Office environment intelligent adjustment method and device, edge device and storage medium
By combining edge devices with cloud servers and using sensors to collect data for real-time adjustments, the problem of traditional office environment adjustment systems being unable to dynamically adjust has been solved, enabling personalized adaptive adjustment of the office environment and improving the user experience.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-26
- Publication Date
- 2026-04-03
AI Technical Summary
Traditional office environment control systems cannot dynamically adjust according to the actual situation of users and the environment, and cannot meet personalized needs.
By combining edge devices with cloud servers, user behavior and environmental data are collected using sensors, and personalized models are used for real-time adjustments, including state prediction and adaptive adjustment.
It enables adaptive and intelligent adjustment of the office environment, meeting personalized needs and improving user experience.
Smart Images
Figure CN121787825A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of artificial intelligence technology, and in particular to intelligent adjustment methods, devices, edge devices, and storage media for office environments. Background Technology
[0002] Traditional office environment control systems typically use fixed environmental parameters or simple rules for adjustment, which cannot meet the personalized needs of different users.
[0003] In existing technologies, some intelligent office systems can record user preferences and then adjust the office environment for different users based on the corresponding preference data to meet their individual needs. However, existing technologies can only store static parameters and cannot dynamically adjust the equipment according to the actual situation of the user and the environment. Summary of the Invention
[0004] This application provides a method, apparatus, edge device, and storage medium for intelligent adjustment of the office environment. The intelligent device can be dynamically adjusted according to the actual situation of the user and the environment to achieve adaptive intelligent adjustment of the office environment.
[0005] In a first aspect, embodiments of this application provide an intelligent adjustment method for an office environment, applied to a target edge device in an intelligent adjustment system for an office environment. The intelligent adjustment system includes a cloud server and multiple edge devices, which are connected to multiple different types of sensor devices and intelligent devices. The method includes: Obtain the workstation usage instruction triggered by the target user for the target edge device. The workstation usage instruction includes an employee key and an employee identifier. The target edge device is installed at the target workstation. The target encrypted data corresponding to the employee identifier is obtained from the cloud server, and the target encrypted data is decrypted using the employee key to obtain the habit parameters and personalized model. The smart device corresponding to the target edge device is initialized and adjusted based on the aforementioned habit parameters; User behavior data and environmental data corresponding to the target workstation are collected by multiple target sensor devices, and device status data of the target intelligent device is obtained. The target sensor devices and the target intelligent device are sensor devices and intelligent devices corresponding to the target edge device. The user behavior data, the environmental data, and the device status data are input into the personalized model for prediction processing to obtain the device adjustment decision result; The target intelligent device is adjusted based on the device adjustment decision results.
[0006] In some embodiments, the step of decrypting the target encrypted data using the employee key to obtain habit parameters and a personalized model includes: The target encrypted data is decrypted using the employee key to obtain a symmetric key and personalized encrypted data. The personalized encrypted data is decrypted using the symmetric key to obtain the habit parameters and the personalized model.
[0007] In some embodiments, the personalized model includes a state prediction sub-model and an adaptive adjustment sub-model. The step of inputting the user behavior data, the environmental data, and the device state data into the personalized model for prediction processing to obtain a device adjustment decision result includes: The user behavior data, the environmental data, and the device status data are input into the status prediction sub-model for status prediction processing to obtain the user's current status prediction result. The user's current state prediction result and the environmental data are input into the adaptive adjustment sub-model for equipment adjustment prediction processing to obtain the equipment adjustment decision result.
[0008] In some embodiments, the step of inputting the user behavior data, the environmental data, and the device status data into the status prediction sub-model for status prediction processing to obtain the user's current status prediction result includes: A composite feature vector is generated based on the user behavior data, the environmental data, and the device status data; The generated composite feature vector is input into the state prediction sub-model for state prediction processing to obtain the user's current state prediction result.
[0009] In some embodiments, before inputting the user's current state prediction result and the environmental data into the adaptive adjustment sub-model for device adjustment prediction processing to obtain the device adjustment decision result, the method further includes: Determine whether the predicted result of the user's current state meets the preset state adjustment conditions; The step of inputting the user's current state prediction result and the environmental data into the adaptive adjustment sub-model for device adjustment prediction processing includes: If the state adjustment conditions are met, the user's current state prediction result and the environmental data are input into the adaptive adjustment sub-model for equipment adjustment prediction processing to obtain the equipment adjustment decision result.
[0010] In some embodiments, after adjusting the target smart device based on the device adjustment decision result, the method further includes: The user's updated state prediction result is obtained through the state prediction sub-model; The user status change data is determined based on the user update status prediction result and the user current status prediction result. The adaptive adjustment sub-model is updated based on the reward signal determined from the user state change data.
[0011] In some embodiments, after determining the reward signal based on the user state change data to update the adaptive adjustment sub-model, the method further includes: The adaptive adjustment sub-model is encrypted using the employee key, and the encrypted adaptive adjustment sub-model is sent to the cloud server.
[0012] Secondly, embodiments of this application also provide an intelligent office environment control device. The intelligent office environment control device is deployed in a target edge device within an intelligent office environment control system. The intelligent office environment control system includes a cloud server and multiple edge devices. The edge devices are connected to multiple different types of sensor devices and intelligent devices. The intelligent office environment control device includes: The transceiver unit is used to acquire the workstation usage instruction triggered by the target user for the target edge device. The workstation usage instruction includes an employee key and an employee identifier. The target edge device is installed on the target workstation. The transceiver unit is used to acquire target encrypted data corresponding to the employee identifier from the cloud server and decrypt the target encrypted data using the employee key to obtain habit parameters and a personalized model. The processing unit is configured to initialize and adjust the smart device corresponding to the target edge device based on the habit parameters; collect user behavior data and environmental data corresponding to the target workstation through multiple target sensor devices, and obtain device status data of the target smart device, wherein the target sensor devices and the target smart device are the sensor devices and smart devices corresponding to the target edge device; input the user behavior data, the environmental data, and the device status data into the personalized model for prediction processing to obtain the device adjustment decision result; and adjust the target smart device based on the device adjustment decision result.
[0013] Thirdly, embodiments of this application also provide an edge device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method.
[0014] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor, can implement the above-described method.
[0015] This application provides a method, apparatus, edge device, and storage medium for intelligent adjustment of office environment. The method is applied to a target edge device in an intelligent office environment adjustment system, which includes a cloud server and multiple edge devices. These edge devices are connected to multiple different types of sensor devices and smart devices. The method includes: first, acquiring a workstation usage instruction triggered by a target user for the target edge device, the workstation usage instruction including an employee key and an employee identifier; the target edge device being installed at the target workstation; then, acquiring target encrypted data corresponding to the employee identifier from the cloud server, and decrypting the target encrypted data using the employee key to obtain habit parameters and a personalized model; initializing and adjusting the smart device corresponding to the target edge device based on the habit parameters; collecting user behavior data and environmental data corresponding to the target workstation, and acquiring device status data of the target smart device through multiple target sensor devices, the target sensor devices and the target smart device being the sensor devices and smart devices corresponding to the target edge device; finally, inputting the user behavior data, environmental data, and device status data into the personalized model for prediction processing to obtain a device adjustment decision result; and adjusting the target smart device based on the device adjustment decision result. This application embodiment can adjust the intelligent devices associated with the corresponding workstations in real time by acquiring user behavior data and environmental data, thereby realizing adaptive intelligent adjustment of the office environment. Attached Figure Description
[0016] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0017] Figure 1 A flowchart illustrating the intelligent office environment adjustment method provided in this application embodiment; Figure 2 A schematic diagram of a sub-process of the intelligent office environment adjustment method provided in the embodiments of this application; Figure 3 This is another schematic diagram of a sub-process of the intelligent office environment adjustment method provided in the embodiments of this application; Figure 4 A schematic block diagram of an intelligent office environment control device provided in the embodiments of this application; Figure 5 A schematic block diagram of an edge device provided in an embodiment of this application. Detailed Implementation
[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0019] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.
[0020] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.
[0021] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.
[0022] This application provides a method, apparatus, edge device, and storage medium for intelligent adjustment of office environment. The target edge device is applied to the intelligent adjustment system of office environment. The intelligent adjustment system of office environment includes a cloud server and multiple edge devices. The edge devices are connected to multiple different types of sensor devices and intelligent devices. In this application embodiment, the target edge device is any one of the multiple edge devices.
[0023] Among them, several different types of sensor devices include user behavior perception sensors and environmental perception sensors. User behavior perception sensors are used to understand the physiological and behavioral state of users without contact or interference, while environmental perception sensors are used to monitor the physical environment in which users are located.
[0024] User behavior sensing sensors include cameras and millimeter-wave radar. Cameras are used to capture the user's posture (identifying poor postures such as "leaning forward," "leaning backward," "hunching over," and "slanting"), head / torso position (determining if you are too close to the screen), and micro-motion frequency (counting the number of small body movements per unit time (fewer micro-movements when focused, more when agitated or fatigued)). Cameras can be deployed directly above the monitor or within the top bezel, covering the upper body. Millimeter-wave radar detects micro-movements by emitting millimeter waves and analyzing subtle changes in the reflected waves (Doppler effect), estimating respiratory rate and heart rate non-contactly (the gold standard for judging fatigue and stress). Millimeter-wave radar can be deployed above the desktop, behind the monitor, or under the desk, facing the user's torso.
[0025] The environmental sensing sensors include a light sensor and a noise / sound pressure sensor. The light sensor measures the ambient light level on the desktop or in the environment to automatically adjust the screen brightness and desk lamp brightness to prevent excessive contrast between the screen and the ambient light from hurting the eyes. The noise / sound pressure sensor measures the ambient noise level in decibels (dB). When the noise is too high, it automatically activates active noise cancellation or plays masking white noise / natural sounds, or reminds the user to lower the call volume when it is quiet.
[0026] Smart devices that connect to edge devices include smart desks, smart chairs, air conditioners, and lights.
[0027] The execution subject of this intelligent office environment adjustment method can be the intelligent office environment adjustment device provided in the embodiments of this application, or an edge device that integrates the intelligent office environment adjustment device. The intelligent office environment adjustment device can be implemented in hardware or software, and the edge device can be a smart electronic device with computing and communication functions, such as a tablet computer, a handheld computer, a laptop computer, or a smart box, set up at the workstation.
[0028] Figure 1 This is a flowchart illustrating the intelligent office environment adjustment method provided in this application embodiment. Figure 1 As shown, the method includes the following steps S110-S160.
[0029] S110. Obtain the workstation usage instruction triggered by the target user for the target edge device. The workstation usage instruction includes an employee key and an employee identifier. The target edge device is installed on the target workstation.
[0030] In this embodiment, the target workstation can be a mobile workstation, that is, there are multiple workstations in the current office environment, and employees can choose any empty workstation to sit in according to their preferences or habits after starting work.
[0031] For example, a target user selects a target workstation and takes a seat. After taking a seat, the user triggers the workstation usage command on the target edge device by swiping their work card or entering their employee ID (employee identifier) and password. The work card stores the employee key and the workstation identifier. The employee ID entered by the user serves as the employee identifier, and the password serves as the employee key. The employee key entered by the user may be the same as or different from the employee key stored on the work card.
[0032] The employee key is either set by the user during the initial registration of the office environment intelligent adjustment system or automatically assigned by the system. After registration, the employee key will be associated with the corresponding employee identifier and uploaded to the server.
[0033] S120. Obtain the target encrypted data corresponding to the employee identifier from the cloud server, and decrypt the target encrypted data using the employee key to obtain the habit parameters and personalized model.
[0034] In this embodiment, when the target edge device receives a workstation usage instruction triggered by the target user, it sends a personalized data acquisition instruction to the cloud server. This instruction carries the employee identifier of the target user. The cloud server stores the target encrypted data corresponding to each user. After receiving the instruction, the cloud server finds the target encrypted data corresponding to the employee identifier from the database and sends it to the target edge device.
[0035] After receiving the target encrypted data, the target edge device decrypts the target encrypted data. Specifically, in some embodiments, please refer to... Figure 2 The step of decrypting the target encrypted data using the employee key to obtain custom parameters and a personalized model includes: S1201. Decrypt the target encrypted data using the employee key to obtain a symmetric key and personalized encrypted data; S1202. Decrypt the personalized encrypted data using the symmetric key to obtain the habit parameters and the personalized model.
[0036] For example, the target encrypted data returned from the cloud includes E(Ku, Du) and E(Km, Ku), where Km is the employee key, Ku is the symmetric key, and Du is the custom parameter and personalized model; the edge device decrypts E(Km, Ku) to obtain Ku through the security module (which stores Km), and then uses Ku to decrypt E(Ku, Du) to obtain Du.
[0037] As can be seen, the target encrypted data in this embodiment is double-encrypted, which further improves the security of user data.
[0038] The habit parameter is an initial parameter manually set by the user. When this parameter is updated, it will be encrypted and updated to the cloud server accordingly.
[0039] S130. Based on the habit parameters, perform initialization adjustments on the smart device corresponding to the target edge device.
[0040] In this embodiment, after decrypting and obtaining the habit parameters, the office environment of the target workstation is adjusted in a timely manner based on these habit parameters to meet the user's needs. For example, the height and backrest tilt of the chair are adjusted to the preset height and tilt of the chair in the habit parameters, the height of the table is adjusted to the preset height of the table in the habit parameters, the brightness of the computer is adjusted to the preset brightness of the computer in the preset parameters, the light is adjusted to the preset brightness of the light in the preset parameters, and the air conditioner is adjusted to the preset temperature in the preset parameters, etc.
[0041] This embodiment allows for the rapid adjustment of the target workstation's office environment to a state that the user is accustomed to.
[0042] S140. Collect user behavior data and environmental data corresponding to the target workstation through multiple target sensor devices, and obtain device status data of the target intelligent device. The target sensor devices and the target intelligent device are sensor devices and intelligent devices corresponding to the target edge device.
[0043] In this embodiment, during the use of the target workstation, user behavior data and environmental data corresponding to the target workstation are continuously collected through multiple target sensor devices.
[0044] User behavior data includes sitting posture data (including data corresponding to different sitting posture labels such as standard sitting posture, leaning forward, leaning back, hunching, crossing legs or leaning to the side), trunk stability data (sway amplitude or static duration calculated based on key points of the spine), micro-motion frequency (number of unnecessary small-amplitude body movements per unit time (e.g., per minute), respiratory rate, and heart rate. Environmental data include light intensity, ambient temperature and humidity, and noise levels; Device status data includes the current height, current tilt angle, and motor status of the smart height-adjustable desk; the seat height, backrest angle, and lumbar support strength of the smart chair; the physical height / angle, brightness, and color temperature of the monitor / screen; the brightness / color temperature of the personal lighting; and the current air conditioning temperature.
[0045] S150. Input the user behavior data, the environmental data, and the device status data into the personalized model for prediction processing to obtain the device adjustment decision result.
[0046] In this embodiment, continuously collected user behavior data, environmental data, and current device status data are input into a personalized model for prediction processing to obtain device adjustment decision results. In some embodiments, the personalized model includes a status prediction sub-model and an adaptive adjustment sub-model; for details, please refer to [link to relevant documentation]. Figure 3 Step S150 includes: S1501. Input the user behavior data, the environmental data and the device status data into the status prediction sub-model for status prediction processing to obtain the user's current status prediction result. S1502. Input the user's current state prediction result and the environmental data into the adaptive adjustment sub-model for equipment adjustment prediction processing to obtain the equipment adjustment decision result.
[0047] In this embodiment, the state prediction sub-model is a state prediction model applicable to multiple users, or a model obtained by fine-tuning a standard state prediction model based on personalized state data. The adaptive adjustment sub-model is a model trained individually for different users.
[0048] Specifically, step S1501 includes generating a composite feature vector based on the user behavior data, the environmental data, and the device status data; inputting the generated composite feature vector into the status prediction sub-model for status prediction processing to obtain the user's current status prediction result.
[0049] In this embodiment, user behavior data, environmental data, and device status data are correlated in the time dimension to form a composite feature vector. This composite feature vector is then input into the status prediction sub-model for status prediction processing to obtain the user's current status prediction result.
[0050] The user's current state prediction result includes state values corresponding to multiple different preset states, such as 90% focus and 20% fatigue.
[0051] After obtaining the prediction result of the user's current state, the result and the current environmental data are input into the adaptive adjustment sub-model for equipment adjustment prediction processing to obtain the equipment adjustment decision result.
[0052] The adaptive adjustment sub-model is trained based on the target user's historical state data and the corresponding optimal adjustment parameters of the device. Therefore, based on the adaptive adjustment sub-model, the target user's office environment can be adjusted to the state that best matches the user's current state.
[0053] Furthermore, in some embodiments, before inputting the user's current state prediction result and the environmental data into the adaptive adjustment sub-model for device adjustment prediction processing to obtain the device adjustment decision result, the method further includes: Determine whether the predicted result of the user's current state meets the preset state adjustment conditions; At this point, the step of inputting the user's current state prediction result and the environmental data into the adaptive adjustment sub-model for device adjustment prediction processing includes: if the state adjustment conditions are met, then inputting the user's current state prediction result and the environmental data into the adaptive adjustment sub-model for device adjustment prediction processing to obtain the device adjustment decision result.
[0054] For example, the state adjustment condition indicates that the focus state value is lower than a first preset threshold (e.g., 50%), or the fatigue state value is higher than a second preset threshold (e.g., 60%). In this case, if the user's current state meets the preset state adjustment condition, the adaptive adjustment sub-model is triggered to perform device adjustment prediction processing.
[0055] The obtained device adjustment decision results include the adjustment parameters of the smart devices that need to be adjusted. When it is determined that the current focus is 60%, the fatigue level is 70%, and the current ambient brightness is relatively dark, the user's current state prediction results and environmental data are input into the adaptive adjustment sub-model to obtain the device adjustment decision results. The device adjustment decision results include the table automatically rising by 5 centimeters and the desk lamp being brightened by 20%.
[0056] In this embodiment, the state prediction sub-model can be an LSTM model, and the adaptive adjustment sub-model can be a reinforcement learning model.
[0057] S160. Adjust the target intelligent device based on the device adjustment decision result.
[0058] In this embodiment, after obtaining the device adjustment decision result, the corresponding target smart device is adjusted according to the specific adjustment parameters of the device adjustment decision result.
[0059] For example, the system can automatically raise the table by 5 centimeters and brighten the desk lamp by 20% (the adaptive adjustment sub-model discovers from training data (historical behavioral data of the target user) that users tend to raise the table and increase the brightness of the desk lamp when they are fatigued) to alleviate user fatigue.
[0060] In this embodiment, after adjusting the target smart device based on the device adjustment decision result, the method further includes: The user's updated state prediction result is obtained through the state prediction sub-model; user state change data is determined based on the user's updated state prediction result and the user's current state prediction result; and a reward signal is determined based on the user state change data to update the adaptive adjustment sub-model.
[0061] For example, based on user state change data, we can determine whether the user's focus has improved or fatigue has decreased, thereby determining the adjustment effect. Based on the adjustment effect, we can determine the reward signal and update the adaptive adjustment sub-model based on the reward signal through reinforcement learning.
[0062] Furthermore, after determining the reward signal and updating the adaptive adjustment sub-model based on the user status change data, the method further includes: encrypting the adaptive adjustment sub-model using the employee key, and sending the encrypted adaptive adjustment sub-model to the cloud server.
[0063] In this embodiment, if the model is updated, it will be encrypted and uploaded to the cloud server. This ensures that the cloud server stores the latest model while ensuring that the user data does not leave the local machine, thus further improving the security of user data.
[0064] In addition, when a user exits the target workstation, the target edge device deletes the data associated with that user.
[0065] In some embodiments, after generating the device adjustment decision result, a corresponding user reminder is generated. For example, a pop-up window on the screen reminds the user, "You feel quite tired. Would you like to automatically raise the table by 5 centimeters and turn the desk lamp up by 20%?" The device adjustment is only officially executed when the user confirms the adjustment. If the user chooses not to adjust, there is no need to perform the device adjustment operation.
[0066] Furthermore, based on user settings, the device adjustment decision can be executed automatically without user confirmation.
[0067] In summary, the method provided in this embodiment is applied to a target edge device in an intelligent office environment control system. The intelligent office environment control system includes a cloud server and multiple edge devices. These edge devices are connected to multiple different types of sensor devices and intelligent devices. The method includes: first, acquiring a workstation usage instruction triggered by a target user for the target edge device. The workstation usage instruction includes an employee key and an employee identifier. The target edge device is installed at the target workstation. Then, acquiring target encrypted data corresponding to the employee identifier from the cloud server and decrypting the target encrypted data using the employee key to obtain habit parameters and a personalized model. Initializing and adjusting the intelligent device corresponding to the target edge device based on the habit parameters. Collecting user behavior data and environmental data corresponding to the target workstation through multiple target sensor devices, and acquiring device status data of the target intelligent device. The target sensor devices and the target intelligent device are the sensor devices and intelligent devices corresponding to the target edge device. Finally, inputting the user behavior data, the environmental data, and the device status data into the personalized model for prediction processing to obtain a device adjustment decision result. Adjusting the target intelligent device based on the device adjustment decision result. This application embodiment can adjust the intelligent devices associated with the corresponding workstations in real time by acquiring user behavior data and environmental data, thereby realizing adaptive intelligent adjustment of the office environment.
[0068] Figure 4 This is a schematic block diagram of an intelligent office environment adjustment device provided in an embodiment of this application. Figure 4 As shown, corresponding to the above-described intelligent office environment adjustment method, this application also provides an intelligent office environment adjustment device. This intelligent office environment adjustment device includes a unit for executing the above-described intelligent office environment adjustment method. The intelligent office environment adjustment device 400 is deployed in a target edge device within an intelligent office environment adjustment system. The intelligent office environment adjustment system includes a cloud server and multiple edge devices, which are connected to multiple different types of sensor devices and intelligent devices. Specifically, please refer to... Figure 4 The intelligent office environment control device 400 includes a transceiver unit 401 and a processing unit 402, wherein: The transceiver unit 401 is used to acquire a workstation usage instruction triggered by a target user for the target edge device. The workstation usage instruction includes an employee key and an employee identifier. The target edge device is installed on the target workstation. The transceiver unit 401 is used to acquire target encrypted data corresponding to the employee identifier from the cloud server and decrypt the target encrypted data using the employee key to obtain habit parameters and a personalized model. The processing unit 402 is configured to initialize and adjust the smart device corresponding to the target edge device based on the habit parameters; collect user behavior data and environmental data corresponding to the target workstation through multiple target sensor devices, and obtain device status data of the target smart device, wherein the target sensor devices and the target smart device are the sensor devices and smart devices corresponding to the target edge device; input the user behavior data, the environmental data, and the device status data into the personalized model for prediction processing to obtain the device adjustment decision result; and adjust the target smart device based on the device adjustment decision result.
[0069] In some embodiments, when the processing unit 402 performs the step of decrypting the target encrypted data using the employee key to obtain the habit parameters and the personalized model, it is specifically used for: The target encrypted data is decrypted using the employee key to obtain a symmetric key and personalized encrypted data. The personalized encrypted data is decrypted using the symmetric key to obtain the habit parameters and the personalized model.
[0070] In some embodiments, the personalized model includes a state prediction sub-model and an adaptive adjustment sub-model. When the processing unit 402 performs the step of inputting the user behavior data, the environmental data, and the device state data into the personalized model for prediction processing to obtain the device adjustment decision result, it is specifically used for: The user behavior data, the environmental data, and the device status data are input into the status prediction sub-model for status prediction processing to obtain the user's current status prediction result. The user's current state prediction result and the environmental data are input into the adaptive adjustment sub-model for equipment adjustment prediction processing to obtain the equipment adjustment decision result.
[0071] In some embodiments, when the processing unit 402 performs the step of inputting the user behavior data, the environmental data, and the device status data into the status prediction sub-model for status prediction processing to obtain the user's current status prediction result, it is specifically used for: A composite feature vector is generated based on the user behavior data, the environmental data, and the device status data; The generated composite feature vector is input into the state prediction sub-model for state prediction processing to obtain the user's current state prediction result.
[0072] In some embodiments, before performing the step of inputting the user's current state prediction result and the environmental data into the adaptive adjustment sub-model for device adjustment prediction processing to obtain the device adjustment decision result, the processing unit 402 is further configured to: Determine whether the predicted result of the user's current state meets the preset state adjustment conditions; At this point, the step of inputting the user's current state prediction result and the environmental data into the adaptive adjustment sub-model for device adjustment prediction processing includes: If the state adjustment conditions are met, the user's current state prediction result and the environmental data are input into the adaptive adjustment sub-model for equipment adjustment prediction processing to obtain the equipment adjustment decision result.
[0073] In some embodiments, after performing the step of adjusting the target smart device based on the device adjustment decision result, the processing unit 402 is further configured to: The user's updated state prediction result is obtained through the state prediction sub-model; The user status change data is determined based on the user update status prediction result and the user current status prediction result. The adaptive adjustment sub-model is updated based on the reward signal determined from the user state change data.
[0074] In some embodiments, after performing the step of determining the reward signal and updating the adaptive adjustment sub-model based on the user state change data, the processing unit 402 is further configured to: The adaptive adjustment sub-model is encrypted using the employee key, and the encrypted adaptive adjustment sub-model is sent to the cloud server.
[0075] In summary, the embodiments of this application can adjust the intelligent devices associated with the corresponding workstations in real time by acquiring user behavior data and environmental data, thereby realizing adaptive intelligent adjustment of the office environment.
[0076] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned intelligent office environment adjustment device and each unit can be referred to the corresponding description in the foregoing method embodiments. For the sake of convenience and brevity, it will not be repeated here.
[0077] The aforementioned intelligent office environment control device can be implemented as a computer program, which can, for example... Figure 5 It runs on the edge device shown.
[0078] Please see Figure 5 , Figure 5This is a schematic block diagram of an edge device provided in an embodiment of this application. The edge device 500 can be a terminal or a server. Specifically, the edge device is a device in an intelligent office environment control system, which includes a cloud server and multiple edge devices, and the edge devices are connected to multiple different types of sensor devices and intelligent devices.
[0079] See Figure 5 The edge device 500 includes a processor 502, a memory, and a network interface 505 connected via a system bus 501. The memory may include a non-volatile storage medium 503 and internal memory 504.
[0080] The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions that, when executed, cause the processor 502 to perform an intelligent adjustment method for an office environment.
[0081] The processor 502 provides computing and control capabilities to support the operation of the entire edge device 500.
[0082] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute an intelligent adjustment method for the office environment.
[0083] This network interface 505 is used for network communication with other devices. Those skilled in the art will understand that... Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the edge device 500 to which the present application is applied. The specific edge device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0084] The processor 502 is used to run a computer program 5032 stored in the memory to perform the following steps: Obtain the workstation usage instruction triggered by the target user for the target edge device. The workstation usage instruction includes an employee key and an employee identifier. The target edge device is installed at the target workstation. The target encrypted data corresponding to the employee identifier is obtained from the cloud server, and the target encrypted data is decrypted using the employee key to obtain the habit parameters and personalized model. The smart device corresponding to the target edge device is initialized and adjusted based on the aforementioned habit parameters; User behavior data and environmental data corresponding to the target workstation are collected by multiple target sensor devices, and device status data of the target intelligent device is obtained. The target sensor devices and the target intelligent device are sensor devices and intelligent devices corresponding to the target edge device. The user behavior data, the environmental data, and the device status data are input into the personalized model for prediction processing to obtain the device adjustment decision result; The target intelligent device is adjusted based on the device adjustment decision results.
[0085] It should be understood that in the embodiments of this application, the processor 502 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.
[0086] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program includes program instructions and can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.
[0087] Therefore, this application also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. When executed by a processor, the program instructions cause the processor to perform the following steps: Obtain the workstation usage instruction triggered by the target user for the target edge device. The workstation usage instruction includes an employee key and an employee identifier. The target edge device is installed at the target workstation. The target encrypted data corresponding to the employee identifier is obtained from the cloud server, and the target encrypted data is decrypted using the employee key to obtain the habit parameters and personalized model. The smart device corresponding to the target edge device is initialized and adjusted based on the aforementioned habit parameters; User behavior data and environmental data corresponding to the target workstation are collected by multiple target sensor devices, and device status data of the target intelligent device is obtained. The target sensor devices and the target intelligent device are sensor devices and intelligent devices corresponding to the target edge device. The user behavior data, the environmental data, and the device status data are input into the personalized model for prediction processing to obtain the device adjustment decision result; The target intelligent device is adjusted based on the device adjustment decision results.
[0088] The storage medium can be any computer-readable storage medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk.
[0089] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.
[0090] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.
[0091] The steps in the methods of this application embodiment can be adjusted, merged, or deleted according to actual needs. The units in the apparatus of this application embodiment can be merged, divided, or deleted according to actual needs. Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0092] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.
[0093] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
Claims
1. A method for intelligent adjustment of an office environment, characterized in that, A target edge device is applied to an intelligent office environment control system, the intelligent office environment control system including a cloud server and multiple edge devices, the edge devices being connected to multiple different types of sensor devices and intelligent devices, the method comprising: Obtain the workstation usage instruction triggered by the target user for the target edge device. The workstation usage instruction includes an employee key and an employee identifier. The target edge device is installed at the target workstation. The target encrypted data corresponding to the employee identifier is obtained from the cloud server, and the target encrypted data is decrypted using the employee key to obtain the habit parameters and personalized model. The smart device corresponding to the target edge device is initialized and adjusted based on the aforementioned habit parameters; User behavior data and environmental data corresponding to the target workstation are collected by multiple target sensor devices, and device status data of the target intelligent device is obtained. The target sensor devices and the target intelligent device are sensor devices and intelligent devices corresponding to the target edge device. The user behavior data, the environmental data, and the device status data are input into the personalized model for prediction processing to obtain the device adjustment decision result; The target intelligent device is adjusted based on the device adjustment decision results.
2. The method according to claim 1, characterized in that, The step of decrypting the target encrypted data using the employee key to obtain custom parameters and a personalized model includes: The target encrypted data is decrypted using the employee key to obtain a symmetric key and personalized encrypted data. The personalized encrypted data is decrypted using the symmetric key to obtain the habit parameters and the personalized model.
3. The method according to claim 1, characterized in that, The personalized model includes a state prediction sub-model and an adaptive adjustment sub-model. The step of inputting the user behavior data, the environmental data, and the device state data into the personalized model for prediction processing to obtain the device adjustment decision result includes: The user behavior data, the environmental data, and the device status data are input into the status prediction sub-model for status prediction processing to obtain the user's current status prediction result. The predicted result of the user's current state and the environmental data are input into the adaptive adjustment sub-model for equipment adjustment prediction processing to obtain the equipment adjustment decision result.
4. The method according to claim 3, characterized in that, The step of inputting the user behavior data, the environmental data, and the device status data into the status prediction sub-model for status prediction processing to obtain the user's current status prediction result includes: A composite feature vector is generated based on the user behavior data, the environmental data, and the device status data; The generated composite feature vector is input into the state prediction sub-model for state prediction processing to obtain the user's current state prediction result.
5. The method according to claim 3, characterized in that, Before inputting the user's current state prediction result and the environmental data into the adaptive adjustment sub-model for device adjustment prediction processing to obtain the device adjustment decision result, the method further includes: Determine whether the predicted result of the user's current state meets the preset state adjustment conditions; The step of inputting the user's current state prediction result and the environmental data into the adaptive adjustment sub-model for device adjustment prediction processing includes: If the state adjustment conditions are met, the user's current state prediction result and the environmental data are input into the adaptive adjustment sub-model for equipment adjustment prediction processing to obtain the equipment adjustment decision result.
6. The method according to claim 3, characterized in that, After adjusting the target smart device based on the device adjustment decision result, the method further includes: The user's updated state prediction result is obtained through the state prediction sub-model; The user status change data is determined based on the user update status prediction result and the user current status prediction result. The adaptive adjustment sub-model is updated based on the reward signal determined from the user state change data.
7. The method according to claim 6, characterized in that, After determining the reward signal and updating the adaptive adjustment sub-model based on the user state change data, the method further includes: The adaptive adjustment sub-model is encrypted using the employee key, and the encrypted adaptive adjustment sub-model is sent to the cloud server.
8. An intelligent office environment control device, characterized in that, The intelligent office environment control device is deployed in the target edge device of the intelligent office environment control system. The intelligent office environment control system includes a cloud server and multiple edge devices. The edge devices are connected to multiple different types of sensor devices and intelligent devices. The intelligent office environment control device includes: The transceiver unit is used to acquire the workstation usage instruction triggered by the target user for the target edge device. The workstation usage instruction includes an employee key and an employee identifier. The target edge device is installed on the target workstation. The transceiver unit is used to acquire target encrypted data corresponding to the employee identifier from the cloud server and decrypt the target encrypted data using the employee key to obtain habit parameters and a personalized model. The processing unit is configured to initialize and adjust the smart device corresponding to the target edge device based on the habit parameters; collect user behavior data and environmental data corresponding to the target workstation through multiple target sensor devices, and obtain device status data of the target smart device, wherein the target sensor devices and the target smart device are the sensor devices and smart devices corresponding to the target edge device; input the user behavior data, the environmental data, and the device status data into the personalized model for prediction processing to obtain the device adjustment decision result; and adjust the target smart device based on the device adjustment decision result.
9. An edge device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the office environment intelligent adjustment method as described in any one of claims 1-7.
10. A storage medium, characterized in that, The storage medium stores a computer program, which includes program instructions that, when executed by a processor, cause the processor to perform the intelligent office environment adjustment method as described in any one of claims 1-7.