An energy optimization management system and management method for hotel rooms

Abstract

The present invention belongs to the technical field of intelligent control. The present invention discloses an energy optimization management system and management method for hotel guest rooms, including a central data pool unit, which constructs a time series database cluster and uploads and interacts data between each unit through a data bus; a presence sensing unit, which integrates multiple sensors using a sensing layer architecture to form a sensing network, captures presence sensing data, and generates a room presence status map based on the presence sensing data; the presence sensing data includes guest room reservation information data, guest room environment data, and guest information data; a partitioned environment control unit, which obtains guest preference data by analyzing the room presence status map; based on the guest preference data and the guest room environment data, uses an intelligent optimization algorithm to selectively activate the environment control of different guest room areas; and improves the energy utilization rate of the hotel and customer satisfaction.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control, and more specifically, to an energy optimization management system and method for hotel guest rooms. Background Art

[0002] The patent with the publication number CN103136826A discloses an energy and room status management system, which relates to the field of intelligent hotel guest room control. A PC is connected to a network converter, and the network converter is respectively connected to an energy and room status controller and an electric energy meter. The energy and room status controller is respectively connected to the electric energy meter, a water control meter, and an identity recognition power-taking switch. The management system platform is connected to the PC through TCP / IP. This invention patent can improve the collection, storage, and management of energy information, reduce energy management links, optimize the energy management process, save energy and reduce consumption, and reduce operating costs. It is beneficial for hotel guest room staff to precisely manage guest room resources. At the same time, the hotel management company can remotely monitor the real-time status of the hotel, promoting the further improvement of management level and the further reduction of operating costs.

[0003] The existing energy optimization management systems and methods for hotel guest rooms mainly have the following problems:

[0004] The existing intelligent guest room environment control systems often adjust the guest room environment through simple preset scenarios or fixed environmental settings (such as temperature, lighting, etc.), lacking dynamic adjustment based on individual guest preferences.

[0005] Most of them only make simple regional divisions based on the physical location of the guest room, without delving into the details of the furniture layout and activity habits in the guest room. Traditional zoning methods are difficult to effectively meet the actual needs of different guests, resulting in insufficient space utilization and comfort.

[0006] In many existing systems, the environmental transition between regions is relatively abrupt, lacking smooth transition, resulting in an unnatural switch in the environmental perception. For example, from the work area to the rest area, the lighting or temperature may change sharply, causing discomfort.

[0007] Existing systems often use fixed and standardized buffer widths, without considering the individual activity data of guests. The existing methods cannot define the buffer zone in a refined manner, resulting in low space utilization or inappropriateness. Traditional buffer zones usually adopt a uniform space division method without considering the directionality and frequency of actual guest activities.

[0008] In view of this, the present invention proposes an energy optimization management system and method for hotel guest rooms to solve the above problems. Summary of the Invention

[0009] To overcome the above defects of the prior art and to achieve the above object, the present invention provides the following technical solution: An energy optimization management system for hotel guest rooms, comprising:

[0010] A central data pool unit, which constructs a time series database cluster and uploads and interacts data between each unit through a data bus;

[0011] A presence sensing unit, which integrates multiple sensors using a sensing layer architecture to form a sensing network, captures presence sensing data, and generates a room presence status map based on the presence sensing data; the presence sensing data includes guest room reservation information data, guest room environment data, and guest information data;

[0012] A partitioned environment control unit, which obtains guest preference data by analyzing the room presence status map; based on the guest preference data and the guest room environment data, uses an intelligent optimization algorithm to selectively activate the environment control of different guest room areas;

[0013] A gradual adjustment unit, which designs personalized environment parameter change curves for different areas based on the guest preference data, obtains the hotel equipment power change curve, and issues a soft transition instruction for scene switching to the equipment collaborative control unit for execution;

[0014] An equipment collaborative control unit, which establishes an energy efficiency model library for hotel equipment, according to the hotel equipment power change curve, adopts an equipment complementary and collaborative mechanism to coordinate the operation of different hotel equipment with each other, and obtains equipment operation data;

[0015] An energy load balancing unit, which predicts the energy demand index in the future period of time according to the guest preference data, the equipment operation data, and the personalized environment parameter change curve; pre-stores and releases energy at different time periods of electricity prices according to the energy demand index to balance the energy load.

[0016] Preferably, the method for capturing the presence sensing data includes:

[0017] Deploy environmental sensors, human activity sensors, and interface devices docked with the hotel management system inside the guest room, integrate the environmental sensors, human activity sensors, and interface devices into the same sensing network through a standardized interface, and perform periodic data collection, thereby obtaining guest room environment data, guest information data, and guest room reservation information data; integrate the guest room environment data, guest information data, and guest room reservation information data to obtain the presence sensing data.

[0018] Preferably, the method for generating the room presence status map includes:

[0019] Based on the obtained presence perception data, the rule engine method is used to determine the room presence status according to the predetermined business rules; the room presence status includes idle, reserved but unused, in use, and abnormal status; entity extraction is performed on the room presence status determination result and the presence perception data as the nodes of the room presence status graph, and the logical relationship between entities is used as the edge of the room presence status graph to construct the room presence status graph.

[0020] Preferably, the method for obtaining the guest preference data includes:

[0021] A guest preference prediction model is constructed through a spatio-temporal graph neural network. The guest preference prediction model includes an input layer, a spatial feature extraction layer, a temporal feature extraction layer, a spatio-temporal fusion layer, and an output layer; the room presence status graph is used as the input data of the input layer of the guest preference model, and the spatial dependence relationship in the room presence status graph is analyzed through graph convolution in the spatial feature extraction layer;

[0022] In the spatio-temporal fusion layer, the gated recurrent unit is used to process the guest behavior change pattern in the time dimension. In the spatio-temporal fusion layer, the obtained spatial dependence relationship and the guest behavior change pattern in the time dimension are spliced and fused to obtain the guest preference data; the guest preference data includes temperature preference, lighting preference, air quality preference, time pattern preference, area usage habit, device interaction habit, energy usage pattern, scene switching preference, and circadian rhythm preference.

[0023] Preferably, the method for selectively activating the environmental control of different guest room areas includes;

[0024] The different guest room areas include a rest area, an entertainment area, a work area, and a bathing area; it is set that each guest room area respectively contains adjustable environmental parameters to form a -dimensional control vector; with the goal of minimizing energy consumption and maximizing comfort, the Actor-Critic framework is selected to build a deep neural network, and the guest preference data and the guest room environment data are spliced and fused to form a state vector; the state vector is used as the input data of the deep neural network, and the deep association information in the state vector is gradually extracted through the policy network of the fully connected layer. Under the goal of minimizing energy consumption and maximizing comfort, the global optimal control vector is output;

[0025] The global optimal control vector is uploaded to the central data pool and sent to the environmental control actuator of the corresponding guest room area through the data bus to adjust the corresponding device status, thereby realizing the selective activation of the environmental control of different guest room areas.

[0026] Preferably, the method for designing the personalized environmental parameter change curve includes:

[0027] Define the regional boundary and transition zone model, and identify the explicit physical boundary based on the physical structure of the guest room; naturally form the first layer of boundary between different regions, automatically identify the first layer of boundary by analyzing the CAD drawings and 3D models of the guest room, and use it as the basic framework for regional division;

[0028] Determine the functional boundary based on the furniture layout. Different furniture combinations indicate different guest room regions. The bed area is defined as the rest area, the table and chair combination is defined as the work area, the sofa and TV area is defined as the entertainment area, and the combination of washbasin, toilet and shower is defined as the bathing area;

[0029] By identifying different furniture combinations, define the functional boundary. The functional boundary consists of the union of the core furniture edge and the functional activity buffer zone; define the core furniture edge and the functional activity buffer zone, construct the regional transition zone model through the distance weighted interpolation algorithm combined with the cubic spline function, construct the guest preference - regional association matrix, analyze the guest activity data and the corresponding environmental requirements, and define the typical scenarios and environmental parameter sets for guests staying in hotel guest rooms. The typical scenarios include check - in scenario, sleep preparation scenario, work scenario and leisure scenario; the parameter set includes temperature, lighting intensity and humidity air ventilation frequency;

[0030] Establish a scenario - parameter multi - dimensional target matrix. The elements in the scenario - parameter multi - dimensional target matrix include typical scenarios, different guest room regions and target environmental parameter set types; define the acceptable range for each target environmental parameter set, adjust the standard target environmental parameter set according to the guest preference data, and analyze the adaptability index of guests to changes in guest room environmental data;

[0031] Establish an environmental parameter change sensitivity model. Through the environmental parameter change sensitivity model, measure the index of the sensitivity of guests' response to changes in guest room environmental data; calculate the optimal change rate of each parameter in the guest room environmental data;

[0032] Apply the cubic Bezier curve algorithm to design a smooth transition curve according to the index of the sensitivity of guests' response to changes in guest room environmental data and the optimal change rate of each parameter in the guest room environmental data, and apply specific physical model constraints for different environmental parameters; establish a correlation matrix between environmental parameters to achieve a parameter linkage mechanism, and coordinate the guest room environmental data through the parameter smooth transition algorithm at the regional junction; and adjust and update the smooth transition curve through the guest preference data to obtain a personalized environmental parameter change curve.

[0033] Preferably, the method for defining the core furniture edge and the functional activity buffer zone includes:

[0034] The method for defining the edge of the core furniture includes defining different furniture combinations corresponding to different guest room areas as the core furniture of that area. For each core furniture, extract its two-dimensional projection contour and construct a polygon boundary representation. For different core furniture, obtain the size and position information of the core furniture through a 3D scanner, calculate the overall contour of the core furniture, and select the corresponding edge definition according to the current state of different furniture combinations.

[0035] Taking the origin at the lower left corner of the guest room, establish a Cartesian coordinate system, project the core furniture data onto the ground plane. For regular-shaped furniture, directly calculate the four-corner coordinates, which include the lower left corner coordinate, upper left corner coordinate, upper right corner coordinate, and lower right corner coordinate, and apply a rotation matrix to process the orientation of the core furniture to obtain its edge. For irregular-shaped furniture, decompose the irregular-shaped furniture into m basic components and merge the boundaries to obtain its edge. For smooth curved surface furniture, approximate its edge using parametric curves. The extracted edge is stored in the form of an ordered point set to obtain the edge of the core furniture.

[0036] The method for defining the functional activity buffer includes that the basic buffer width is determined according to the guest activity data.

[0037] The shape of the basic buffer is obtained by non-uniform directional expansion according to the guest activity data, and the basic buffer width is adjusted according to different direction coefficients to obtain the widths of the buffer in different directions. The guest activity data includes the residence time of the guest in different direction areas, the maximum residence time of the guest at all direction angles, the number of times the guest moves along different direction angles, and the total number of times the guest moves at all direction angles.

[0038] The basic buffer includes a rest buffer, a work buffer, an entertainment buffer, and a bathing buffer. The basic buffer width is obtained by presetting the widths of different buffers.

[0039] Preferably, the method for coordinating the operation of different hotel equipment with each other includes:

[0040] Collect the energy consumption data of various hotel equipment under different working conditions, and construct a mathematical model of equipment energy efficiency. The mathematical model of equipment energy efficiency includes an equipment power-load curve, a start-stop efficiency curve, and a temperature-energy consumption relationship curve. The equipment power-load curve is obtained by using the standard segmented test method. The construction method of the start-stop efficiency curve is obtained based on the industrial energy efficiency test standard. The temperature-energy consumption relationship curve is obtained by using the environmental temperature impact test process defined by the international standard test method.

[0041] Convert the personalized environmental parameter change curve generated by the gradient adjustment unit into a device power change curve, define a device complementary and collaborative mechanism, which includes using time-series complementarity, implementing spatial complementarity, and executing source-end complementarity; generate device linkage instructions based on the collaborative optimization algorithm, and issue the device linkage instructions through the energy management intelligent terminal to coordinate the operation of different hotel devices in cooperation with each other.

[0042] Preferably, the method for balancing the energy load includes:

[0043] Match and analyze the energy demand index in the predicted future for a period of time with the grid electricity price period information. The grid electricity price period is divided into peak period, normal period, and valley period. Identify the overlapping area of the highest demand and the highest electricity price through the time-series matching algorithm, and balance the energy load for the period corresponding to the overlapping area of the highest demand and the highest electricity price; activate the energy pre-storage mechanism when it is in the electricity price valley period and the highest demand in the future is predicted, and store the energy of the hotel guest rooms; preset the grid electricity price threshold, and set the energy release instruction according to the preset grid electricity price threshold during the peak period. When the grid electricity price is greater than or equal to the grid electricity price threshold, trigger the energy release instruction to release the energy of the hotel guest rooms.

[0044] An energy optimization management method for hotel guest rooms includes:

[0045] S1. Construct a time-series database cluster, and upload and interact data between each unit through the data bus;

[0046] S2. Integrate multiple sensors using the perception layer architecture to form a perception network, capture presence perception data, and generate a room presence state map based on the presence perception data; the presence perception data includes guest room reservation information data, guest room environment data, and guest information data;

[0047] S3. Analyze the room presence state map to obtain guest preference data; based on the guest preference data and the guest room environment data, use an intelligent optimization algorithm to selectively activate the environmental control of different guest room areas;

[0048] S4. Design a personalized environmental parameter change curve for different areas based on the guest preference data, obtain the hotel device power change curve, and issue a soft transition instruction for scene switching to the device collaborative control unit for execution;

[0049] S5. Establish a hotel device energy efficiency model library, according to the hotel device power change curve, adopt a device complementary and collaborative mechanism to coordinate the operation of different hotel devices in cooperation with each other, and obtain device operation data;

[0050] S6. Predict the future based on the guest preference data, device operation data, and personalized environmental parameter change curve The energy demand index within a period of time; according to the energy demand index, energy is pre-stored and released during different time periods of the electricity price to balance the energy load.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] The present invention automatically adjusts the environmental control through guest preference data, can accurately meet the unique needs of each guest, makes the guest room environment more in line with individual living habits. As the number of times a user checks in increases, the system will accumulate more detailed preference data, further improving the accuracy of personalized adjustment, continuously optimizing the guest room environment, and providing more precise services for frequent guests;

[0053] By automatically identifying the physical boundaries and furniture layouts of the guest room, the system can accurately divide different functional areas and adjust the environment according to the needs of each area. By dynamically adjusting the width and shape of the buffer zone, the system can optimize the space layout according to the guest's activity habits and direction needs, avoiding unnecessary space waste; through refined functional area division, the sense of oppression in the guest room is alleviated. Especially in a smaller guest room space, the discomfort caused by unreasonable space layout can be effectively avoided;

[0054] The sudden feeling during area switching in the existing system is avoided, and the guest room environment data can smoothly transition between different areas. Through the transition zone model, the conflicts between the environments of different areas are avoided. Guests will not feel uncomfortable due to sudden light changes or drastic temperature fluctuations during activities, enhancing the overall comfort in the guest room;

[0055] By dynamically adjusting the environmental data of the guest room such as temperature, humidity, and light, unnecessary energy waste can be avoided. For example, based on the detection of the actual activities of the guests, when the guests leave the room, the system can automatically adjust the temperature and light to save energy consumption; when the guests change areas, the system can automatically optimize the energy use to avoid multiple areas being in a high energy consumption state at the same time; for different environmental requirements, the system can optimize the energy consumption through intelligent algorithms. For example, the lighting and temperature control in the working area will be automatically adjusted according to the time period of the guests' activities, without the need for manual switching, greatly improving the energy efficiency and energy conservation;

[0056] Guests no longer need to manually adjust various devices to adapt to personal needs. The system automatically adjusts the environmental settings of the guest room area according to personal preferences and activity patterns, simplifies the customer operation, and improves the convenience of check-in. By adapting to the needs of guests in advance and making real-time adjustments, a more considerate service experience can be provided. When guests feel a comfortable and personalized environment, higher customer satisfaction is obtained. Brief Description of the Drawings

[0057] Figure 1Schematic diagram of the energy optimization management system for a hotel guest room of the present invention;

[0058] Figure 2 Schematic diagram of the process of the energy optimization management method for a hotel guest room of the present invention;

[0059] Figure 3 Technical roadmap for selectively activating environmental control in different guest room areas provided by the present invention. Specific embodiments

[0060] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present invention.

[0061] Embodiment 1

[0062] Please refer to Figure 1 and Figure 3 shown in the figure. In this first embodiment, a hotel guest room energy optimization management system proposed by the present invention is further described, including:

[0063] With the intensification of the global energy shortage problem, the hotel industry, as one of the high-energy-consuming industries, faces the challenge of energy conservation and emission reduction. The energy consumption in hotel guest rooms mainly comes from air conditioners, lighting, hot water supply, and various electrical appliances. The traditional hotel energy management mode often relies on fixed time control or manual adjustment, lacking intelligent and refined management, resulting in energy waste and a decline in the customer experience. Therefore, an energy optimization management system based on intelligent algorithms has become the key research direction, aiming to improve energy use efficiency, reduce operating costs, and provide a more comfortable check-in experience through sensing technology, data analysis, and intelligent control.

[0064] The current hotel guest room energy management technologies mainly have the following problems:

[0065] The environmental control mode is rigid and lacks personalized adjustment: The air conditioners, lighting, and other equipment in traditional hotel guest rooms usually rely on fixed time control or manual settings, and cannot be dynamically adjusted according to the specific needs and preferences of guests; the comfort requirements of guests at different times are not considered, resulting in increased energy consumption and affecting the check-in experience.

[0066] The equipment collaborative control ability is insufficient: Most of the existing hotel guest room equipment operates independently, and there is a lack of collaborative adjustment among equipment such as air conditioners, lighting, and curtains, and a systematic energy-saving strategy has not been formed; there is a lack of an energy efficiency optimization model based on the operating status of the equipment, resulting in some equipment running for a long time or starting and stopping frequently, affecting energy efficiency and reducing the equipment life.

[0067] Limited energy load management capabilities: Existing energy management systems lack an accurate energy demand prediction mechanism, resulting in unreasonable energy distribution; they cannot perform energy pre-storage or load balancing adjustment according to electricity price fluctuations, and fail to make full use of low electricity price periods to optimize energy use, increasing operating costs.

[0068] To effectively solve the above problems, the present invention proposes an energy optimization management system for hotel guest rooms, including:

[0069] A central data pool unit that constructs a time-series database cluster and uploads and interacts data between units through a data bus;

[0070] A presence sensing unit that integrates multiple sensors using a sensing layer architecture to form a sensing network, captures presence sensing data, and generates a room presence status map based on the presence sensing data; the presence sensing data includes guest room reservation information data, guest room environment data, and guest information data;

[0071] A zoned environment control unit that analyzes the room presence status map to obtain guest preference data; based on the guest preference data and the guest room environment data, uses an intelligent optimization algorithm to selectively activate the environmental control of different guest room areas;

[0072] A gradual adjustment unit that designs personalized environmental parameter change curves for different areas based on the guest preference data, obtains the hotel equipment power change curve, and issues a soft transition instruction for scene switching to the equipment collaborative control unit for execution;

[0073] An equipment collaborative control unit that establishes an energy efficiency model library for hotel equipment, according to the hotel equipment power change curve, uses an equipment complementary collaboration mechanism to coordinate the operation of different hotel equipment with each other, and obtains equipment operation data;

[0074] An energy load balancing unit that predicts the energy demand index in the future period of time based on the guest preference data, equipment operation data, and personalized environmental parameter change curve; performs energy pre-storage and release at different electricity price periods according to the energy demand index to balance the energy load.

[0075] The method for capturing presence sensing data includes:

[0076] Deploy environmental sensors (such as temperature sensors, humidity sensors, light sensors, CO2 concentration sensors, noise sensors, etc.), human activity sensors (such as infrared sensors, ultrasonic sensors, motion detectors, etc.) and interface devices docked with the hotel management system inside the guest room. Integrate the environmental sensors, human activity sensors and interface devices into the same perception network through standardized interfaces (such as MQTT, ZigBee, Wi-Fi or BLE), and perform periodic data collection to obtain guest room environmental data, guest information data and guest room reservation information data; integrate the guest room environmental data, guest information data and guest room reservation information data to obtain presence perception data.

[0077] The guest room environmental data includes temperature data, humidity data, light data, CO2 concentration data and noise data; the guest information data includes identity information (guest name, identity certificate, membership level and contact information), occupancy status (occupied, checked out or vacant), travel trajectory and historical occupancy data; the guest room reservation information data includes basic reservation information (reservation number, reservation date, check-in time and check-out time), room type and configuration (room type, bed type and meals) and special requirements (such as temperature adjustment, lighting mode, air purification requirements, etc.).

[0078] The method for generating a room presence status map includes:

[0079] Based on the obtained presence perception data, the rule engine method is used to determine the room presence status according to the predefined business rules; the room presence status includes idle (no current reservation, no access record at the access control, no human activity signal detected), reserved but unused (currently reserved, no access record at the access control, no human activity signal detected), in use (current reservation or no reservation, access record of entry at the access control and no departure, human activity signal detected), and abnormal status (human activity signal detected during non-reservation time period, no one for a long time during the reservation time period); entity extraction is performed on the room presence status determination result and the presence perception data as the nodes of the room presence status graph, and the logical relationships between entities are used as the edges of the room presence status graph to construct the room presence status graph, which is stored and updated through a graph database; the nodes of the room presence status graph include room entities (node attributes include room number, room type, and room capacity), guest room areas (rest area, work area, bathing area, etc.), time points, devices, room presence status, event status (door opening / closing, person detected, room reservation submission, etc.), and guest room environment data (sensor data such as temperature, light, etc.); the logical relationships between entities are, for example: the status of "room-xx" at "time point s1" is "room presence status-idle"; "room-xx" has "event status-door opening"; "room-xx" at "time point s2" has the "device-light" in the "guest room area-sleeping area" adjust the "guest room environment parameter-light brightness reduction", etc.

[0080] The methods for obtaining guest preference data include:

[0081] A guest preference prediction model is constructed through a spatio-temporal graph neural network. The guest preference prediction model includes an input layer, a spatial feature extraction layer, a temporal feature extraction layer, a spatio-temporal fusion layer, and an output layer; the room presence status graph is used as the input data of the input layer of the guest preference model. In the spatial feature extraction layer, the spatial dependence relationship in the room presence status graph is analyzed through graph convolution, that is, the interaction patterns between different guest room areas, sensors, and devices; in the room presence status graph, the interaction patterns between different areas, sensors, and devices mainly refer to their physical connections, device linkage relationships, and associations caused by guest behavior habits. For example: work area - desk lamp, interaction pattern: light adjustment (that is, if a guest often uses the desk lamp in the work area for supplementary lighting, it can be predicted that the guest likes a brighter office environment and will automatically adjust the desk lamp brightness in the future).

[0082] In the spatio-temporal fusion layer, the gated recurrent unit is used to process the changing patterns of guests' behaviors in the time dimension. For example, how guests adjust the devices over time to change the guest room environment data. In the spatio-temporal fusion layer, the obtained spatial dependency relationships and the changing patterns of guests' behaviors in the time dimension are concatenated and fused to obtain guests' preference data; the guests' preference data includes temperature preferences (guests' preferences for temperature settings in different guest room areas), lighting preferences (guests' preferences for brightness, color temperature, and lighting modes), air quality preferences (humidity, ventilation frequency, and air purification settings), time mode preferences (the changing demands of guests for the environment at different times), area usage habits (the usage frequency and methods of guests for different guest room areas), device interaction habits (the usage frequency and methods of guests for various devices in the room), energy usage patterns (guests' energy-saving or comfort preferences), scene switching preferences (the acceptance degree of guests for the adjustment speed of guest room environment data), and circadian rhythm preferences (the work and rest time of guests and the corresponding guest room environment demands).

[0083] The method for selectively activating the environmental control of different guest room areas includes:

[0084] The different guest room areas include a rest area (mainly for sleeping and resting), an entertainment area (for leisure, entertainment, and social activities), a work area (mainly for focused activities such as office work and reading), and a bathing area; it is set that each guest room area respectively contains adjustable environmental parameters (such as temperature, illuminance, and air purifier gear), forming a -dimensional control vector; aiming to minimize energy consumption and maximize comfort, an Actor-Critic framework is selected to build a deep neural network, and the guests' preference data and the guest room environment data are concatenated and fused to form a state vector; the state vector is used as the input data of the deep neural network, and the deep correlation information in the state vector is gradually extracted through the policy network of the fully connected layer. Under the goal of minimizing energy consumption and maximizing comfort, the global optimal control vector is output;

[0085] The energy consumption of the devices under different control vectors is calculated through power, for example: the power consumption of air conditioner temperature adjustment, the power demand for lighting brightness control, the energy consumption of air purifier operation, etc., and it is converted into a negative reward to ensure that energy consumption is preferentially reduced during the iterative optimization process of the control vector; the comprehensive comfort score is calculated according to the guest room environment data, and the Gaussian function is used to measure the deviation between the current guest room environment data and the preset optimal comfort interval, so that the deep neural network can identify the factors that have the greatest impact on comfort, and then optimize the control vector.

[0086] The global optimal control vector is uploaded to the central data pool and sent to the environmental control actuator of the corresponding guest room area through the data bus to adjust the corresponding device states, thereby realizing the selective activation of the environmental control of different guest room areas.

[0087] For example: Environmental control of the main activity area: Prioritize adjusting the environmental parameters of the area where the guest is currently located to achieve the best comfort level; Secondary area maintenance: For areas that the guest has not used but may enter, maintain the equipment in the area in an energy-saving standby state; Inactive area: For areas that the guest has not used for a long time, control the equipment in the area to enter a deep sleep mode.

[0088] The method for designing a personalized environmental parameter change curve includes:

[0089] Define the area boundary and transition zone model to ensure smooth transition of environmental parameters between areas; Identify the explicit physical boundaries based on the physical structure of the guest room, where the physical structure of the guest room includes clear physical partition elements such as walls and partition screens; Naturally form the first layer of boundaries between different areas, automatically identify the first layer of boundaries by analyzing the CAD drawings and 3D models of the guest room, and use it as the basic framework for area division;

[0090] Determine the functional boundaries based on the furniture layout. Different furniture combinations indicate different guest room areas. The bed area is defined as the rest area, the table and chair combination is defined as the work area, the sofa and TV area is defined as the entertainment area, and the combination of washbasin, toilet and shower is defined as the bathing area;

[0091] By identifying different furniture combinations, define the functional boundaries. The functional boundaries are composed of the union of the core furniture edges and the functional activity buffer zones; Define the core furniture edges and the functional activity buffer zones, construct the area transition zone model through the distance weighted interpolation algorithm combined with the cubic spline function, construct the guest preference - area association matrix, analyze the guest activity data and the corresponding environmental requirements, and define the typical scenarios and environmental parameter sets for the guest staying in the hotel guest room. The typical scenarios include check-in scenario, sleep preparation scenario, work scenario and leisure scenario; The parameter sets include temperature, lighting intensity and humidity air ventilation frequency; For example, for the check-in scenario: The guest first enters the room; The environmental parameter set: {Welcome temperature, Welcome lighting, Moderate ventilation}; For the sleep preparation scenario: The guest prepares to rest; The environmental parameter set: {Lower temperature, Dim the light, Increase humidity}; For the work scenario: The guest works in the room; The environmental parameter set: {Bright lighting, Moderate temperature, Frequent air renewal}; For the leisure scenario: The guest relaxes and entertains; The environmental parameter set: {Comfortable temperature, Soft lighting, Moderate humidity};

[0092] Establish a scenario - parameter multi-dimensional target matrix. The elements in the scenario - parameter multi-dimensional target matrix include typical scenarios, different guest room areas and target environmental parameter set types; Define the acceptable range for each target environmental parameter set, adjust the standard target environmental parameter set according to the guest preference data, and analyze the adaptability index of the guest to the change of the guest room environmental data. The higher the value, the better the guest's adaptability to the change of the guest room environmental data, and the lower the value, the more sensitive the guest is to the change of the guest room environmental data;

[0093] Establish an environmental parameter change sensitivity model. Through the environmental parameter change sensitivity model, measure the index of the guest's sensitivity to changes in guest room environmental data. ; Among them, represents the frequency of the guest adjusting parameters in the guest room environmental data; is the index of the parameter, ; represents the change range of the guest room environmental data, which is obtained by weighted averaging the difference between the maximum value and the minimum value of different parameters in the guest room environmental data;

[0094] Calculate the optimal change rate of each parameter in the guest room environmental data ; Among them, represents the preset basic change rate, which is the default value set according to the physical characteristics of different environmental parameters (such as the default temperature is 0.5 °C per minute); represents the typical scenario priority coefficient, which reflects the importance of the current activity. For high-priority scenarios (such as sleep preparation), the value is greater than 1, then the parameter adjustment is accelerated. For low-priority scenarios, the value is less than 1, then the adjustment speed is slowed down;

[0095] Apply the cubic Bézier curve algorithm to design a smooth transition curve according to the index of the guest's sensitivity to changes in guest room environmental data and the optimal change rate of each parameter in the guest room environmental data. Apply specific physical model constraints for different environmental parameters. For example, the temperature change curve adopts the thermodynamic model, and the light change curve adopts the human eye adaptation model; establish a correlation matrix between environmental parameters to achieve a parameter linkage mechanism, and coordinate the guest room environmental data through the parameter smooth transition algorithm at the area junction; and adjust and update the smooth transition curve according to the guest preference data to obtain a personalized environmental parameter change curve.

[0096] According to the personalized environmental parameter change curve and the device power change curve, the system will generate specific control instructions. These instructions not only include the target values of environmental parameters (such as the new temperature, light intensity), but also the change rate (such as "increase the temperature from 22 °C to 24 °C within 30 minutes"). At the same time, the instructions will also consider the limitations of device power to ensure that the system stability will not be affected due to excessive device load.

[0097] Instruction features of smooth transition: Instructions must ensure that there are no excessive power fluctuations during the execution of each device and also avoid mutual interference between devices. For example, the air conditioner and lighting system need to work in coordination. While the temperature gradually rises, the light intensity also gradually increases instead of an immediate jump. These generated smooth transition instructions will be transmitted to the device collaborative control unit through communication protocols (such as Wi-Fi, Zigbee, Bluetooth, etc.). The role of the device collaborative control unit is to transmit the instructions to specific devices and ensure that the devices are adjusted according to a predetermined curve.

[0098] Methods for defining the edges of core furniture and functional activity buffers include:

[0099] The method for defining the edges of core furniture includes defining different furniture combinations corresponding to different guest room areas as the core furniture of that area. For each core furniture, extract its two-dimensional projection contour, construct a polygon boundary representation. For different core furniture, obtain the size and position information of the core furniture through a 3D scanner, calculate the overall contour of the core furniture, and select the corresponding edge definition according to the current state of different furniture combinations;

[0100] Taking the origin at the lower left corner of the guest room, establish a Cartesian coordinate system, project the core furniture data onto the ground plane. For regular-shaped furniture (rectangular beds, square tables, etc.), directly calculate the four-corner coordinates, which include the lower left corner coordinate, upper left corner coordinate, upper right corner coordinate, and lower right corner coordinate, and apply a rotation matrix to process the orientation of the core furniture to obtain its edge; for irregular-shaped furniture, decompose the irregular-shaped furniture (L-shaped sofas, special-shaped tables, etc.) into m basic components and merge the boundaries to obtain its edge; for smooth curved surface furniture (round tables, curved sofas), approximate its edge using parametric curves; the extracted edges are stored in the form of an ordered point set to obtain the edges of the core furniture;

[0101] The method for defining the functional activity buffer includes that the basic buffer width is determined according to guest activity data,

[0102] The shape of the basic buffer is obtained by non-uniform directional expansion according to guest activity data. Adjust the basic buffer width according to different direction coefficients to obtain the widths of the buffer in different directions; for example, for a desk, the buffer in the front side (the direction where the human body is located) is larger (100 - 120 cm), while the buffer in the back side is smaller (20 - 30 cm); guest activity data includes the residence time of guests in different direction areas, the maximum residence time of guests at all direction angles, the number of times guests move along different direction angles, and the total number of times guests move at all direction angles;

[0103] The basic buffer area includes a rest buffer area, a work buffer area, an entertainment buffer area, and a bathing buffer area; the width of the basic buffer area is obtained by presetting the widths of different buffer areas. For example, the rest buffer area: 80 - 100 cm (space required for getting in and out of bed and making the bed); the work buffer area: 70 - 120 cm (space required for sitting, standing up, and moving); the entertainment buffer area: 60 - 80 cm (space for standing use); the bathing buffer area: 50 - 70 cm (space required for bathing).

[0104] The width of the buffer area in different directions is the width of the basic buffer area multiplied by the direction coefficient; the direction coefficient ; where represents any one of the direction angles in different directions; represents the proportion of the staying time of the guest in any one direction area; represents the weight coefficient for adjusting the moving frequency. According to the expert experience method, ; represents the moving frequency;

[0105] Proportion of staying time ; where represents the staying time of the guest at any one direction angle; represents the maximum staying time of the guest at all direction angles; represents the maximum staying time; Moving frequency ; where represents the guest moving along any one direction angle The number of movements; represents the total number of movements of the guest at all direction angles; represents the index of the staying time of the guest at any one direction angle.

[0106] The following main problems existing in the prior art are solved:

[0107] The traditional guest room environment control system regards the entire room as a single area or uses fixed preset areas, and cannot adapt to the real activity patterns of guests;

[0108] The prior art usually divides the buffer area with a unified standard width, without considering the differences in the actual activity data of guests, resulting in low space utilization efficiency and insufficient comfort;

[0109] There is a lack of a systematic method for converting guest activity data into environmental control parameters, and the environmental parameter changes at the area junctions are abrupt, resulting in an inconsistent guest experience;

[0110] The creativity of this solution lies in: integrating the definition of the edges of static furniture with dynamic guest behavior data, establishing a non-uniform direction expansion buffer model based on actual usage data, developing a complete mathematical framework to quantitatively convert behavior data into spatial design parameters, and establishing differential buffer strategies for different functional areas (80 - 100 cm for rest, 70 - 120 cm for work, etc.);

[0111] It should be noted that the design of the direction coefficient is supported by the following existing technologies. This formula draws on the accessibility analysis model in space syntax, combines static space characteristics with dynamic pedestrian flow behavior through weight coefficients. The residence time ratio in the formula is derived from the behavior mapping technology in architecture, which has been widely used in the design of retail and hotel spaces. The movement frequency parameter is based on the activity frequency model in ergonomics, and similar methods have been used in the design of workspaces and the development of human-computer interaction interfaces; The use of a product-sum structure instead of a simple linear sum is based on the non-linear interaction principle in environmental behavior research proposed by the MIT Media Lab, which can more accurately reflect the characteristics of human spatial behavior. The direction coefficient is essentially an application innovation that combines existing spatial behavior analysis methods with environmental control systems, and its mathematical structure has theoretical support;

[0112] Beneficial effects compared to the prior art:

[0113] Through precise furniture boundary definition and dynamic buffer design based on activity data, the functionality of each area is optimized, avoiding the problem in traditional methods where space division is too general and cannot meet personalized needs;

[0114] The buffer is adjusted according to the direction coefficient, which can better adapt to the actual activity needs of guests and avoid space waste; for example, the buffer widths on the front and back sides of the desk are no longer uniform, but are adjusted according to the actual usage habits of guests, making the space layout more in line with actual needs.

[0115] Through smooth transition of area division and dynamic buffer design, guests can enjoy a more comfortable and natural living experience. Especially the transition between different activity areas is smoother, and the environmental change will not make guests feel abrupt or uncomfortable.

[0116] The method for coordinating the operation of different hotel facilities includes:

[0117] Collect the energy consumption data of various hotel equipment under different working conditions, and construct a mathematical model of equipment energy efficiency. The mathematical model of equipment energy efficiency includes the equipment power-load curve, start-stop efficiency curve, and temperature-energy consumption relationship curve. The equipment power-load curve is obtained by the standard segmented test method, and data is obtained through equally spaced test points between 0% and 100%. This method has been widely used in the evaluation of HVAC systems. The polynomial fitting model used in the air conditioning system is derived from the energy efficiency evaluation method of ASHRAE Standard 90.1. The cubic law model (the cubic relationship between power and flow) of fans and pumps is a classic model that has been used in the field of fluid machinery for a long time. These curve fitting techniques have been widely used in building energy management systems.

[0118] The construction method of the start-stop efficiency curve is obtained based on industrial energy efficiency test standards, namely ISO15627 and GB / T21452 for industrial energy efficiency testing standards. The start-up process model of exponential decay and linear combination is derived from the mature theory in the field of motor control. The energy efficiency penalty calculation method has been promoted by the Building Technology Office of the US Department of Energy and incorporated into multiple commercial building energy efficiency evaluation software. The minimum running time determination method is a standard practice in HVAC control systems, mainly used to prevent equipment from being damaged by frequent start-stop.

[0119] The temperature-energy consumption relationship curve is obtained by the environmental temperature impact test process defined by the international standard test method. The international standard test method (AHRI210 / 240), the COP correction model for refrigeration equipment and the efficiency model for heating equipment are widely used in energy efficiency rating systems, such as the energy label in Europe and the Energy Star program in the United States. The query table and interpolation method used in the temperature compensation algorithm are common techniques in industrial control systems and have been implemented in many commercial building automation systems. These models provide a theoretical basis for equipment energy efficiency prediction and are widely used in energy management systems.

[0120] Convert the personalized environmental parameter change curve generated by the gradual adjustment unit into an equipment power change curve. First, the system receives the multi-dimensional environmental parameter target curve (temperature, humidity, light, etc.) through the parameter parser, and applies signal preprocessing technology to eliminate noise and perform legality verification. This process adopts the data processing specifications defined by building automation standard protocols (such as BACnet).

[0121] Secondly, use the physical model conversion engine to convert the environmental parameter requirements into load requirements. The temperature parameter adopts the ASHRAE load calculation method, considering the characteristics of the building envelope, occupancy load, and equipment load; humidity adopts the CIBSE wet load calculation standard; light adopts the IES lighting calculation method; and air quality is based on the ventilation calculation method of European standard EN13779.

[0122] In the third step, device characteristics mapping is applied, and load-power conversion is performed through the device energy efficiency model library established in the early stage. The air conditioning system adopts the part-load performance curve defined by the AHRI standard; the water pump and fan use the flow-power relationship of the ISO 5801 standard; the lighting system uses the power factor mapping of the IEC62442 standard.

[0123] Finally, the power change curves of multiple devices are integrated through a multi-objective optimization algorithm, signal processing technologies such as moving average filtering are applied to smooth the power fluctuations, and power constraint checks are performed to ensure that the total power does not exceed the system capacity. A device complementary and collaborative mechanism is defined. The complementary and collaborative mechanism includes using time-sequence complementarity, implementing space complementarity, and performing source-end complementarity; using time-sequence complementarity means avoiding the overlap of device power peaks to achieve off-peak operation; implementing space complementarity means the collaboration of devices in adjacent areas to reduce boundary energy losses; performing source-end complementarity means selecting the optimal energy combination from multiple energy combinations; based on the collaborative optimization algorithm, device linkage instructions are generated, and the device linkage instructions are sent through the energy management intelligent terminal to coordinate the operation of different hotel devices in cooperation with each other.

[0124] The methods for balancing energy loads include:

[0125] Matching and analyzing the predicted energy demand index in the future time period with the grid electricity price period information. The grid electricity price periods are divided into peak periods (14:00 - 17:00, 19:00 - 22:00), normal periods (8:00 - 14:00, 17:00 - 19:00, 22:00 - 23:00), and valley periods (23:00 - 8:00 the next day). Through the time-sequence matching algorithm, the overlapping area of the highest demand and the highest electricity price is identified, and the energy load is balanced for the time period corresponding to the overlapping area of the highest demand and the highest electricity price; when it is in the valley period of the electricity price and the highest demand in the future is predicted, the energy pre-storage mechanism is activated to store the energy of the hotel guest rooms; a preset grid electricity price threshold is set, and an energy release instruction is set according to the preset grid electricity price threshold during the peak period. When the grid electricity price is greater than or equal to the grid electricity price threshold, the energy release instruction is triggered to release the energy of the hotel guest rooms.

[0126] The preset grid electricity price threshold is set by the expert experience method. Similarly, the preset optimal comfort interval, the preset basic change rate, the widths of different buffers, and the fixed preset area are set.

[0127] In this embodiment, by automatically adjusting the environmental control based on the guest preference data, the unique needs of each guest can be precisely met, making the guest room environment more in line with the individual's living habits. As the number of user check-ins increases, the system will accumulate more detailed preference data, further improving the accuracy of personalized adjustment, continuously optimizing the guest room environment, and providing more accurate services for frequent guests;

[0128] By automatically identifying the physical boundaries and furniture layouts of guest rooms, the system can accurately divide different functional areas and adjust the environment according to the needs of each area. By dynamically adjusting the width and shape of the buffer zone, the system can optimize the space layout according to the guests' activity habits and directional needs, avoiding unnecessary space waste; through refined functional area division, the sense of oppression in the guest room can be alleviated. Especially in smaller guest room spaces, the discomfort caused by unreasonable space layout can be effectively avoided;

[0129] The sudden feeling during area switching in the existing system is avoided, and the guest room environment data can smoothly transition between different areas. Through the transition zone model, the conflicts between the environments of different areas are avoided. Guests will not feel uncomfortable due to sudden light changes or drastic temperature fluctuations during activities, enhancing the overall comfort in the guest room;

[0130] By dynamically adjusting the guest room environment data such as temperature, humidity, and lighting, unnecessary energy waste can be avoided. For example, based on the detection of the guests' actual activities, when the guests leave the room, the system can automatically adjust the temperature and lighting to save energy; when the guests change areas, the system can automatically optimize the energy use to avoid multiple areas being in a high-energy consumption state simultaneously; for different environmental requirements, the system can optimize the energy consumption through intelligent algorithms. For example, the lighting and temperature control in the working area will be automatically adjusted according to the time period of the guests' activities, eliminating the need for manual switching, greatly improving the energy efficiency and energy conservation;

[0131] Guests no longer need to manually adjust various devices to meet their personal needs. The system automatically adjusts the environmental settings of the guest room area according to personal preferences and activity patterns, simplifying the customer operation and enhancing the convenience of check-in. By adapting to the guests' needs in advance and making real-time adjustments, a more considerate service experience can be provided. When guests feel a comfortable and personalized environment, higher customer satisfaction can be obtained.

[0132] Embodiment 2

[0133] Please refer to Figure 2 As shown, for the parts not described in detail in this embodiment, refer to the description content of Embodiment 1. Provide an energy optimization management method for hotel guest rooms, including:

[0134] S1. Build a time-series database cluster, and upload and interact data between each unit through a data bus;

[0135] S2. Adopt a perception layer architecture to integrate multiple sensors to form a perception network, capture presence perception data, and generate a room presence state map based on the presence perception data; the presence perception data includes guest room reservation information data, guest room environment data, and guest information data;

[0136] S3. By analyzing the room occupancy status map, obtain guest preference data; based on the guest preference data and the guest room environment data, use an intelligent optimization algorithm to selectively activate the environmental control of different guest room areas;

[0137] S4. Based on the guest preference data, design personalized environmental parameter change curves for different areas, obtain the hotel equipment power change curve, and send a soft transition instruction for scene switching to the equipment collaborative control unit for execution;

[0138] S5. Establish an energy efficiency model library for hotel equipment. According to the hotel equipment power change curve, adopt an equipment complementary and collaborative mechanism to coordinate the operation of different hotel equipment with each other, and obtain equipment operation data;

[0139] S6. Predict the energy demand index in the future period of time based on the guest preference data, equipment operation data, and personalized environmental parameter change curve; according to the energy demand index, perform energy pre-storage and release during different electricity price periods to balance the energy load.

[0140] Since the electronic device introduced in this embodiment is the electronic device used to implement the energy optimization management system and management method for a hotel guest room in the embodiments of the present application, based on the energy optimization management system and management method for a hotel guest room introduced in the embodiments of the present application, those skilled in the art can understand the specific implementation manners and various variations of the electronic device in this embodiment. Therefore, the specific implementation of how this electronic device implements the method in the embodiments of the present application will not be described in detail here. As long as those skilled in the art implement the electronic device used in the energy optimization management system and management method for a hotel guest room in the embodiments of the present application, it falls within the scope of protection of the present application.

[0141] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula that is closest to the actual situation. The preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.

[0142] The above is only the preferred implementation manner of the present invention. The protection scope of the present invention is not limited to the above embodiments. Any technical solutions falling within the idea of the present invention belong to the protection scope of the present invention. It should be noted that for those ordinary technical users in the technical field, several improvements and refinements made without departing from the principle of the present invention should also be regarded as within the protection scope of the present invention.

Claims

1. An energy optimization management system for hotel guest rooms, characterized in that, Including: A central data pool unit that constructs a time-series database cluster and uploads and interacts data between units through a data bus; A presence perception unit that integrates multiple sensors using a perception layer architecture to form a perception network, captures presence perception data, and generates a room presence state map based on the presence perception data; the presence perception data includes guest reservation information data, guest room environment data, and guest information data; A partitioned environment control unit that obtains guest preference data by analyzing the room presence state map; Based on the guest preference data and the guest room environment data, an intelligent optimization algorithm is used to selectively activate the environmental control of different guest room areas; The method for obtaining the guest preference data includes: Constructing a guest preference prediction model through a spatio-temporal graph neural network, where the guest preference prediction model includes an input layer, a spatial feature extraction layer, a temporal feature extraction layer, a spatio-temporal fusion layer, and an output layer; using the room presence state map as the input data of the input layer of the guest preference model, and analyzing the spatial dependence relationship in the room presence state map through graph convolution in the spatial feature extraction layer; Processing the guest behavior change pattern in the time dimension through a gated recurrent unit in the spatio-temporal fusion layer, and splicing and fusing the obtained spatial dependence relationship and the guest behavior change pattern in the time dimension in the spatio-temporal fusion layer to obtain guest preference data; the guest preference data includes temperature preference, lighting preference, air quality preference, time pattern preference, area usage habit, device interaction habit, energy usage pattern, scene switching preference, and circadian rhythm preference; A gradual adjustment unit that designs personalized environmental parameter change curves for different areas based on the guest preference data, obtains the hotel equipment power change curve, and issues a soft transition instruction for scene switching to the device collaborative control unit for execution; A device collaborative control unit that establishes an energy efficiency model library for hotel equipment, according to the hotel equipment power change curve, adopts a device complementary and collaborative mechanism to coordinate the operation of different hotel equipment with each other, and obtains device operation data; An energy load balancing unit that predicts the energy demand index in the next n time periods according to the guest preference data, device operation data, and personalized environmental parameter change curve; pre-stores and releases energy at different electricity price periods according to the energy demand index to balance the energy load.

2. The energy optimization management system for hotel rooms according to claim 1, characterized in that, The method for capturing the presence perception data includes: Deploying environmental sensors, human activity sensors, and interface devices connected to the hotel management system inside the guest room, integrating the environmental sensors, human activity sensors, and interface devices into the same perception network through a standardized interface, and performing periodic data collection to obtain guest room environment data, guest information data, and guest room reservation information data; integrating the guest room environment data, guest information data, and guest room reservation information data to obtain the presence perception data.

3. The energy optimization management system for hotel rooms according to claim 2, characterized in that, The method for generating the room presence state map includes: Based on the obtained presence perception data, the room presence status is determined using the rule engine method according to the predefined business rules; the room presence status includes idle, reserved but unused, in use, and abnormal status; entity extraction is performed on the room presence status determination result and the presence perception data as the nodes of the room presence status graph, and the logical relationships between entities are used as the edges of the room presence status graph to construct the room presence status graph.

4. The energy optimization management system for hotel rooms according to claim 3, wherein The method for selectively activating the environmental control of different guest room areas includes: The different guest room areas include a rest area, an entertainment area, a work area, and a bathing area; it is set that each guest room area respectively includes M adjustable environmental parameters to form a 4×M-dimensional control vector; aiming at minimizing energy consumption and maximizing comfort, an Actor-Critic framework is selected to build a deep neural network, and the guest preference data and the guest room environmental data are spliced and fused to form a state vector; the state vector is used as the input data of the deep neural network, and the deep correlation information in the state vector is gradually extracted through the policy network of the fully connected layer. Under the goal of minimizing energy consumption and maximizing comfort, the global optimal control vector is output. The global optimal control vector is uploaded to the central data pool and sent to the environmental control actuator of the corresponding guest room area through the data bus to adjust the corresponding device status, thereby realizing the selective activation of the environmental control of different guest room areas.

5. The energy optimization management system for hotel rooms according to claim 4, wherein The method for designing the personalized environmental parameter change curve includes: Define the regional boundary and transition zone model, and identify the explicit physical boundary based on the physical structure of the guest room; the first layer of boundary between different regions is naturally formed, and the first layer of boundary is automatically identified by analyzing the CAD drawings and 3D models of the guest room and used as the basic framework for regional division. Determine the functional boundary based on the furniture layout. Different furniture combinations indicate different guest room areas. The bed area is defined as the rest area, the table and chair combination is defined as the work area, the sofa and TV area is defined as the entertainment area, and the combination of washbasin, toilet, and shower is defined as the bathing area. By identifying different furniture combinations, define the functional boundary. The functional boundary consists of the union of the core furniture edge and the functional activity buffer zone; define the core furniture edge and the functional activity buffer zone, construct the regional transition zone model through the distance weighted interpolation algorithm combined with the cubic spline function, construct the guest preference - area association matrix, analyze the guest activity data and the corresponding environmental requirements, and define the typical scenarios and environmental parameter sets for guests staying in hotel guest rooms. The typical scenarios include check-in scenario, sleep preparation scenario, work scenario, and leisure scenario; the parameter set includes temperature, illumination intensity, and humidity and air ventilation frequency. Establish a scenario - parameter multi-dimensional target matrix. The elements in the scenario - parameter multi-dimensional target matrix include typical scenarios, different guest room areas, and types of target environmental parameter sets; define an acceptable range for each target environmental parameter set, adjust the standard target environmental parameter set according to the guest preference data, and analyze the adaptability index of the guests to the changes in the guest room environmental data. Establish an environmental parameter change sensitivity model. Through the environmental parameter change sensitivity model, an index is used to measure the sensitivity of guests' responses to changes in guest room environmental data; calculate the optimal change rate of each parameter in the guest room environmental data. Apply the cubic Bezier curve algorithm to design a smooth transition curve based on the index of the sensitivity of guests' responses to changes in guest room environmental data and the optimal change rate of each parameter in the guest room environmental data, and apply specific physical model constraints for different environmental parameters; establish a correlation matrix between environmental parameters to implement a parameter linkage mechanism, and coordinate the guest room environmental data through a parameter smooth transition algorithm at the junction of regions; and adjust and update the smooth transition curve based on guests' preference data to obtain a personalized environmental parameter change curve.

6. The energy optimization management system for hotel rooms according to claim 5, characterized in that, The method for defining the core furniture edge and the functional activity buffer area includes: The method for defining the core furniture edge includes defining different furniture combinations corresponding to different guest room areas as the core furniture of that area. For each core furniture, extract its two-dimensional projection contour, construct a polygon boundary representation. For different core furniture, obtain the size and position information of the core furniture through a 3D scanner, calculate the overall contour of the core furniture, and select the corresponding edge definition according to the current state of different furniture combinations. Taking the origin at the lower left corner of the guest room, establish a Cartesian coordinate system, project the core furniture data onto the ground plane. For regular-shaped furniture, directly calculate the four corner coordinates, which include the lower left corner coordinate, the upper left corner coordinate, the upper right corner coordinate, and the lower right corner coordinate, and apply a rotation matrix to process the orientation of the core furniture to obtain its edge; for irregular-shaped furniture, decompose the irregular-shaped furniture into m basic components and merge the boundaries to obtain its edge; for smooth curved surface furniture, approximate its edge using parametric curves; the extracted edges are stored in the form of an ordered point set to obtain the core furniture edge. The method for defining the functional activity buffer area includes that the basic buffer width is determined according to guests' activity data, the basic buffer shape is obtained by non-uniform directional expansion according to guests' activity data, and the width of the adjusted buffer area in different directions is obtained by adjusting the basic buffer width according to different direction coefficients; guests' activity data includes the staying time of guests in different direction areas, the maximum staying time of guests at all direction angles, the number of times guests move along different direction angles, and the total number of times guests move at all direction angles. The basic buffer area includes a rest buffer area, a work buffer area, an entertainment buffer area, and a bathing buffer area.

7. The energy optimization management system for hotel rooms according to claim 6, characterized in that The method for coordinating the operation of different hotel equipment in cooperation with each other includes: Collect the energy consumption data of various hotel equipment under different working conditions, and construct a mathematical model of equipment energy efficiency. The mathematical model of equipment energy efficiency includes an equipment power-load curve, a start-stop efficiency curve, and a temperature-energy consumption relationship curve; the equipment power-load curve is obtained by the standard segmented test method; the construction method of the start-stop efficiency curve is obtained based on the industrial energy efficiency test standard; the temperature-energy consumption relationship curve is obtained by the environmental temperature influence test process defined by the international standard test method. Convert the personalized environmental parameter change curve generated by the gradient adjustment unit into a device power change curve, define a device complementary cooperation mechanism, which includes using time sequence complementarity, implementing space complementarity, and executing source-side complementarity; generate a device linkage instruction based on a cooperative optimization algorithm, and issue the device linkage instruction through the energy management intelligent terminal to coordinate the operation of different hotel devices in cooperation with each other.

8. The energy optimization management system for hotel rooms according to claim 7, characterized in that, The method for balancing the energy load includes: Match and analyze the predicted energy demand index in the next n time periods with the grid electricity price period information. The grid electricity price periods are divided into peak periods, normal periods, and valley periods. Identify the overlapping area of the highest demand and the highest electricity price through a time sequence matching algorithm, and balance the energy load for the period corresponding to the overlapping area of the highest demand and the highest electricity price; when it is in the valley period of the electricity price and the highest demand in the future is predicted, activate the energy pre-storage mechanism to store the energy of the hotel guest rooms; preset a grid electricity price threshold, and set an energy release instruction according to the preset grid electricity price threshold during the peak period. When the grid electricity price is greater than or equal to the grid electricity price threshold, trigger the energy release instruction to release the energy of the hotel guest rooms.

9. An energy optimization management method for hotel guest rooms, applied to the energy optimization management system for hotel guest rooms described in any one of claims 1 to 8, characterized in that, It includes: S1. Construct a time sequence database cluster, and upload and interact data between each unit through a data bus; S2. Integrate multiple sensors using a perception layer architecture to form a perception network, capture presence perception data, and generate a room presence state map based on the presence perception data; the presence perception data includes guest room reservation information data, guest room environment data, and guest information data; S3. Analyze the room presence state map to obtain guest preference data; based on the guest preference data and the guest room environment data, use an intelligent optimization algorithm to selectively activate the environmental control of different guest room areas; S4. Design a personalized environmental parameter change curve for different areas based on the guest preference data, obtain the hotel device power change curve, and issue a soft transition instruction for scene switching to the device cooperative control unit for execution; S5. Establish a hotel device energy efficiency model library, according to the hotel device power change curve, adopt a device complementary cooperation mechanism to coordinate the operation of different hotel devices in cooperation with each other, and obtain device operation data; S6. Predict the energy demand index in the next n time periods according to the guest preference data, device operation data, and personalized environmental parameter change curve; perform energy pre-storage and release according to the energy demand index in different electricity price periods to balance the energy load.

Images