Household environment control method and system based on indoor and outdoor sensing data

Abstract

The invention discloses a home environment control method and system based on indoor and outdoor sensing data. The method comprises the following steps: acquiring first sensing data of an indoor area and second sensing data of an outdoor area; according to the first sensing data, identifying living activity characteristics corresponding to the indoor area; according to the second sensing data, external activity characteristics corresponding to the outdoor area are identified; and determining a corresponding home equipment control strategy based on an association mapping model according to the living activity characteristics and the external activity characteristics. Therefore, accurate equipment cooperative control of indoor and outdoor activity linkage perception can be realized, the home intelligent responsiveness and the user convenience are improved, and the equipment adjustment lagging risk caused by indoor and outdoor activity disjunction is reduced.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for controlling the home environment based on indoor and outdoor sensor data. Background Technology

[0002] With the rapid popularization of smart home systems in daily life, users are increasingly valuing the coordinated control of home devices through the linkage of indoor and outdoor activities to improve responsiveness and convenience. Among these challenges, generating precise control strategies to avoid adjustment lag has become a key technical issue. Existing technologies typically collect sensor data from single indoor or outdoor areas, using independent activity recognition or fixed rules to trigger home device operation to meet basic smart needs. However, existing solutions lack the separate identification of indoor and outdoor activity characteristics and the dynamic modeling of their correlation, making it difficult to achieve coordinated device control linking indoor and outdoor activities. Commonly used isolated or delayed response control strategies cannot adapt to changes in user behavior across different areas, resulting in insufficient smart home responsiveness. This leads to device adjustment lag or ineffective operation due to the disconnect between indoor and outdoor activities, limiting user convenience and overall system efficiency. Therefore, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a home environment control method and system based on indoor and outdoor sensor data, which can realize precise coordinated control of devices based on the linkage perception of indoor and outdoor activities, improve the smart responsiveness and user convenience of the home, and reduce the risk of device adjustment lag caused by the disconnect between indoor and outdoor activities.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a home environment control method based on indoor and outdoor sensor data, the method comprising: Acquire first sensor data for the indoor area and second sensor data for the outdoor area; Based on the first sensor data, the residential activity characteristics corresponding to the indoor area are identified; Based on the second sensor data, the external activity characteristics corresponding to the outdoor area are identified; Based on the residential activity characteristics and the external activity characteristics, a corresponding home appliance control strategy is determined using an association mapping model.

[0005] As an optional implementation, in a first aspect of the invention, the first sensing data includes at least one of sound data, image data, and light reflection data acquired through home appliances in the indoor area.

[0006] As an optional implementation, in a first aspect of the invention, the second sensing data is obtained through a portal home device located in the boundary area between the indoor area and the outdoor area; the second sensing data includes at least one of sound data, image data, and light reflection data in the outdoor area.

[0007] As an optional implementation, in a first aspect of the present invention, identifying the residential activity characteristics corresponding to the indoor area based on the first sensing data includes: For the first sensor data at each historical time point, the first sensor data at that historical time point is input into the trained resident identification model to obtain the resident activity data corresponding to that historical time point; the resident activity data includes resident identity, resident location and resident actions; the resident identification model is trained using a training dataset that includes multiple training sensor data and corresponding resident activity annotations; Based on a time-series analysis algorithm, the residential activity characteristics corresponding to the indoor area are determined using all the resident activity data at the aforementioned historical time points.

[0008] As an optional implementation, in the first aspect of the present invention, determining the residential activity characteristics corresponding to the indoor area based on a time-series analysis algorithm using all the resident activity data at the historical time points includes: Based on the corresponding historical time points, all the resident identities, resident locations, and resident actions are sorted from morning to night to obtain resident identity sequences, resident location sequences, and resident action sequences. The resident identity sequence, resident location sequence, and resident action sequence are fused using multiple features to obtain a fused dataset. The fused dataset is input into a trained LSTM neural network to obtain the residential activity features corresponding to the indoor area; the LSTM neural network is trained using a training dataset that includes multiple training fused datasets and corresponding residential activity feature annotations.

[0009] As an optional implementation, in the first aspect of the present invention, identifying the external activity characteristics corresponding to the outdoor area based on the second sensing data includes: The second sensor data is input into the trained weather recognition model to obtain the corresponding weather features; The second sensor data is input into the trained visitor prediction model to obtain the corresponding visitor probability; When the probability of a visit is greater than a preset first probability threshold, the second sensing data is input into the trained visitor identification model to obtain the corresponding visitor information. Determine multiple historical external activities corresponding to the visitor information in a preset database; All the historical external activities and the weather characteristics are fused together to obtain the external activity characteristics corresponding to the outdoor area.

[0010] As an optional implementation, in the first aspect of the invention, fusing all the historical external activities and the weather characteristics to obtain the external activity characteristics corresponding to the outdoor area includes: For each historical external activity, calculate the similarity between the weather data corresponding to that historical external activity and the weather characteristics; Filter out multiple historical external activities with a similarity greater than a preset threshold to obtain similar external activities; All similar external activities and their corresponding similarity scores are identified as external activity features corresponding to the outdoor area; the similar external activities include activity location, activity type, participants, and home appliances used in the activity.

[0011] As an optional implementation, in the first aspect of the present invention, determining the corresponding home appliance control strategy based on an association mapping model according to the residential activity characteristics and the external activity characteristics includes: The residential activity features and the external activity features are input into a trained association vector prediction model to obtain the output association vector; the association vector prediction model is trained using a training dataset that includes multiple training residential activity features and training external activity features, as well as corresponding association degree labels. Based on the preset mapping relationship between association vectors and devices, determine multiple associated home devices corresponding to the association vectors; Set each of the aforementioned associated home devices to a pre-start standby state; For any number of the associated home devices, the device parameters of the associated home devices are matched in the historical control strategy database to obtain the corresponding device collaborative control combination; Determine the control command identifier corresponding to the device collaborative control combination; The control command identifier is set as the priority judgment identifier corresponding to the plurality of associated home devices, so that when the plurality of associated home devices receive an instruction that conforms to the control command identifier, they will be activated in advance to the device state corresponding to the device collaborative control combination.

[0012] A second aspect of this invention discloses a home environment control system based on indoor and outdoor sensor data, the system comprising: The acquisition module is used to acquire first sensor data of the indoor area and second sensor data of the outdoor area; The first identification module is used to identify the residential activity characteristics corresponding to the indoor area based on the first sensing data. The second identification module is used to identify the external activity characteristics corresponding to the outdoor area based on the second sensing data. The determination module is used to determine the corresponding home device control strategy based on the residential activity characteristics and the external activity characteristics, using an association mapping model.

[0013] As an optional implementation, in a second aspect of the invention, the first sensing data includes at least one of sound data, image data, and light reflection data acquired by home appliances within the indoor area.

[0014] As an optional implementation, in a second aspect of the invention, the second sensing data is obtained through a portal home device located in the boundary area between the indoor area and the outdoor area; the second sensing data includes at least one of sound data, image data, and light reflection data in the outdoor area.

[0015] As an optional implementation, in a second aspect of the present invention, the specific method by which the first identification module identifies the residential activity characteristics corresponding to the indoor area based on the first sensing data includes: For the first sensor data at each historical time point, the first sensor data at that historical time point is input into the trained resident identification model to obtain the resident activity data corresponding to that historical time point; the resident activity data includes resident identity, resident location and resident actions; the resident identification model is trained using a training dataset that includes multiple training sensor data and corresponding resident activity annotations; Based on a time-series analysis algorithm, the residential activity characteristics corresponding to the indoor area are determined using all the resident activity data at the aforementioned historical time points.

[0016] As an optional implementation, in a second aspect of the invention, the first identification module determines the specific method by which it uses time-series analysis algorithms to analyze the resident activity data at all historical time points to determine the residential activity characteristics corresponding to the indoor area, including: Based on the corresponding historical time points, all the resident identities, resident locations, and resident actions are sorted from morning to night to obtain resident identity sequences, resident location sequences, and resident action sequences. The resident identity sequence, resident location sequence, and resident action sequence are fused using multiple features to obtain a fused dataset. The fused dataset is input into a trained LSTM neural network to obtain the residential activity features corresponding to the indoor area; the LSTM neural network is trained using a training dataset that includes multiple training fused datasets and corresponding residential activity feature annotations.

[0017] As an optional implementation, in a second aspect of the invention, the specific method by which the second identification module identifies the external activity characteristics corresponding to the outdoor area based on the second sensing data includes: The second sensor data is input into the trained weather recognition model to obtain the corresponding weather features; The second sensor data is input into the trained visitor prediction model to obtain the corresponding visitor probability; When the probability of a visit is greater than a preset first probability threshold, the second sensing data is input into the trained visitor identification model to obtain the corresponding visitor information. Determine multiple historical external activities corresponding to the visitor information in a preset database; All the historical external activities and the weather characteristics are fused together to obtain the external activity characteristics corresponding to the outdoor area.

[0018] As an optional implementation, in a second aspect of the invention, the specific method by which the second identification module fuses all the historical external activities and the weather characteristics to obtain the external activity characteristics corresponding to the outdoor area includes: For each historical external activity, calculate the similarity between the weather data corresponding to that historical external activity and the weather characteristics; Filter out multiple historical external activities with a similarity greater than a preset threshold to obtain similar external activities; All similar external activities and their corresponding similarity scores are identified as external activity features corresponding to the outdoor area; the similar external activities include activity location, activity type, participants, and home appliances used in the activity.

[0019] As an optional implementation, in a second aspect of the invention, the determining module determines the specific method of the corresponding home device control strategy based on the residential activity characteristics and the external activity characteristics, using an association mapping model, including: The residential activity features and the external activity features are input into a trained association vector prediction model to obtain the output association vector; the association vector prediction model is trained using a training dataset that includes multiple training residential activity features and training external activity features, as well as corresponding association degree labels. Based on the preset mapping relationship between association vectors and devices, determine multiple associated home devices corresponding to the association vectors; Set each of the aforementioned associated home devices to a pre-start standby state; For any number of the associated home devices, the device parameters of the associated home devices are matched in the historical control strategy database to obtain the corresponding device collaborative control combination; Determine the control command identifier corresponding to the device collaborative control combination; The control command identifier is set as the priority judgment identifier corresponding to the plurality of associated home devices, so that when the plurality of associated home devices receive an instruction that conforms to the control command identifier, they will be activated in advance to the device state corresponding to the device collaborative control combination.

[0020] A third aspect of this invention discloses another home environment control system based on indoor and outdoor sensor data, the system comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute some or all of the steps in the home environment control method based on indoor and outdoor sensor data disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the home environment control method based on indoor and outdoor sensor data disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: This invention acquires first sensor data from indoor areas and second sensor data from outdoor areas to identify residential activity characteristics and external activity characteristics, respectively. Based on an association mapping model, it determines home device control strategies, thereby enabling precise coordinated control of devices through the linkage of indoor and outdoor activities. This improves the responsiveness of smart homes and user convenience, and reduces the risk of device adjustment lag caused by the disconnect between indoor and outdoor activities. Attached Figure Description

[0023] 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.

[0024] Figure 1This is a flowchart illustrating a home environment control method based on indoor and outdoor sensor data disclosed in an embodiment of the present invention.

[0025] Figure 2 This is a schematic diagram of a home environment control system based on indoor and outdoor sensor data disclosed in an embodiment of the present invention.

[0026] Figure 3 This is a schematic diagram of another home environment control system based on indoor and outdoor sensor data disclosed in an embodiment of the present invention. Detailed Implementation

[0027] 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.

[0028] 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 device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0029] 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.

[0030] This invention discloses a home environment control method and system based on indoor and outdoor sensor data. By acquiring first sensor data of the indoor area and second sensor data of the outdoor area, it identifies residential activity characteristics and external activity characteristics respectively. Based on an association mapping model, it determines the control strategy for home devices, thereby achieving precise coordinated control of devices through the linkage of indoor and outdoor activities. This improves the responsiveness of home intelligence and user convenience, and reduces the risk of device adjustment lag caused by the disconnect between indoor and outdoor activities. Detailed explanations follow.

[0031] Example 1 Please see Figure 1 , Figure 1 This is a flowchart illustrating a home environment control method based on indoor and outdoor sensor data disclosed in an embodiment of the present invention. Figure 1 The described home environment control method based on indoor and outdoor sensor data can be applied to data processing systems / data processing devices / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 1 As shown, the home environment control method based on indoor and outdoor sensor data may include the following operations: 101. Acquire the first sensor data of the indoor area and the second sensor data of the outdoor area.

[0032] Optionally, the first sensing data includes at least one of sound data, image data, and light reflection data acquired through home appliances within the indoor area.

[0033] Optionally, the second sensor data is obtained through a portal home device located in the boundary area between the indoor and outdoor zones.

[0034] Optionally, the second sensing data includes at least one of sound data, image data, and light reflection data in the outdoor area.

[0035] Optionally, the first sensing data may include indoor camera images, infrared array thermal imaging, door and window magnetic sensors, floor pressure sensors, or smart speaker microphone pickups; this invention does not limit the scope of the data.

[0036] Optionally, the second sensor data may include outdoor weather station data (temperature, humidity, wind speed, PM2.5), doorbell camera images, door lock records, or community access control card swipe data; this invention does not impose any limitations.

[0037] 102. Based on the first sensor data, identify the residential activity characteristics corresponding to the indoor area. Optionally, the residential activity characteristics may include feature representation data corresponding to features such as "elderly person resting alone", "children playing", "family dining", or "no one in the house", and this invention does not limit these features.

[0038] 103. Based on the second sensor data, identify the external activity characteristics corresponding to the outdoor area. Optionally, the external activity feature may include feature representation data corresponding to features such as "walking on a sunny day", "not going out on a rainy day", "family members returning home", "delivery of express", or "stranger loitering", and the present invention does not limit it.

[0039] 104. Based on the characteristics of residential activities and external activities, determine the corresponding home appliance control strategies using an association mapping model.

[0040] As can be seen, the above-mentioned embodiments of the invention acquire first sensor data of the indoor area and second sensor data of the outdoor area, respectively identify residential activity characteristics and external activity characteristics, and determine home equipment control strategies based on the correlation mapping model. This enables precise coordinated control of equipment based on the linkage perception of indoor and outdoor activities, improves the responsiveness of smart home and user convenience, and reduces the risk of equipment adjustment lag caused by the disconnect between indoor and outdoor activities.

[0041] As an optional embodiment, the step above, identifying the residential activity characteristics corresponding to the indoor area based on the first sensing data, includes: For the first sensor data at each historical time point, the first sensor data at that historical time point is input into the trained resident identification model to obtain the resident activity data corresponding to that historical time point. Based on time-series analysis algorithms, the residential activity characteristics corresponding to indoor areas are determined using all historical time point resident activity data.

[0042] Optionally, resident activity data includes resident identity, resident location, and resident actions.

[0043] Optionally, the resident identification model is trained using a training dataset that includes multiple training sensor data and corresponding resident activity annotations.

[0044] Optionally, the resident identification model can be a YOLOv8-Pose+OpenPose multi-human keypoint detection + action classification model, trained on 80,000 hours of labeled home surveillance data, with an mAP of 0.93. This invention does not limit the model.

[0045] Optionally, the time series analysis algorithm can be a rule engine + state machine or a Transformer time series encoder; this invention does not limit it.

[0046] As can be seen, through the above optional embodiments, by inputting the first sensor data from multiple historical time points into the resident identification model to obtain resident activity data, and determining indoor residential activity characteristics based on time series analysis, continuous quantitative assessment of resident identity, location and actions at multiple time points can be achieved, thereby improving the comprehensiveness and accuracy of indoor activity feature identification and reducing the risk of misjudgment of activity features due to single-moment data.

[0047] As an optional embodiment, the above steps, which involve using time-series analysis algorithms to determine the residential activity characteristics corresponding to the indoor area based on all historical time point resident activity data, include: Based on the corresponding historical time points, all residents' identities, locations, and actions are sorted from morning to night to obtain resident identity sequences, resident location sequences, and resident action sequences. The resident identity sequence, resident location sequence, and resident action sequence are fused using multiple features to obtain a fused dataset. The fused dataset is input into the trained LSTM neural network to obtain the residential activity features corresponding to the indoor areas in the output.

[0048] Optionally, the sorting can form a three-channel time series, with each channel having a fixed window length (e.g., 30 minutes), but this invention does not impose any limitations on this.

[0049] Optionally, the multi-feature fusion can be channel splicing + 1D convolution dimensionality reduction or cross-attention fusion, and this invention does not limit it.

[0050] Optionally, the LSTM neural network is trained using a training dataset that includes multiple training fusion data and corresponding residential activity feature annotations.

[0051] Optionally, the LSTM neural network can be a 4-layer unidirectional LSTM (512 hidden units per layer) + global max pooling + fully connected classification head (outputting 32 residential activity categories), trained on 150,000 household time-series labeled data, with a Top-1 accuracy of 96.7%. This invention does not impose any limitations.

[0052] As can be seen, through the above optional embodiments, by sorting resident identity, location and action sequence by time, performing multi-feature fusion and inputting it into an LSTM neural network to output residential activity features, accurate indoor activity trend analysis based on long time series fusion is achieved, improving the dynamics and predictability of residential activity features and reducing the risk of missing activity associations due to feature isolation.

[0053] As an optional embodiment, the step above, identifying the external activity characteristics corresponding to the outdoor area based on the second sensing data, includes: The second sensor data is input into the trained weather recognition model to obtain the corresponding weather features; The second sensor data is input into the trained visitor prediction model to obtain the corresponding visitor probability; When the probability of a visitor is greater than a preset first probability threshold, the second sensor data is input into the trained visitor identification model to obtain the corresponding visitor information. Identify multiple historical external activities corresponding to visitor information in a pre-defined database; By integrating all historical external activities and weather characteristics, the corresponding external activity characteristics for the outdoor area are obtained.

[0054] Optionally, the weather recognition model can be a ResNet-50 image classification + numerical regression dual-head model, trained on local weather station images + sensor data, and this invention does not limit it.

[0055] Optionally, the visitor prediction model can be a time-series classification model with 3 convolutional layers + LSTM, outputting a 0-1 visitor probability. This invention does not impose any limitations on this model.

[0056] Optionally, the visitor recognition model can be an ArcFace+ResNet-100 face recognition model, trained on a database of 100,000 faces for community access control, with a Top-1 recognition rate of 99.1%. This invention does not impose any limitations on this model.

[0057] Optionally, the historical external activities may include marked events such as "express delivery", "relatives visit", and "property maintenance", but this invention does not limit them.

[0058] Optionally, the fusion can be feature concatenation or weighted vectors, and this invention does not limit it.

[0059] As can be seen, through the above optional embodiments, by inputting the second sensor data into the weather recognition and visitor prediction model, and further identifying visitor information when the probability of a visit is high, and by fusing historical external activities and weather characteristics to generate external activity characteristics, comprehensive perception of outdoor weather and visit events can be achieved, thereby improving the pertinence and completeness of external activity characteristics and reducing the risk of incomplete characteristics caused by a single external factor.

[0060] As an optional embodiment, the above steps, which involve fusing all historical external activities and weather characteristics to obtain the external activity characteristics corresponding to the outdoor area, include: For each historical external event, calculate the similarity between the weather data and weather features corresponding to that historical external event; Filter out multiple historical external activities with similarity greater than a preset threshold to obtain similar external activities; All similar external activities and their corresponding labeled similarities are identified as the external activity features corresponding to the outdoor area.

[0061] Optional, similar external events include event location, event type, event participants, and home equipment used.

[0062] Optionally, the similarity can be multidimensional Euclidean distance or cosine similarity, and this invention does not limit it.

[0063] As can be seen, through the above optional embodiments, by filtering historical external activities with high weather similarity and labeling the similarity to generate external activity features, accurate external activity representation based on historical similar cases can be achieved, improving the practicality and relevance of external activity features and reducing the risk of activity feature deviation due to insufficient current external data.

[0064] As an optional embodiment, the step described above, determining the corresponding home appliance control strategy based on a correlation mapping model according to residential activity characteristics and external activity characteristics, includes: The residential activity features and external activity features are input into the trained association vector prediction model to obtain the output association vector; Based on the preset mapping relationship between association vectors and devices, determine multiple associated home devices corresponding to the association vectors; Set each connected home device to pre-start standby mode; For any number of associated home devices, match the device parameters of these devices in the historical control strategy database to obtain the corresponding device collaborative control combination; Determine the control command identifier corresponding to the equipment collaborative control combination; The control command identifier is set as the priority judgment identifier corresponding to the multiple associated home devices, so that when the multiple associated home devices receive an instruction that matches the control command identifier, they will start in advance to the device state corresponding to the device collaborative control combination.

[0065] Optionally, the association vector prediction model is trained using a training dataset that includes multiple training residential activity features and training external activity features, along with corresponding association degree labels.

[0066] Optionally, the association vector prediction model can be a dual-tower Siamese network (3 fully connected layers per tower, 512-256-128), trained with contrast loss, trained on 120,000 indoor and outdoor activity association pairs, achieving an AUC of 0.95. This invention does not impose any limitations.

[0067] Optionally, the mapping relationship can be vector clustering + device label rule base, such as a highly correlated vector corresponding to "entrance light + air conditioner + door lock", which is not limited in this invention.

[0068] Optionally, the early start standby can be low-power preheating or Wake-up over the network, and this invention does not limit it.

[0069] Optionally, the priority determination flag can be used to preload instructions or preset states; this invention does not limit this.

[0070] As can be seen, through the above optional embodiments, by inputting residential activity features and external activity features into the correlation vector prediction model and outputting the correlation vector, and mapping the associated home devices to pre-standby and collaborative control, the precise pre-start and combination optimization of devices driven by indoor and outdoor activities can be achieved, thereby improving the foresight and collaborative efficiency of home device response and reducing the risk of user experience degradation caused by failure to adjust in time due to activity changes.

[0071] The solution in this embodiment of the invention is illustrated by a specific case, taking Mr. Wang's virtual smart apartment as an example: At 18:45 on November 20, 2025, Mr. Wang was on his way home from get off work.

[0072] The indoor infrared array and camera detected that no one was in the living room or the kitchen, and determined that the current residential activity was characterized as "no one waiting to return".

[0073] The outdoor doorbell camera and weather station detected light rain and a temperature of 18℃. Facial recognition determined that Mr. Wang was 30 meters away from the gate, with a visit probability of 0.96, which is greater than the threshold of 0.85, and identified him as "the homeowner returning home".

[0074] The system integrates indoor "no one waiting to return" and outdoor "homeowner returning home + light rain" features, inputs the correlation vector prediction model, and outputs highly correlated vectors corresponding to "welcoming home scene".

[0075] Matching associated devices: entryway light, living room air conditioner, door lock, background music speaker.

[0076] Preheat the entryway light to 30%, set the air conditioner to 26°C, lock the door to the unlocking position, and play welcome music on the speaker.

[0077] The moment Mr. Wang unlocked the door with his face, the system triggered the "SCENE_HOME_COMING" command, and four devices worked together: the lights gradually brightened to 80%, the air conditioner turned on, the music "Welcome Home" played, and the door lock automatically unlocked.

[0078] The entire process, from detecting the visitor to the device being ready, took only 18 seconds. Mr. Wang was able to enjoy a comfortable environment as soon as he entered the house without having to operate it manually, which improved his home experience and saved 15% energy (avoiding long-term full-power standby).

[0079] Example 2 Please see Figure 2 , Figure 2 This is a schematic diagram of a home environment control system based on indoor and outdoor sensor data, as disclosed in an embodiment of the present invention. Figure 2 The described home environment control system based on indoor and outdoor sensor data can be applied to data processing systems / data processing devices / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 2 As shown, the home environment control system based on indoor and outdoor sensor data may include: The acquisition module 201 is used to acquire first sensing data of the indoor area and second sensing data of the outdoor area.

[0080] The first identification module 202 is used to identify the residential activity characteristics corresponding to the indoor area based on the first sensor data. The second identification module 203 is used to identify the external activity characteristics corresponding to the outdoor area based on the second sensor data. The determination module 204 is used to determine the corresponding home device control strategy based on the characteristics of residential activities and external activities, using an association mapping model.

[0081] As can be seen, the above-mentioned embodiments of the invention acquire first sensor data of the indoor area and second sensor data of the outdoor area, respectively identify residential activity characteristics and external activity characteristics, and determine home equipment control strategies based on the correlation mapping model. This enables precise coordinated control of equipment based on the linkage perception of indoor and outdoor activities, improves the responsiveness of smart home and user convenience, and reduces the risk of equipment adjustment lag caused by the disconnect between indoor and outdoor activities.

[0082] As an optional embodiment, the first sensing data includes at least one of sound data, image data, and light reflection data acquired through home appliances within the indoor area.

[0083] As can be seen, the content of the first sensing data is defined through the above optional embodiments to accurately characterize the activity characteristics of the indoor area, assist in realizing precise device collaborative control of indoor and outdoor activity linkage perception, improve the responsiveness of smart home and user convenience, and reduce the risk of device adjustment lag caused by the disconnect between indoor and outdoor activities.

[0084] As an optional embodiment, the second sensing data is obtained through a portal home device located in the boundary area between the indoor and outdoor areas; the second sensing data includes at least one of sound data, image data, and light reflection data in the outdoor area.

[0085] As can be seen, the content of the second sensing data is defined through the above optional embodiments to accurately characterize the relevant characteristics of the outdoor area, assist in realizing precise device collaborative control of indoor and outdoor activity linkage perception, improve the responsiveness of smart home and user convenience, and reduce the risk of device adjustment lag caused by the disconnect between indoor and outdoor activities.

[0086] As an optional embodiment, the first identification module identifies the specific methods by which it identifies the residential activity characteristics corresponding to the indoor area based on the first sensor data, including: For the first sensor data at each historical time point, the first sensor data at that historical time point is input into the trained resident identification model to obtain the resident activity data corresponding to that historical time point; optionally, the resident activity data includes resident identity, resident location and resident actions; the resident identification model is trained through a training dataset that includes multiple training sensor data and corresponding resident activity annotations. Based on time-series analysis algorithms, the residential activity characteristics corresponding to indoor areas are determined using all historical time point resident activity data.

[0087] As can be seen, through the above optional embodiments, by inputting the first sensor data from multiple historical time points into the resident identification model to obtain resident activity data, and determining indoor residential activity characteristics based on time series analysis, continuous quantitative assessment of resident identity, location and actions at multiple time points can be achieved, thereby improving the comprehensiveness and accuracy of indoor activity feature identification and reducing the risk of misjudgment of activity features due to single-moment data.

[0088] As an optional embodiment, the first identification module uses time-series analysis algorithms to determine the specific methods for identifying the residential activity characteristics corresponding to indoor areas based on all historical time point resident activity data, including: Based on the corresponding historical time points, all residents' identities, locations, and actions are sorted from morning to night to obtain resident identity sequences, resident location sequences, and resident action sequences. The resident identity sequence, resident location sequence, and resident action sequence are fused using multiple features to obtain a fused dataset. The fused dataset is input into the trained LSTM neural network to obtain the residential activity features corresponding to the indoor areas in the output; the LSTM neural network is trained using a training dataset that includes multiple training fused datasets and corresponding residential activity feature annotations.

[0089] As can be seen, through the above optional embodiments, by sorting resident identity, location and action sequence by time, performing multi-feature fusion and inputting it into an LSTM neural network to output residential activity features, accurate indoor activity trend analysis based on long time series fusion is achieved, improving the dynamics and predictability of residential activity features and reducing the risk of missing activity associations due to feature isolation.

[0090] As an optional embodiment, the second identification module identifies the specific method by which it identifies the external activity characteristics corresponding to the outdoor area based on the second sensor data, including: The second sensor data is input into the trained weather recognition model to obtain the corresponding weather features; The second sensor data is input into the trained visitor prediction model to obtain the corresponding visitor probability; When the probability of a visitor is greater than a preset first probability threshold, the second sensor data is input into the trained visitor identification model to obtain the corresponding visitor information. Identify multiple historical external activities corresponding to visitor information in a pre-defined database; By integrating all historical external activities and weather characteristics, the corresponding external activity characteristics for the outdoor area are obtained.

[0091] As can be seen, through the above optional embodiments, by inputting the second sensor data into the weather recognition and visitor prediction model, and further identifying visitor information when the probability of a visit is high, and by fusing historical external activities and weather characteristics to generate external activity characteristics, comprehensive perception of outdoor weather and visit events can be achieved, thereby improving the pertinence and completeness of external activity characteristics and reducing the risk of incomplete characteristics caused by a single external factor.

[0092] As an optional embodiment, the second identification module fuses all historical external activities and weather features to obtain the specific method for obtaining the external activity features corresponding to the outdoor area, including: For each historical external event, calculate the similarity between the weather data and weather features corresponding to that historical external event; Filter out multiple historical external activities with similarity greater than a preset threshold to obtain similar external activities; All similar external activities and their corresponding similarity scores are identified as the external activity features corresponding to the outdoor area; similar external activities include activity location, activity type, participants, and home appliances used in the activity.

[0093] As can be seen, through the above optional embodiments, by filtering historical external activities with high weather similarity and labeling the similarity to generate external activity features, accurate external activity representation based on historical similar cases can be achieved, improving the practicality and relevance of external activity features and reducing the risk of activity feature deviation due to insufficient current external data.

[0094] As an optional embodiment, the determining module determines the specific method of the corresponding home device control strategy based on the characteristics of residential activities and external activities, using an association mapping model, including: The residential activity features and external activity features are input into the trained association vector prediction model to obtain the output association vector; optionally, the association vector prediction model is trained using a training dataset that includes multiple training residential activity features and training external activity features and corresponding association degree labels. Based on the preset mapping relationship between association vectors and devices, determine multiple associated home devices corresponding to the association vectors; Set each connected home device to pre-start standby mode; For any number of associated home devices, match the device parameters of these devices in the historical control strategy database to obtain the corresponding device collaborative control combination; Determine the control command identifier corresponding to the equipment collaborative control combination; The control command identifier is set as the priority judgment identifier corresponding to the multiple associated home devices, so that when the multiple associated home devices receive an instruction that matches the control command identifier, they will start in advance to the device state corresponding to the device collaborative control combination.

[0095] As can be seen, through the above optional embodiments, by inputting residential activity features and external activity features into the correlation vector prediction model and outputting the correlation vector, and mapping the associated home devices to pre-standby and collaborative control, the precise pre-start and combination optimization of devices driven by indoor and outdoor activities can be achieved, thereby improving the foresight and collaborative efficiency of home device response and reducing the risk of user experience degradation caused by failure to adjust in time due to activity changes.

[0096] Example 3 Please see Figure 3 , Figure 3 This is another home environment control system based on indoor and outdoor sensor data disclosed in the embodiments of the present invention. Figure 3 The described home environment control system based on indoor and outdoor sensor data is applied in a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 3 As shown, the home environment control system based on indoor and outdoor sensor data may include: Memory 301 storing executable program code; Processor 302 coupled to memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the home environment control method based on indoor and outdoor sensor data described in Embodiment 1.

[0097] Example 4 This invention discloses a computer read storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to execute the steps of the home environment control method based on indoor and outdoor sensor data described in Embodiment 1.

[0098] Example 5 This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the home environment control method based on indoor and outdoor sensor data described in Embodiment 1.

[0099] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0100] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0101] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0102] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0103] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0104] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0105] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0106] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0107] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0108] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0109] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0110] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0111] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0112] Finally, it should be noted that the home environment control method and system based on indoor and outdoor sensor data 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; and these 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 controlling home environment based on indoor and outdoor sensor data, characterized in that, The method includes: Acquire first sensor data for the indoor area and second sensor data for the outdoor area; Based on the first sensor data, the residential activity characteristics corresponding to the indoor area are identified; Based on the second sensor data, the external activity characteristics corresponding to the outdoor area are identified; Based on the residential activity characteristics and the external activity characteristics, a corresponding home appliance control strategy is determined using an association mapping model.

2. The home environment control method based on indoor and outdoor sensor data according to claim 1, characterized in that, The first sensing data includes at least one of sound data, image data, and light reflection data acquired through home appliances within the indoor area.

3. The home environment control method based on indoor and outdoor sensor data according to claim 1, characterized in that, The second sensing data is obtained through a portal home device installed in the boundary area between the indoor area and the outdoor area; the second sensing data includes at least one of sound data, image data and light reflection data in the outdoor area.

4. The home environment control method based on indoor and outdoor sensor data according to claim 1, characterized in that, The step of identifying the residential activity characteristics corresponding to the indoor area based on the first sensing data includes: For the first sensor data at each historical time point, the first sensor data at that historical time point is input into the trained resident identification model to obtain the resident activity data corresponding to that historical time point; the resident activity data includes resident identity, resident location and resident actions; the resident identification model is trained using a training dataset that includes multiple training sensor data and corresponding resident activity annotations; Based on a time-series analysis algorithm, the residential activity characteristics corresponding to the indoor area are determined using all the resident activity data at the aforementioned historical time points.

5. The home environment control method based on indoor and outdoor sensor data according to claim 4, characterized in that, The step of using time-series analysis algorithms to determine the residential activity characteristics corresponding to the indoor area based on the resident activity data from all the historical time points includes: Based on the corresponding historical time points, all the resident identities, resident locations, and resident actions are sorted from morning to night to obtain resident identity sequences, resident location sequences, and resident action sequences. The resident identity sequence, resident location sequence, and resident action sequence are fused using multiple features to obtain a fused dataset. The fused dataset is input into a trained LSTM neural network to obtain the residential activity features corresponding to the indoor area; the LSTM neural network is trained using a training dataset that includes multiple training fused datasets and corresponding residential activity feature annotations.

6. The home environment control method based on indoor and outdoor sensor data according to claim 1, characterized in that, The step of identifying external activity characteristics corresponding to the outdoor area based on the second sensing data includes: The second sensor data is input into the trained weather recognition model to obtain the corresponding weather features; The second sensor data is input into the trained visitor prediction model to obtain the corresponding visitor probability; When the probability of a visit is greater than a preset first probability threshold, the second sensing data is input into the trained visitor identification model to obtain the corresponding visitor information. Identify multiple historical external activities corresponding to the visitor information in a pre-defined database; All the historical external activities and the weather characteristics are fused together to obtain the external activity characteristics corresponding to the outdoor area.

7. The home environment control method based on indoor and outdoor sensor data according to claim 6, characterized in that, The process of fusing all the historical external activities and the weather characteristics to obtain the external activity characteristics corresponding to the outdoor area includes: For each historical external activity, calculate the similarity between the weather data corresponding to that historical external activity and the weather characteristics; Filter out multiple historical external activities with a similarity greater than a preset threshold to obtain similar external activities; All similar external activities and their corresponding similarity scores are identified as external activity features corresponding to the outdoor area; the similar external activities include activity location, activity type, participants, and home appliances used in the activity.

8. The home environment control method based on indoor and outdoor sensor data according to claim 1, characterized in that, The step of determining the corresponding home appliance control strategy based on the residential activity characteristics and the external activity characteristics, using an association mapping model, includes: The residential activity features and the external activity features are input into a trained association vector prediction model to obtain the output association vector; the association vector prediction model is trained using a training dataset that includes multiple training residential activity features and training external activity features, as well as corresponding association degree labels. Based on the preset mapping relationship between association vectors and devices, determine multiple associated home devices corresponding to the association vectors; Set each of the aforementioned associated home devices to a pre-start standby state; For any number of the associated home devices, the device parameters of the associated home devices are matched in the historical control strategy database to obtain the corresponding device collaborative control combination; Determine the control command identifier corresponding to the device collaborative control combination; The control command identifier is set as the priority judgment identifier corresponding to the plurality of associated home devices, so that when the plurality of associated home devices receive an instruction that conforms to the control command identifier, they will be activated in advance to the device state corresponding to the device collaborative control combination.

9. A home environment control system based on indoor and outdoor sensor data, characterized in that, The system includes: The acquisition module is used to acquire first sensor data of the indoor area and second sensor data of the outdoor area; The first identification module is used to identify the residential activity characteristics corresponding to the indoor area based on the first sensing data. The second identification module is used to identify the external activity characteristics corresponding to the outdoor area based on the second sensing data. The determination module is used to determine the corresponding home device control strategy based on the residential activity characteristics and the external activity characteristics, using an association mapping model.

10. A home environment control system based on indoor and outdoor sensor data, characterized in that, The system 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 home environment control method based on indoor and outdoor sensor data as described in any one of claims 1-8.

Images