actions such as entering the study, sitting down, and turning on the desk lamp. According to historical data and user habits, the system selects the two furniture states with the highest correlation as the joint control trigger factors. For example, if the time when the user sits on the office chair and the desk lamp is turned on accounts for 80% of the total time, and this combination is used frequently, the correlation between the office chair and the desk lamp will be higher, becoming the preferred joint control trigger factor, such as "the user sits on the office chair" and "the desk lamp is turned on"; the system detects in real time whether the user's behavior pattern matches the joint control trigger factor. If the user is indeed sitting on the office chair and the desk lamp is turned on, the match is successful. Extract the specific time when the user enters the study and starts working (such as 8:10 pm), confirm that the user is currently in the study, and the specific location is close to the desk. According to the user's behavior pattern, time feature information and spatial feature information, the model calculates the optimal state of each piece of furniture, such as the desk should be at a working height of 0.8m, the office chair should be adjusted to a comfortable sitting position, the desk lamp should be adjusted to a moderate brightness, the air conditioner should be set to a suitable temperature, and the curtains should be closed to reduce external interference. Based on the model calculation, the adjustment instructions and parameters of each furniture are generated. According to the real-time furniture status information and linkage data, the control instructions are sent to the intelligent controller of each furniture to achieve automatic adjustment.

[0062] Embodiment 2: like Figure 4 As shown, a technical solution also provided in the embodiment of the present invention is a smart furniture linkage control system, comprising: First construction model 101: constructing a first scene space based on furniture state data, furniture linkage data and user behavior data; Second construction module 102: The first scene space constructs a second scene space in response to user feedback data; Analysis module 103: performing a spatial ghosting operation on the first scene space and the second scene space to obtain a spatial gap; and obtaining an intention calibration factor by slicing the spatial gap; Generation module 104: constructing a scenario response model according to furniture status information, furniture linkage data, intention calibration factor, and user behavior data; Execution module: The scene response model obtains the furniture linkage control strategy in response to the user's spatiotemporal data.

[0063] In this embodiment, at least the following technical effects are achieved: the system constructs the first scene space and the second scene space in response to user feedback, thereby realizing the preliminary capture and understanding of user behavior and needs, and can make dynamic adjustments based on the user's specific behavior and feedback. The system not only considers the state and linkage data of the furniture, but also fully integrates the user's behavior data. Secondly, the intention calibration factor is obtained through spatial ghosting operation and slicing processing, and the system further improves the recognition accuracy of the user's intention; the system can more accurately grasp the real needs of the user, so as to provide more personalized services; on this basis, a scene response model is constructed, which integrates multiple information such as furniture status, linkage data, user behavior and intention calibration factor, and realizes accurate recognition and rapid response to user needs. This makes the furniture linkage control not only more in line with the actual needs and expectations of users, but also significantly improves the practicality and user satisfaction of the system; further, the model can respond to the user's spatiotemporal data, that is, it can make dynamic adjustments based on the user's location, time and other information. This feature enables the furniture linkage control to not only take into account the user's behavior, but also fully integrate the user's environment and time factors, realizing more comprehensive and intelligent control, and bringing users a more comfortable, convenient and intelligent home life experience.

[0064] Embodiment three: An optional embodiment also provided in the embodiments of the present invention is: an electronic device, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the steps of the smart furniture linkage control method based on time and space perception technology are implemented.

[0065] Embodiment 4: An optional embodiment also provided in the embodiments of the present invention is: a storage medium, in which computer executable instructions are stored. When the computer executable instructions are loaded and executed by a processor, the steps of the smart furniture linkage control method based on time and space perception technology are implemented.

[0066] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the specific device can be divided into different functional modules to complete all or part of the functions described above.

[0067] In the embodiments provided in the present application, it should be understood that the disclosed structures and methods can be implemented in other ways. For example, the embodiments of the structure described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another structure, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, structures or units, which can be electrical, mechanical or other forms.

[0068] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0069] In addition, each functional unit in the embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0070] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0071] The specific implementation described above is a preferred implementation of the intelligent furniture linkage control method and system based on time-space perception technology of the present invention, and is not intended to limit the specific implementation scope of the present invention. The scope of the present invention includes but is not limited to this specific implementation. All equivalent changes made in accordance with the shape and structure of the present invention are within the protection scope of the present invention.

Claims

1. A smart furniture linkage control method based on time-space perception technology, characterized in that: The steps include: S1. Construct the first scene space based on furniture status data, furniture linkage data and user behavior data; S2, the first scene space constructs a second scene space in response to user feedback data; S3, performing a spatial ghosting operation according to the first scene space and the second scene space to obtain a spatial gap; and obtaining an intention calibration factor by slicing the spatial gap; S4, building a scenario response model based on furniture status information, furniture linkage data, intention calibration factor, and user behavior data; S5. The scene response model obtains a furniture linkage control strategy in response to the user's spatiotemporal data.

2. The intelligent furniture linkage control method based on time-space perception technology according to claim 1 is characterized in that: The step of constructing the first scene space based on furniture status data, furniture linkage data, and user behavior data includes the following steps: S11, extracting historical behavior features of real behavior intentions, and constructing historical behavior sections of historical behavior features on time slices; S12, characterize the historical behavior section by furniture type, furniture spatiotemporal characteristics, and furniture behavior characteristics to obtain the historical scene behavior section; S13. Construct a first scene space corresponding to the real behavior intention based on the historical scene behavior section on the time slice.

3. The intelligent furniture linkage control method based on time-space perception technology according to claim 2 is characterized in that: Build furniture status data based on furniture type and furniture behavior characteristics; build furniture linkage data based on furniture type and furniture spatiotemporal characteristics.

4. The intelligent furniture linkage control method based on time-space perception technology according to claim 1 is characterized in that: The first scene space constructs a second scene space in response to user feedback data, comprising the following steps: S21, obtaining the user's predicted behavior intention according to the behavior recognition model, and constructing a behavior deviation vector between the predicted behavior intention and the actual behavior intention according to the user feedback data; S22. Reconstruct the first scene space in sections based on the behavior deviation vector to obtain a second scene space.

5. The intelligent furniture linkage control method based on time-space perception technology according to claim 4 is characterized in that: The step of reconstructing the first scene space based on the behavior deviation vector to obtain the second scene space comprises the following steps: S221, determining the vector depth of the behavior deviation vector according to the overlap degree of the correlation indicator factors of the predicted behavior intention and the actual behavior intention; S222, determining the vector content of the behavior deviation vector according to the deviation amount of the correlation indicator factor between the predicted behavior intention and the actual behavior intention; S223: Reconstruct the first scene space in sections based on the vector depth and the vector content to obtain a second scene space.

6. The intelligent furniture linkage control method based on time-space perception technology according to claim 5 is characterized in that: The step of reconstructing the first scene space based on the vector depth and the vector content to obtain the second scene space comprises the following steps: S2231, extracting the historical scene behavior section of the first scene space, and correcting the furniture linkage data in the historical scene behavior section according to the vector depth; S2232, performing secondary correction on the furniture state data of the corrected historical scene behavior section according to the vector content to obtain the target scene behavior section; S2233. Construct a second scene space corresponding to the predicted behavior intention based on the target scene behavior section on the time slice.

7. The intelligent furniture linkage control method based on time-space perception technology according to claim 1 is characterized by: The method of performing a spatial ghosting operation on the first scene space and the second scene space to obtain a spatial gap and performing a slicing process on the spatial gap to obtain an intention calibration factor comprises the following steps: S31, performing a spatiotemporal alignment operation on the first scene space and the second scene space according to the spatiotemporal features, extracting the aligned scene behavior sections of the first scene space and the second scene space in sequence according to the slice scale of the time slice, and performing feature deduplication processing to determine the spatial gap; S32, determining a slice scale, and sequentially slicing the space gaps according to the slice scale to obtain an intended calibration factor; The slice scale includes time scale, space scale, furniture type scale and behavior characteristic scale; The intention calibration factor includes a furniture state calibration factor determined according to a time scale and a behavior characteristic scale, and a furniture type calibration factor determined according to a space scale and a furniture type scale.

8. The intelligent furniture linkage control method based on time-space perception technology according to claim 1 is characterized by: The construction of a scenario response model based on furniture status information, furniture linkage data, intention calibration factor, and user behavior data includes the following steps: S41, sequentially obtaining furniture state information, furniture linkage data, user behavior data, and intention calibration factors corresponding to the scene behavior section according to the slice scale of the time slice; S42, using furniture status information, furniture linkage data, intention calibration factor, and user behavior data as feature vectors of a support vector machine model to train it and construct a scene response model.

9. The intelligent furniture linkage control method based on time-space perception technology according to claim 1 is characterized by: The scene response model obtains the furniture linkage control strategy in response to the user's spatiotemporal data, including the following steps: Detect whether the user behavior pattern in the user's spatiotemporal data matches the linkage control trigger factor. If so, extract the temporal feature information and spatial feature information in the user's spatiotemporal data and combine them with the scene response model to obtain real-time furniture status information and real-time furniture linkage data; use the furniture status information and real-time furniture linkage data as the furniture linkage control strategy; Otherwise, no action; Among them, the correlation under the corresponding user behavior pattern is constructed according to the linkage duration and usage frequency of each piece of furniture, and the state values ​​corresponding to the two pieces of furniture with the largest correlation are selected as the joint control trigger factor for starting the model.

10. An intelligent furniture linkage control system, applicable to the intelligent furniture linkage control method based on time-space perception technology as claimed in any one of claims 1 to 9, characterized in that: include: The first construction module: constructs the first scene space based on furniture status data, furniture linkage data and user behavior data; A second construction module: the first scene space constructs a second scene space in response to user feedback data; Analysis module: performing a spatial ghosting operation on the first scene space and the second scene space to obtain a spatial gap; and obtaining an intention calibration factor by slicing the spatial gap; Generation module: builds a scenario response model based on furniture status information, furniture linkage data, intention calibration factors, and user behavior data; Execution module: The scene response model obtains the furniture linkage control strategy in response to the user's spatiotemporal data.

11. An electronic device, characterized in that: It includes a memory and a processor, wherein the memory stores a computer program, and when the processor calls the computer program in the memory, the steps of the smart furniture linkage control method based on time-space perception technology as described in any one of claims 1 to 9 are implemented.

12. A storage medium, characterized in that: The storage medium stores computer executable instructions, and when the computer executable instructions are loaded and executed by the processor, the steps of the smart furniture linkage control method based on time-space perception technology as described in any one of claims 1 to 9 are implemented.

Citation Information

Patent Citations

  • Using change of scene to trigger automatic image capture

    CN113170049A

  • Learning method and control method of smart home control system

    CN114578701A

  • Method, device and system for linkage recommendation of intelligent equipment

    CN114691971A

  • Intelligent furniture comfort degree adjusting method and system based on behavior feature recognition

    CN118655859A

  • Virtual scene control method and system based on MR large space

    CN118708085A

Cited By

  • Intelligent terminal operation scene optimization system and method based on multi-dimensional behavior data

    CN119620628A

  • Intelligent terminal operation scenario optimization system and method based on multi-dimensional behavior data

    CN119620628B