A method and system for regulating energy consumption

Abstract

The embodiments of this specification provide a method and system for regulating energy consumption. The method for regulating energy consumption includes obtaining first information and second information; determining a room status based on the first information; determining a resident's behavioral tendency based on the second information; generating an energy consumption control strategy based on the room status and the resident's behavioral tendency, and controlling the facilities in the room based on the energy consumption control strategy. The system for regulating energy consumption includes: an information acquisition module for obtaining first information and second information; a state determination module for determining a room status based on the first information; an action prediction module for determining a resident's behavioral tendency based on the second information; and a control module for generating a control strategy based on the room status and the resident's behavioral tendency, and controlling the facilities in the room based on the control strategy.

Description

Technical Field

[0001] This specification relates to the field of smart homes, and in particular to a method and system for regulating energy consumption. Background Art

[0002] The widespread adoption of smart homes has brought numerous conveniences to residents. However, during smart home use, especially when residents temporarily leave their rooms, running home appliances at full capacity for extended periods can lead to unnecessary energy consumption. Therefore, the workload should be appropriately reduced. However, if smart home operating modes are not adjusted before residents return to their rooms, the living experience can be compromised.

[0003] Therefore, there is a need for a method and system for regulating the working status and energy consumption of smart homes, so as to optimize the living experience of residents while saving energy. Summary of the Invention

[0004] One of the embodiments of this specification provides a method for regulating energy consumption, the method comprising: obtaining first information and second information; determining a room status based on the first information; determining a resident's behavioral tendency based on the second information; generating an energy consumption control strategy based on the room status and the resident's behavioral tendency, and controlling facilities in the room based on the energy consumption control strategy.

[0005] One of the embodiments of the present specification provides a system for regulating energy consumption, the system comprising: an information acquisition module for acquiring first information and second information; a state determination module for determining a room state based on the first information; an action prediction module for determining an action tendency of a resident based on the second information; and an energy consumption control module for generating an energy consumption control strategy based on the room state and the action tendency of the resident, and controlling facilities in the room based on the energy consumption control strategy.

[0006] One of the embodiments of this specification provides a processing device for adjusting energy consumption, including at least one storage medium and at least one processor; the at least one storage medium is used to store computer instructions; the at least one processor is used to execute the computer instructions to implement a method for adjusting energy consumption.

[0007] One embodiment of this specification provides a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method for adjusting energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0009] Figure 1 is a schematic diagram of an application scenario of an energy consumption adjustment system according to some embodiments of this specification;

[0010] Figure 2 is an exemplary flow chart of a method for adjusting energy consumption according to some embodiments of this specification;

[0011] Figure 3 is an exemplary flow chart of a method for determining action tendencies based on key images according to some embodiments of this specification;

[0012] Figure 4 is a schematic diagram of a method for obtaining a key image according to some embodiments of this specification;

[0013] Figure 5 is an exemplary flow chart of a method for controlling room facilities according to some embodiments of this specification;

[0014] Figure 6 is an exemplary flow chart of another method for controlling room facilities according to some embodiments of this specification;

[0015] Figure 7 is an exemplary module diagram of a system for regulating energy consumption according to some embodiments of this specification. DETAILED DESCRIPTION

[0016] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0017] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0018] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0019] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0020] Figure 1 This is a schematic diagram of an application scenario of the energy consumption adjustment system according to some embodiments of this specification. Figure 1 As shown, the application scenario 100 of the energy consumption regulation system may include a processor 110, a functional device 120, a storage device 130, a resident mobile terminal 140, and a network 150. The processor 110 may obtain information from the functional device 120, the resident mobile terminal 140, and the storage device 130 via the network 150, and the functional device 120 and the resident mobile terminal 140 may upload information to the storage device 130 via the network 150.

[0021] Processor 110 may process data and / or information obtained from other devices or system components. Based on this data, information, and / or processing results, the processor may execute program instructions to perform one or more functions described herein. For example, processor 110 may obtain connection status information of a resident mobile terminal 140. For another example, processor 110 may generate a control policy based on information obtained from functional device 120 and resident mobile terminal 140.

[0022] Functional device 120 may include a facility monitoring device within a room and a camera within an elevator, and may be used to obtain the first information and the second information. For example, functional device 120 may obtain status information of a smart home appliance and a resident's terminal within a room, and generate the first information based on this information. For another example, functional device 120 may obtain an image of a resident riding in an elevator, and generate the second information based on the image. Specifically, the image may be obtained by a camera within the elevator.

[0023] The storage device 130 can be used to store data and / or instructions. For example, the storage device 130 can store room status information and resident behavior tendency information, etc. For another example, the storage device 130 can store parameters of the first model and the second model. The storage device 130 may include one or more storage components, each of which may be an independent device or part of another device. In some embodiments, the storage device 130 may include random access memory (RAM), read-only memory (ROM), mass storage, removable memory, volatile read-write memory, etc., or any combination thereof. In some embodiments, the storage device 130 may be implemented on a cloud platform.

[0024] Resident mobile terminal 140 refers to one or more terminal devices used by a resident. In some embodiments, resident mobile terminal 140 can connect to a wireless network and generate connection status information. In some embodiments, connection status information may include network name, connection time, network signal strength, etc. In some embodiments, resident mobile terminal can generate work status information. In some embodiments, work status information may include the mobile terminal's work content, work duration, network bandwidth usage, etc. In some embodiments, user mobile terminal 140 can be one or any combination of other terminal devices with input and / or output functions, such as mobile device 140-1, tablet computer 140-2, laptop personal computer 140-3, etc.

[0025] The network 150 can connect the various components of the system and / or connect the system with external resources. The network 150 enables communication between the various components and with other parts outside the system, facilitating the exchange of data and / or information. In some embodiments, the network 150 can be any one or more of a wired network or a wireless network. The network connection between the various parts can be in one of the above-mentioned ways, or in multiple ways. In some embodiments, the network can be a point-to-point, shared, centralized, or other topological structure or a combination of multiple topological structures. In some embodiments, the network 150 can include one or more network access points. For example, the network 150 can include a wired or wireless network access point, such as a base station and / or a network exchange point, through which one or more components of the system can be connected to the network 150 to exchange data and / or information.

[0026] Figure 2 is an exemplary flow chart of a method for adjusting energy consumption according to some embodiments of this specification. Figure 2 As shown, the process 200 includes the following steps: In some embodiments, the process 200 may be executed by the processor 110 .

[0027] Step 210 , obtaining first information and second information. In some embodiments, step 210 may be performed by the information obtaining module 710 .

[0028] In some embodiments, the first information may include status information of the smart home in the room and status information of the resident's mobile terminal. The smart home status information may include the operating status of the facilities in the room, for example, whether the air conditioner or television is turned on. The status information of the resident's mobile terminal may include whether the resident's mobile phone, tablet, or computer is connected to the room's wireless network, and changes in the connection signal strength.

[0029] In some embodiments, the first information can be obtained by the smart home itself or related detection devices. For example, the smart home can record its own operating conditions and generate a log file. The smart home can send the log file to the information acquisition module 710 periodically or in response to an acquisition instruction, so that the information acquisition module 710 can extract the first information of the smart device from the log file. For another example, the connection status of a resident's mobile phone, tablet computer, or computer to the wireless network in the room can be obtained through related detection devices.

[0030] Secondary information can include information related to the user's movement trajectory or behavioral tendencies. For example, secondary information can include residents' registration information in various areas, such as hotel check-in information and epidemic investigation registration information. Another example is that secondary information can also include key images of residents in surveillance videos. Key images can refer to images or image sequences that contain the residents and can reflect the residents' behavioral tendencies.

[0031] In some embodiments, the key image may include an image frame or sequence of images associated with a resident pressing a floor button. For example, the key image may be an image of the user pressing an elevator floor button. For another example, the key image may be images of the elevator button before and after the user presses the corresponding elevator floor button.

[0032] In some embodiments, the second information can be obtained by processing monitoring data. For example, monitoring data can be obtained through a monitoring device such as a camera, and the information acquisition module 710 obtains key images of each resident from the monitoring data as the second information. For more information on determining the second information based on monitoring data, see Figure 4 and its related descriptions.

[0033] In some embodiments, the information acquisition module 710 can also access the server of relevant information to obtain second information, for example, obtaining the registration information of residents through the hotel's management system, or for example, obtaining the epidemic investigation registration information of residents through the epidemic investigation management system.

[0034] Step 220 , determining the room status based on the first information. In some embodiments, step 220 may be performed by the status determination module 720 .

[0035] A room can refer to a resident's residence or temporary residence. For example, a room can include a hotel room, a rented serviced apartment, or a long-term residence. It should be noted that a room does not simply refer to a unit in a residence; it can also refer to a residence or an entire building, depending on the needs. For example, if a resident lives in a single-family villa, the room in the embodiments of this specification can be understood to refer to the entire villa.

[0036] The room status may include information related to the living conditions of the occupants in the room or the working status of the facilities in the room, for example, whether the occupants are in the room, whether the facilities in the room are in working condition, and for example, if the facilities in the room are in working condition, the room status may include information related to the working parameters of the facilities.

[0037] In some embodiments, the state determination module 720 may process the first information to determine the room state. For example, it may directly extract some information from the first information as the room state. For another example, it may estimate the room state based on the correlation between various data in the first information. For example, data related to the environmental state and the equipment operating state in the first information may be directly used as the indoor environmental state and the facility operating state.

[0038] In some embodiments, the state determination module 720 can determine the state of the room based on a preset rule combined with the first information. The preset rule may include at least one prediction algorithm. After inputting part of the first information into the corresponding preset method, the corresponding room state can be determined by the prediction method. For example, the preset rule may be whether the facilities in the room are turned on. If the air conditioner or TV in the room is on, it is considered that there is someone in the room. For another example, the preset rule may be that when the resident's mobile terminal is connected to the wireless network in the room and the signal strength is stable, it is considered that there is someone in the room. In some embodiments, the preset rule may also include other content, such as whether the user's room card is inserted into the designated position, etc., which can be determined according to the actual situation.

[0039] Step 230 : Determine the resident's behavioral tendency based on the second information. In some embodiments, step 230 may be performed by the behavioral prediction module 730 .

[0040] A resident may refer to a person who resides or temporarily resides in a room. For example, a resident may include a hotel resident, a temporary visitor to a hotel resident, or a resident of a residence. In some embodiments, the correspondence between a resident and a room may be determined by registration. For example, when a resident checks into a hotel room, they may register their identity at the front desk, thereby establishing a correspondence between the resident and the room. The resident may be identified by a relevant identification code (such as a citizen ID number) and / or feature information (such as facial image features), and the room may be identified by a relevant identification code (such as a room number) and / or feature information (such as the location of a room door in corridor monitoring).

[0041] The action tendency may reflect the resident's actions relative to the room or possible future actions. For example, the action tendency may include leaving the room or returning to the room. In some embodiments, the action tendency may also include the duration of time the resident is away from the room. For example, the resident's action tendency may be that the user leaves the room and returns to the room approximately 6 hours after leaving the room.

[0042] In some embodiments, the relationship between the resident and the room can also be adjusted based on the duration. For example, after the resident checks out, it can be assumed that the resident's behavior of leaving the room will continue, and the relationship between the resident and the room can be terminated.

[0043] In some embodiments, the duration of a resident's absence can be estimated based on the resident's destination and related information. For example, if the resident's destination is the living room, then the resident may be going there to meet a guest. The duration of this activity can be estimated based on the resident's scheduled living room usage time and / or the resident's historical visitor times, thereby estimating the duration of the user's absence. For another example, if the resident's destination also includes a room, the duration of this process can refer to the travel time from the user's current location to the room.

[0044] In some embodiments, the action prediction module 730 can predict the action tendency of the resident based on the second information. For more information on predicting the action tendency of the resident, please refer to Figure 3 and its related descriptions.

[0045] Step 240 : Generate a control strategy based on the room status and the resident's behavioral tendency and control the facilities in the room based on the control strategy. In some embodiments, step 240 may be performed by the control module 740 .

[0046] The control strategy may include control instructions for the facilities in the room, which are used to control the working status and / or working parameters of the facilities in the room. In some embodiments, the control strategy may also be referred to as an energy consumption control strategy.

[0047] In some embodiments, the control strategy may be determined by the control module 740 and sent to the corresponding facilities so that the corresponding facilities adjust the working status and / or working parameters in response to the control instructions.

[0048] In some embodiments, the control policy may include a control policy for the smart thermostat, and the smart thermostat may adjust its energy consumption in response to the control policy. For example, the control policy may include a standby instruction for the smart thermostat after a resident leaves the room. In response to the standby instruction, the smart thermostat may adjust its operating state to a standby state to reduce its power consumption. For another example, the control policy may include a temperature adjustment instruction for the smart thermostat after a resident returns to the room. In response to the temperature adjustment instruction, the smart thermostat may enter an operating state according to preset parameters to control the room temperature.

[0049] In some embodiments, a control strategy that satisfies resident needs and minimizes energy consumption can be determined based on the room status and the resident's behavioral tendencies. In some embodiments, resident needs can include room energy consumption control requirements in multiple situations, where multiple situations can be related to the resident's behavioral tendencies. For example, multiple situations can include different behavioral tendencies such as the user leaving the room, the user returning to the room, etc. For more information on control strategies and their determination in multiple situations, please refer to Figure 5 、 Figure 6 and its related descriptions.

[0050] It should be noted that the above description of process 200 is for illustration and explanation only and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 200 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification. For example, the method for obtaining the first information and the method for obtaining the second information in step 210 can be independently executed as needed. For another example, the related methods of determining the room status in step 220 and determining the resident's action tendency in step 230 can also be executed according to actual needs. For example, when the monitoring device detects a resident, step 230 can be triggered to determine the resident's action tendency.

[0051] Based on the method of adjusting energy consumption provided in some embodiments of this specification, the control strategy for the facilities in the room can be determined based on the room status and the resident's behavioral tendencies, so as to intelligently control the facilities in the room to maintain low energy consumption while meeting the user's usage needs, avoiding unnecessary energy consumption.

[0052] Figure 3 FIG. 1 is an exemplary flow chart of a method for determining action tendency based on key images according to some embodiments of this specification. Figure 3 As shown, the process 300 includes the following steps: In some embodiments, the process 300 may be executed by the processor 110 .

[0053] Step 310 , determining a key image from the elevator monitoring data. In some embodiments, step 310 may be performed by the information acquisition module 710 .

[0054] Elevator monitoring data may refer to video captured by monitoring equipment installed in an elevator in the building where the room is located. The elevator monitoring video may record the entry and exit of each passenger in the elevator and the floor selection.

[0055] A key image can refer to one or more key frames in elevator monitoring data that reflect a resident's destination. For example, a key image can include an image of a resident exiting an elevator, including the floor the elevator was on at the time of exit. Another example is an image of a resident pressing an elevator floor button. Based on this image, the resident's selection of the desired floor in the elevator can be obtained.

[0056] In some embodiments, the information acquisition module 710 can extract relevant images or image sequences related to the resident's behavioral tendencies from the elevator monitoring data as key images. In some embodiments, the behavior prediction module 730 can retrieve the key images from the information acquisition module 710 when executing step 310.

[0057] In some embodiments, the information acquisition module 710 can process the elevator monitoring data through the model to determine the key image. For more information about determining the key image through the model, see Figure 4 and its related descriptions.

[0058] In some embodiments, a mirror can be installed in the elevator. When acquiring elevator monitoring data, the camera can use the mirror's reflection to obtain a comparison image of the resident before and after pressing the button. This can avoid the situation where the elevator button panel is blocked when there are many people in the elevator, thus preventing the relevant image from being captured.

[0059] Step 320 : Determine the resident's destination floor based on the key image. In some embodiments, step 320 may be performed by the action prediction module 730 .

[0060] The destination floor may be the floor that the resident wants to reach. For example, the destination floor may be the floor that the resident selects by pressing an elevator button. For another example, the destination floor may be the floor that the resident is at when the elevator gets off.

[0061] In some embodiments, the floor corresponding to the elevator button pressed by the resident and / or the floor where the elevator was when the resident left can be determined based on the key image as the resident's destination floor.

[0062] In some embodiments, the action prediction module 730 can determine the key moment when a resident presses a floor button after entering the elevator based on the key image, and obtain the triggered floor corresponding to the key moment from the elevator signal. The elevator signal can refer to the control information generated by the elevator in response to a passenger's interaction (such as pressing an elevator button), which can be transmitted to the elevator control unit.

[0063] In some embodiments, the action prediction module 730 can obtain the button signal pressed by the user at the critical moment from the elevator control unit. The signal includes the floor corresponding to the button. When the action prediction module 730 determines that the passenger who triggered the elevator signal is the aforementioned resident based on the key image, the elevator signal at the critical moment corresponding to the key image can be obtained, and the resident's destination floor can be determined through the elevator signal.

[0064] In some embodiments, the action prediction module 730 can also determine the resident's destination floor based on the elevator signal combined with resident identification information. This resident identification information can include identification information from the resident's room card (such as a hotel room card, access card, etc.). To ensure resident safety and identify resident permissions, when using the elevator, the resident can first place the resident's room card in the corresponding card reader position in the elevator so that the elevator can recognize the room card information. After the elevator recognizes the room card information, the resident can press the elevator button. Accordingly, the action prediction module 730 can determine the resident and the resident's destination floor based on the room card information in the elevator signal and the triggered floor.

[0065] In some embodiments, the action prediction module 730 can also obtain images of the elevator buttons before and after the critical moment, use the image before the critical moment as the first target image, and use the image after the critical moment as the second target image. By comparing the first target image and the second target image, the triggered floor and then the resident's destination floor are determined.

[0066] In some embodiments, the action prediction module 730 may determine the first target image and the second target image based on a preset time interval. For example, if the preset time interval is 3 seconds, the first target image is a continuous image 3 seconds before the critical moment, and the second target image is a continuous image 3 seconds after the critical moment.

[0067] In some embodiments, the action prediction module 730 may determine the first target image and the second target image based on a preset frame interval. For example, if the preset frame interval is 100 frames, the first target image is the continuous image of 100 frames before the critical moment, and the second target image is the continuous image of 100 frames after the critical moment.

[0068] In some embodiments, a machine learning model can be used to process the first and second target images to determine the triggered floor. For example, a convolutional neural network-based image recognition algorithm can be used to identify the elevator button that changed after a critical moment, and the triggered floor corresponding to that elevator button can be used as the resident's destination floor. For another example, an image recognition algorithm can be used to determine the floor the elevator was on when the resident exited the elevator as the destination floor.

[0069] In some embodiments, the action prediction module 730 can obtain the floor number corresponding to each preset position of the elevator button and determine the triggered floor based on the pixel difference between the areas corresponding to each preset position in the first target image and the second target image. For example, the monitoring equipment in the elevator can obtain elevator monitoring data with a fixed field of view at a fixed angle. The preset position can be the location of each elevator button in the fixed field of view. When a resident presses an elevator button, the corresponding elevator button can present different states (such as color, brightness, lighting, etc.) in response to the resident's operation. The preset position that has changed can be determined by comparing the pixel difference between each preset position in the elevator monitoring data before and after the critical moment, thereby determining the elevator button pressed by the resident. The triggered floor is then determined as the destination floor based on the correspondence between the elevator button and the floor.

[0070] In some embodiments, when the pixel difference of a certain preset area is greater than a difference threshold, it can be determined that the preset area has changed, and the floor corresponding to the preset area is used as the triggered floor.

[0071] Pixel difference may refer to the difference between the pixels constituting each preset area before and after the critical moment. Pixels may refer to the basic constituent units of an image, and each pixel may include a color value, which is generally at least one value in the range [0, 255]. For example, an RGB type pixel may include a red color value, a green color value, and a blue color value. For another example, a grayscale type pixel may include a grayscale value. In some embodiments, the difference between two pixels may be evaluated by the vector distance formed by the color values. For example, the difference between the two pixels may be determined based on the Euclidean distance of the color values ​​of the two pixels.

[0072] In some embodiments, the difference between two pixels can be converted into a grayscale value and the grayscale value difference can be calculated by a preset algorithm. For example, the preset algorithm can be Gray = R×0.3+G×0.59+B×0.11, where Gray is the grayscale value, and R, G, and B are the values ​​of the three color channels respectively. Exemplarily, the RGB value of a pixel is (254, 100, 76), then Gray(254, 100, 76) = 254×0.3+100×0.59+76×0.11 = 144. The pixel difference between the preset areas can be determined by the statistical value of the pixel difference corresponding to each position in the two preset areas.

[0073] In some embodiments, the pixel difference between the preset areas can be described by statistical indicators such as the sum of the pixel differences between the preset areas and the mean square error.

[0074] Step 330 : Determine the resident's behavioral tendency based on the resident's destination floor. In some embodiments, step 330 may be performed by the behavioral prediction module 730 .

[0075] In some embodiments, different functional areas are set up on different floors of the building where the room is located, and the resident's behavioral tendencies can be determined based on the floor the resident is traveling to in the elevator. For example, the functional area set up on the floor can be determined based on the destination floor the resident is traveling to, and then the resident's behavior destination, behavior duration, etc. can be estimated based on the functional area. For example, the 6th floor of the building where the room is located may include functional areas such as a living room and a library. After the resident leaves the room, the monitoring equipment in the elevator can be used to determine that the resident is traveling to the 6th floor by elevator. Then, based on the resident's behavioral habits or the average behavior duration in the area, it can be estimated that the resident is likely to go to the living room on the 6th floor and the resident's stay time on the 6th floor as the behavior destination and behavior duration.

[0076] Based on the key image-based behavior propensity determination method described in some embodiments of this specification, a resident's behavior propensity can be estimated based on their elevator destination floor. This improves the accuracy of the resident's behavior propensity estimation, thereby improving the accuracy of the energy consumption adjustment method provided in this specification.

[0077] Figure 4 is a schematic diagram illustrating a method for obtaining a key image according to some embodiments of this specification. As shown in the figure, in some embodiments, processor 110 may determine a key image containing a resident using a first model and a second model based on elevator monitoring data acquired by elevator monitoring equipment. In some embodiments, method 400 for obtaining a key image may include at least the following:

[0078] In some embodiments, the information acquisition module 710 may determine the key image through the first model 410 and the second model 420 .

[0079] In some embodiments, the first model 410 can identify elevator surveillance data and determine video segments containing residents. For example, the first model can determine passenger characteristics (e.g., passenger facial images) of passengers contained in each video segment in the elevator surveillance data. The first model can then compare the passenger characteristics with the resident's reserved characteristics (e.g., facial images of the resident recorded in the room or during registration) to determine whether each video segment contains the resident. If a video segment contains the resident, the video segment containing the resident is output.

[0080] In some embodiments, the input of the first model may include elevator monitoring data, and the output may be a video clip containing the resident. In some embodiments, the first model may be a Convolutional Neural Networks (CNN) model.

[0081] In some embodiments, the second model 420 can classify each frame of a video clip containing a resident to determine a key image. For example, the second model 420 can identify a resident's interaction with an elevator button. When a resident interacts with an elevator button in a video (e.g., presses the button), that image is used as a key image. Identifying the interaction between a resident and an elevator button can be achieved using related algorithms, such as behavior recognition algorithms and target recognition algorithms. For example, the second model 420 can monitor the distance between a resident's hand and an elevator button in real time. When that distance is less than a preset threshold, the resident can be deemed to have performed the button-pressing interaction.

[0082] In some embodiments, the input of the second model may include a video clip containing the resident, and the output may include the key image. In some embodiments, the second model may be a Convolutional Neural Networks (CNN) model.

[0083] In some embodiments, the output of the first model can be used as the input of the second model, and the first model 410 and the second model 420 can be jointly trained. In some embodiments, the abnormality judgment model can be obtained by jointly training the feature determination layer and the result judgment layer.

[0084] In some embodiments, the training sample may include at least historical elevator monitoring data. In some embodiments, the training sample may be obtained through the storage device 130 or through the information acquisition module 710 .

[0085] In some embodiments, the training labels may be historical key images. In some embodiments, the historical key images may be obtained from historical data of the information acquisition module 710, may be obtained through manual annotation, or may be obtained through a network call from a storage device, depending on actual needs.

[0086] In some embodiments, historical elevator monitoring data can be input into an initial first model to obtain historical video clips containing residents. Historical video clips containing residents can also be input into an initial second model to obtain historical key images. A loss function is constructed based on the output of the second model and the trained labels. The parameters of the first and second models are then iteratively updated based on the loss function. Model training is completed when the loss function meets preset conditions, such as convergence of the loss function or a threshold number of iterations. After training is complete, the parameters of both the first and second models can be determined.

[0087] Obtaining the parameters of the first model and the second model through the above training method can, in some cases, solve the problem of difficulty in obtaining labels when training the first model alone, which is conducive to more accurate acquisition of key images.

[0088] In some embodiments of this specification, by determining key images in elevator monitoring data through the first model and the second model, video clips of residents interacting with elevator buttons in the elevator can be accurately determined, thereby avoiding interference of other behaviors of residents in the elevator on the recognition results, improving the accuracy of determining the destination floor, and thus facilitating more accurate judgment of the user's behavioral tendencies.

[0089] Figure 5 FIG. 1 is an exemplary flow chart of a method for controlling room facilities according to some embodiments of this specification. Figure 5 As shown, the process 500 may include the following steps. In some embodiments, the process 500 may be executed by the processor 110.

[0090] Step 510 : When the room is in an unoccupied state and the room facilities are turned off, determine whether the resident's action tendency is to go to the room. In some embodiments, step 510 may be performed by the action prediction module 730 .

[0091] In some embodiments, the second information can be used to determine whether the resident's action tendency is to go to the room. For example, when a user presses the button for the floor where the room is located in an elevator, it can be determined that the user's action tendency is to go to the room. For details on determining the user's action tendency, please refer to Figure 3 and its related descriptions.

[0092] In step 520 , in response to the resident going to the room, generating a first control strategy. In some embodiments, step 520 may be performed by the control module 740 .

[0093] The first control strategy may include a strategy for controlling the operating state of facilities in the room and corresponding operating parameters. In some embodiments, the first control strategy may include a strategy for controlling the temperature control device in the room. For example, the first control strategy may be "turn on the room air conditioner and set the temperature to 26°C."

[0094] In some embodiments, the control module 740 may send the first control strategy to the facilities in the room, so that the corresponding room facilities start to operate according to the parameters of the first control strategy.

[0095] In some embodiments, the first control strategy can be determined based on the resident's historical usage data of in-room facilities. For example, the control module 740 can record the operating status of each device in the room before the resident leaves. Upon the user's return, the recorded operating status of each device can be compared with the current operating status. Based on the comparison results, the first control strategy is generated to determine which facilities need to be enabled.

[0096] In some embodiments, the control module 740 can also determine a first control strategy based on the resident's behavioral habits. Specifically, the control module 740 can first obtain the resident's behavioral habits, then determine the operating parameters of various room facilities while the resident is in the room based on these habits. Finally, the control strategy is generated based on the operating parameters. For example, if a resident habitually turns on the bathing equipment for a shower upon returning to the room in the afternoon, the corresponding first control strategy may include the bathing equipment and the resident's habitual operating parameters.

[0097] In some embodiments, a resident's behavioral habits can be determined based on the resident's historical first data and historical second data. The historical first data and historical second data may refer to the collection of all first data and second data about the resident acquired by the information acquisition module 710 after the resident registers (e.g., checking into a room at a hotel front desk). For example, the historical second data can be used to determine that the resident typically returns to their room at 6:00 PM. For another example, the historical first data can be used to determine the resident's preferred indoor temperature, preferred indoor ventilation method, and so on.

[0098] In some embodiments, the operating parameters of the equipment in the first control strategy can be determined based on the resident's behavioral habits. For example, the resident's accustomed air conditioning operating mode, air conditioning temperature, wind speed, etc. can be determined based on the historical first data to determine the air conditioning operating parameters.

[0099] Step 530: Control facilities in the room based on the first control strategy.

[0100] In some embodiments, the facilities in the room can respond to the received first control policy by adjusting their operating states and operating parameters according to the first control policy. For example, a device in standby mode can be powered on and then set to the device parameters according to the first control policy. A device in shutdown mode can be powered on and then set to the device parameters according to the first control policy.

[0101] In some embodiments, the execution mode of the first control strategy can also be determined based on the time when the resident returns to the room. The time of the resident's return can be determined by detecting the time the resident returns to the room and the duration of the journey using the second information. In some embodiments, the time it takes for the equipment to reach the resident's usual indoor parameters after operation can be determined based on the resident's habits, and preemptive control can be implemented based on this time. For example, resident habits can include the resident's usual indoor temperature. When executing the first control strategy, the preemptive control time can be determined based on the current indoor temperature, the resident's usual indoor temperature, and the air conditioner's power consumption, and preemptive control of the indoor air conditioner can be implemented based on this time.

[0102] In some embodiments, whether to generate a control strategy or whether to execute a control strategy can be determined based on the total confidence level. Specifically, when the total confidence level is higher than a threshold, the control strategy can be generated and executed; when the total confidence level is lower than a threshold, the control strategy may not be generated or executed. The control strategy may include a first control strategy, a second control strategy, and other control strategies. In some embodiments, when the total confidence level of the first control strategy (also referred to as a first indicator) is lower than a threshold, a control instruction for controlling the indoor device to be in energy-saving mode may be generated.

[0103] In some embodiments, the overall confidence level may be determined based on the clarity of the key image, the confidence level of the first model in the key image acquisition model, and the confidence level of the second model.

[0104] The clarity of a key image refers to the clarity of the detailed textures and boundaries of the key image. For example, the clarity of a key image may refer to the image resolution of a resident and an elevator button in the key image. Another example may refer to the clarity of the outlines of a resident and an elevator button in the key image. In some embodiments, the clarity of a key image may be determined using a clarity evaluation method. For example, the clarity of a key image may be determined using operators such as the Tenengrad gradient function and the Laplacian gradient function.

[0105] The confidence level of a model, such as the confidence level of the first model and the confidence level of the second model in the key image acquisition model, can refer to the degree of trustworthiness of the model output. In some embodiments, the confidence level of a model can be determined based on the consistency between the model's output results for a test sample and the test label. For example, if the output results of 95% of the test data in a trained model are consistent with the test label, the model confidence level can be 95%. In some embodiments, the confidence level of a model can also be determined by determining whether the model input and output are consistent with the training data.

[0106] In some embodiments, the first indicator may be determined by weighting the clarity of the key image, the confidence of the first model in the key image acquisition model, and the confidence of the second model. For example, the calculation formula of the first indicator may be:

[0107] C=aD+bZ1+dZ2+e

[0108] Among them, C is the first indicator value, D is the key image clarity, Z1 and Z2 are the confidence of the first model and the second model in the key image acquisition model respectively, and a, b, d, and e can be preset constants.

[0109] Based on the energy consumption adjustment method provided in some embodiments of this specification, a first control strategy can be determined based on the resident's tendency to return to the room, so that when the resident returns to the room, the indoor equipment is in the working state that the user is accustomed to, thereby improving the resident's living experience.

[0110] Figure 6 FIG. 1 is an exemplary flow chart of another method for controlling room facilities according to some embodiments of this specification. Figure 6 As shown, the process 600 includes the following steps. In some embodiments, the process 600 may be executed by the processor 110.

[0111] Step 610: When the room is in an unoccupied state and the room facilities are turned on, determine the resident's action tendency; in response to the resident's action tendency being to leave the room, predict the resident's absence duration.

[0112] In some embodiments, the duration of a resident's absence can be determined by an infrared sensor. In some embodiments, the infrared sensor is positioned high within the room and can sense infrared radiation from a human body anywhere within the room. The presence of a resident in the room is determined based on whether or not infrared radiation from a human body is sensed. The infrared sensor can also record the time a human body is sensed and the time a human body is not sensed. The time a human body is sensed represents the time the resident enters the room, while the time a human body is not sensed represents the time the resident leaves the room.

[0113] In some embodiments, when a resident leaves a room, it is determined whether the resident's action intention is to "check out." In some embodiments, this determination can be based on check-out records at the front desk. In some embodiments, the preset duration for "check out" can be set to infinite.

[0114] In some embodiments, in response to the resident's action tendency not being "checking out", the resident's departure duration can be predicted based on the resident's action tendency type. For example, the duration corresponding to "eating breakfast" can be preset to 20 minutes. When the resident's action tendency type is "eating breakfast", the predicted departure duration of the resident is 20 minutes. For another example, the duration corresponding to "going to the gym" can be preset to 80 minutes. When the resident's action tendency type is "going to the gym", the predicted departure duration of the resident is 80 minutes. For details on the definition and determination method of the resident's action tendency type, see Figure 2 and Figure 3 The corresponding descriptions will not be repeated here.

[0115] In some embodiments, the preset duration can be adjusted based on the status of the user's mobile terminal. In some embodiments, the status of the user's mobile terminal can include the connection status between the resident's mobile terminal and the wireless network in the room. In some embodiments, it can be determined whether the connection status between the resident's mobile terminal and the wireless network in the room is connected and whether the signal is stable. If the connection signal is stable, it indicates that the resident is close to the room and is likely to return to the room soon. In this case, the preset duration corresponding to all action tendency types can be reduced.

[0116] In some embodiments, the type of the resident's mobile terminal can be determined based on the connection characteristics between the resident's mobile terminal and the wireless network in the room, and the adjustment amount of the preset duration can be determined based on the type of the resident's mobile terminal. In some embodiments, the connection characteristics between the resident's mobile terminal and the wireless network in the room can include the name, serial number, IP address, etc. of the terminal connected to the network.

[0117] In some embodiments, the adjustment range may refer to a ratio adjusted based on the preset duration. In some embodiments, the adjustment range may also be preset. For example, the adjustment range may be preset to 10%, meaning that the adjusted preset duration is 90% of the original preset duration.

[0118] In some embodiments, in response to determining that the type of the resident's mobile terminal is a mobile phone, the adjustment range of the preset duration can be increased. For example, when the type of the resident's mobile terminal is determined to be a mobile phone, since the range of a mobile phone's connection to the network is limited, the phone's status cannot be detected if the resident moves beyond a certain distance with the phone. Therefore, if the status of the resident's mobile terminal can be obtained and the mobile terminal is determined to be a mobile phone, it can be preliminarily determined that the user has not left the room very far and is likely to return to the room soon. Therefore, the adjustment range can be increased, such as increasing the adjustment range to 15%, and the preset duration can be adjusted to 85% of the original preset duration.

[0119] The preset duration is adjusted based on the status and type of the resident's mobile terminal. The preset duration can be flexibly adjusted according to the actual situation of the resident to better adapt to the current habits of the resident, thereby better determining the control strategy for the facilities in the room.

[0120] Step 620: Generate a second control strategy based on the resident's absence duration.

[0121] In some embodiments, the second control policy may include control instructions for various facilities within the room. In some embodiments, the control instructions may include instructions regarding the operating status of the facilities within the room and whether operating parameters require adjustment. In some embodiments, the second control policy may include a policy for controlling the temperature control device within the room. For example, the second control policy may be "turn on the room air conditioner after 90 minutes and set the temperature to 26°C."

[0122] In some embodiments, a second energy consumption control policy can be determined based on the time range of the resident's absence. In some embodiments, the time range can be categorized as short, long, or permanent. In some embodiments, a time threshold can be set to determine whether the resident's absence is short or long. For example, the time threshold can be set to 30 minutes, where short can refer to a time period of less than 30 minutes, long can refer to a time period of more than 30 minutes, and permanent can refer to the time period after the resident has checked out. In some embodiments, if the resident's absence is short, the corresponding second policy is to not change the current operating status of the in-room facilities. In some embodiments, if the resident's absence is long, the corresponding second policy is to issue a standby command to the in-room facilities, and to determine the time at which the facilities will be turned back on based on the duration of the resident's absence. In some embodiments, if the resident's absence is permanent, the corresponding second control policy is to issue a shutdown command to the in-room facilities.

[0123] In some embodiments, the second control strategy may also include other control schemes, which may be determined based on actual needs.

[0124] Step 630: Control the facilities in the room based on the second control strategy.

[0125] In some embodiments, the control module 740 can issue control instructions to the facilities in the room based on the second control strategy. The facilities in the room perform corresponding operations based on the control instructions. For example, upon receiving a temperature increase instruction, the intelligent thermostat switches to a temperature increase mode, raising the room temperature. Another example is when receiving a power-on instruction, the intelligent audio-visual device turns on.

[0126] In some embodiments, staff can be notified based on the second control policy. In some embodiments, upon receiving the notification, staff can enter the room to manually control in-room facilities or perform other tasks within the room. In some embodiments, the staff may be a cleaning staff member. For example, if a resident's absence duration is set to permanent, the corresponding second control policy may include issuing a shutdown command for in-room facilities and notifying the cleaning staff. Furthermore, upon receiving the notification, the cleaning staff can enter the room to perform sanitation and cleaning tasks.

[0127] In some embodiments of this specification, the duration of a resident's absence is predicted based on the resident's behavioral tendencies, and the working status and energy consumption of the facilities in the room are regulated. At the same time, an adjustment strategy is determined based on the connection status of the resident's mobile device, thereby achieving the purpose of intelligent regulation of the energy consumption of the facilities in the room.

[0128] Figure 7 7 is an exemplary block diagram of a system for regulating energy consumption according to some embodiments of this specification. In some embodiments, the system 700 for regulating energy consumption may include an information acquisition module 710 , a state determination module 720 , an action prediction module 730 , and a control module 740 .

[0129] In some embodiments, the information acquisition module 710 can be used to acquire first information and second information. In some embodiments, the first information may include status information of the smart home in the room and status information of the resident's mobile terminal. In some embodiments, the second information may include key images related to the resident.

[0130] In some embodiments, the state determination module 720 may be configured to determine the state of the room according to the first information.

[0131] In some embodiments, the action prediction module 730 may be configured to determine the resident's action tendency based on the second information. In some embodiments, the action prediction module 730 may determine the resident's destination floor based on the key image, and determine the resident's action tendency based on the resident's destination floor.

[0132] In some embodiments, the control module 740 can be configured to generate an energy consumption control strategy based on the room status and the resident's behavioral tendencies and control the facilities in the room based on the energy consumption control strategy. In some embodiments, when the room status is unoccupied and the room facilities are turned off, the control module 740 generates a first control strategy in response to the resident's behavioral tendencies being to move toward the room, and controls the facilities in the room based on the first control strategy. In some embodiments, when the room status is unoccupied and the room facilities are turned on, the control module 740 predicts the resident's absence duration in response to the resident's behavioral tendencies being to leave the room, generates a second control strategy based on the absence duration, and controls the facilities in the room based on the second control strategy.

[0133] It should be noted that the above description of the information acquisition module, state determination module, action prediction module and control module is for convenience only and does not limit this specification to the scope of the embodiments. It is understandable that those skilled in the art, after understanding the principles of the system, may arbitrarily combine the modules or form subsystems connected with other modules without deviating from the principles. In some embodiments, Figure 7 The information acquisition module, state determination module, action prediction module, and control module disclosed herein may be separate modules within a single system, or a single module may implement the functions of two or more of the aforementioned modules. For example, each module may share a storage module, or each module may have its own storage module. Such variations are within the scope of protection of this specification.

[0134] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

[0135] This specification also uses specific terms to describe the embodiments of this specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0136] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the spirit and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0137] Similarly, it should be noted that, in order to simplify the presentation of this specification and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this specification sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this specification requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single disclosed embodiment.

[0138] In some embodiments, numbers are used to describe the quantity of components and attributes. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may change according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0139] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, and documents, cited in this specification is hereby incorporated by reference in its entirety. This includes application history documents that are inconsistent with or conflict with the content of this specification, as well as documents (currently or subsequently attached to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if the descriptions, definitions, and / or terminology used in the accompanying materials are inconsistent or conflicting with the content of this specification, the descriptions, definitions, and / or terminology used in this specification will control.

[0140] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. A method for regulating energy consumption, characterized in that: The method comprises: Acquiring first information and second information; the first information includes status information of the smart home in the room and status information of the resident's mobile terminal, and the second information includes a key image related to the resident; the key image refers to one or more key frames in the elevator monitoring data that reflect the resident's whereabouts; acquiring the key image includes: Identifying the elevator monitoring data based on the first model to determine a video segment containing the resident; classifying each frame of the video clip containing the resident based on the second model to determine the key image; determining a room state according to the first information; Determining the resident's action tendency based on the second information includes: determining, based on the key image, a key moment when the resident presses a floor button after entering the elevator; Get images of the elevator buttons before and after the critical moment; Processing images of elevator buttons before and after the critical moment using a machine learning model to determine the triggered floor and, in turn, the resident's destination floor; Determining the resident's movement tendency based on the resident's destination floor; and A control strategy is generated based on the room status and the resident's behavioral tendency, and facilities in the room are controlled based on the control strategy.

2. The method according to claim 1, characterized in that Generating a control strategy based on the room state and the resident's behavioral tendency, and controlling facilities in the room based on the control strategy, including: When the room is in an unoccupied state and facilities in the room are turned off, determining the resident's behavioral tendency; In response to the resident's action tendency being to go to the room, a first control strategy is generated, and facilities in the room are controlled based on the first control strategy.

3. The method according to claim 1, characterized in that Generating a control strategy based on the room state and the resident's behavioral tendency, and controlling facilities in the room based on the control strategy, including: When the room is in an unoccupied state and the facilities in the room are turned on, determining the resident's action tendency; In response to the resident's action tendency being to leave the room, predicting the resident's absence duration based on the resident's action tendency type; Adjusting the absence duration based on status information of the resident mobile terminal, wherein the status information of the resident mobile terminal includes a connection status between the resident mobile terminal and a wireless network in the room; In response to the connection status between the resident mobile terminal and the wireless network in the room being connected and the signal being stable, reducing the absence duration corresponding to all the action tendency types; A second control strategy is generated based on the absence duration, and facilities in the room are controlled based on the second control strategy.

4. A system for regulating energy consumption, characterized in that: The system comprises: an information acquisition module, configured to acquire first information and second information; the first information including status information of the smart home in the room and status information of the resident's mobile terminal; and the second information including key images related to the resident; the key images being one or more key frames in the elevator monitoring data reflecting the resident's whereabouts; The information acquisition module is further used to: Identifying the elevator monitoring data based on the first model to determine a video segment containing the resident; classifying each frame of the video clip containing the resident based on the second model to determine the key image; a state determination module, configured to determine a room state according to the first information; an action prediction module, configured to determine the action tendency of the resident based on the second information; The action prediction module is further configured to: determining, based on the key image, a key moment when the resident presses a floor button after entering the elevator; Get images of the elevator buttons before and after the critical moment; Processing images of elevator buttons before and after the critical moment using a machine learning model to determine the triggered floor and, in turn, the resident's destination floor; Determining the resident's movement tendency based on the resident's destination floor; and A control module is used to generate a control strategy based on the state of the room and the action tendency of the resident, and control the facilities in the room based on the control strategy.

5. The system according to claim 4, characterized in that The control module is further configured to: When the room is in an unoccupied state and the facilities in the room are turned off, determining whether the resident's action tendency is to go to the room; In response to the resident's action tendency being to go to the room, a first control strategy is generated, and facilities in the room are controlled based on the first control strategy.

6. The system according to claim 4, characterized in that The control module is further configured to: When the room is in an unoccupied state and the facilities in the room are turned on, determining the resident's behavioral tendency; In response to the resident's action tendency being to leave the room, predicting the resident's absence duration based on the resident's action tendency type; Adjusting the absence duration based on status information of the resident mobile terminal, wherein the status information of the resident mobile terminal includes a connection status between the resident mobile terminal and a wireless network in the room; In response to the connection status between the resident mobile terminal and the wireless network in the room being connected and the signal being stable, reducing the absence duration corresponding to all the action tendency types; A second control strategy is generated based on the absence duration, and facilities in the room are controlled based on the second control strategy.

7. A processing device for adjusting energy consumption, comprising a processor, wherein the processor is configured to execute the method for adjusting energy consumption according to any one of claims 1 to 3.

8. A computer-readable storage medium storing computer instructions, wherein when a computer reads the computer instructions in the storage medium, the computer executes the method for adjusting energy consumption according to any one of claims 1 to 3.

Images