Hotel self-service equipment collaborative management system and method based on Internet of Things

Abstract

The invention discloses a hotel self-service equipment collaborative management system and method based on the Internet of Things, and relates to the technical field of hotel intelligent management, and the method comprises the steps: a sensing module monitors personnel distribution and behavior characteristics in an equipment operation radius in real time through a multi-source sensor network, and generates spatial state data; the scheduling engine module receives the spatial state data, divides a physical space into virtual grids, calculates a service pressure index and generates an equipment state control strategy; an equipment cooperation module responds to the equipment state control strategy, establishes an equipment cluster dynamic health baseline and executes cross-equipment micro-task scheduling and verification; and the user interaction module fuses the biological characteristics and the behavior data to generate a dynamic trust score, and controls equipment service activation. According to the invention, the problem of low efficiency caused by rigid spatial layout, uneven load and fault diffusion of hotel self-service equipment is solved, full-link collaborative optimization from a physical environment to digital resources is realized, the user experience is improved, and the operation and maintenance cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of hotel intelligent management, and in particular to a hotel self-service equipment collaborative management system and method based on the Internet of Things. Background Art

[0002] With the deep penetration of IoT technology in the hotel industry, self-service devices such as self-check-in terminals, smart luggage lockers, and mobile service robots have gradually formed distributed cluster architectures. Existing systems primarily monitor device status through low-power wide-area network protocols such as ZigBee and LoRa, and utilize basic queuing algorithms (such as FCFS) to optimize task allocation. In recent years, multimodal sensor fusion (such as RGB-D cameras and millimeter-wave radar) has been introduced to the field of crowd flow monitoring. Combined with SLAM technology, static environmental maps are constructed to provide a preliminary spatial basis for device placement. At the resource scheduling level, some research has attempted to apply reinforcement learning to device load balancing, such as a dynamic task migration mechanism based on Q-learning, which predicts service bottlenecks using historical load data. However, these systems often focus on optimizing the performance of a single device and lack the ability to collaboratively manage the interaction between device clusters and physical spaces.

[0003] Current technology has three significant flaws: First, the allocation of spatial resources is rigid. The existing system relies on preset equipment layout strategies and cannot dynamically perceive channel congestion caused by overlapping operating areas (such as the intersection of traffic in multi-device interaction areas during peak hours). Although some solutions use visual sensors to detect queue lengths, they have not established a quantitative model for spatial overlapping areas, and lack a real-time morphological control mechanism for deformable equipment (such as retractable counters), resulting in low physical space utilization. Second, service pressure response is delayed. Traditional scheduling algorithms trigger task migration based on fixed thresholds and fail to integrate multi-dimensional dynamic factors (such as equipment response delay, task urgency, and traffic movement trajectories) to construct a pressure index model. This results in coarse granularity in the disassembly of high-load areas, and the selection of migration targets only considers static equipment parameters (such as CPU occupancy), ignoring real-time differences in the health status of similar equipment. Third, safety verification and energy efficiency control are separated. Existing cross-device verification mostly uses simple redundant comparison, and has not established a trusted execution environment (TEE) driven by a dynamic health baseline. In addition, the device state switching strategy (sleep / activation) usually only responds to electricity price signals and does not incorporate the decision-making dimensions of device risk level and traffic pressure. This can easily lead to a chain reaction of service interruptions during peak hours due to the forced activation of high-risk devices. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a hotel self-service equipment collaborative management system based on the Internet of Things, which solves the technical problem of realizing intelligent collaborative management of hotel self-service equipment through Internet of Things technology, dynamically optimizing equipment layout and task scheduling, so as to alleviate service area congestion, improve equipment response efficiency and ensure system operation reliability.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a hotel self-service equipment collaborative management system based on the Internet of Things, which includes:

[0008] The perception module is used to monitor the distribution and behavior characteristics of people within the equipment's operating radius in real time through a multi-source sensor network to generate spatial status data;

[0009] a scheduling engine module, configured to receive the space status data, divide the physical space into virtual grids, calculate the service pressure index, and generate a device status control strategy;

[0010] A device collaboration module, configured to respond to the device status control strategy, establish a dynamic health baseline for the device cluster, and perform cross-device microtask scheduling and verification;

[0011] The user interaction module is used to integrate biometric and behavioral data to generate dynamic trust scores and control device service activation.

[0012] As a preferred solution of the Internet of Things-based hotel self-service equipment collaborative management system described in the present invention, the sensing module includes a spatial overlap sensing unit, which is equipped with a time-of-flight sensor array to scan the density distribution, movement speed, and height of people in real time, and generates a regional congestion signal when the overlapping area of ​​multiple device operation areas exceeds a preset spatial overlap threshold;

[0013] a morphology adaptive control unit, in response to the regional congestion signal, executing an initial reconstruction task execution sequence, controlling the adjustable morphology device to perform physical displacement and mechanical structure adjustment to expand the channel space; wherein the initial reconstruction task execution sequence evaluates the urgency of tasks through a scheduling engine, defers non-urgent tasks below an urgency threshold, and prioritizes tasks above the urgency threshold;

[0014] The physical displacement includes moving the equipment expansion channel sideways according to the environmental assessment results and adjusting the equipment height according to the estimated height of the personnel;

[0015] The perception module packages the adjusted equipment height and expansion channel into space status data and outputs it to the scheduling engine module.

[0016] As a preferred solution of the hotel self-service equipment collaborative management system based on the Internet of Things described in the present invention, the scheduling engine module includes dividing the expanded channel space into virtual grids with adjustable side lengths, and using a hierarchical partitioning method to subdivide the grids based on personnel density;

[0017] Calculate the service pressure index of each grid based on device response delay, historical service processing time, the number of people currently waiting in the grid, the priority coefficient in the task execution sequence, and the complexity of the current task.

[0018] When the service pressure index exceeds the preset pressure threshold, the high-load area functions are decomposed into migratable service units, and the weighted cosine similarity model is used to select alternative devices to generate a migration strategy and output it to the device collaboration module.

[0019] As a preferred solution of the hotel self-service equipment collaborative management system based on the Internet of Things described in the present invention, the equipment collaborative module includes collecting operating indicators of similar equipment and generating a dynamic health baseline through cluster analysis of historical data of equipment of the same model;

[0020] When the operating indicators of a single device deviate from the dynamic health baseline by more than the preset deviation threshold, the multi-device collaborative verification mechanism is triggered. If the verification succeeds, the health baseline weight is updated; if the verification fails, the deviation index is calculated;

[0021] The equipment risk level is marked according to the deviation index and fed back to the scheduling engine module.

[0022] As a preferred solution of the Internet of Things-based hotel self-service equipment collaborative management system described in the present invention, the scheduling engine module further includes converting the equipment risk level into a risk attenuation coefficient as the X-axis, converting the crowd flow prediction data into a crowd flow pressure index as the Y-axis, and converting the real-time electricity price signal into an electricity price cost factor as the Z-axis, and constructing a three-dimensional decision space based on the X-axis, Y-axis, and Z-axis;

[0023] Generate device status instructions in a three-dimensional decision space using the Q-learning algorithm. When a sleep instruction is executed, a service interrupt signal with a timestamp is generated, locking the target device task port and rejecting new tasks.

[0024] The tasks interrupted by the service interruption signal are decomposed into the smallest migratable operation units, and a directed acyclic graph is generated according to the execution order and data flow.

[0025] As a preferred solution of the hotel self-service equipment collaborative management system based on the Internet of Things described in the present invention, wherein: the equipment collaborative module further includes, in response to the equipment status instruction, constructing a verification token including the equipment identification code, timestamp and risk level;

[0026] The verification token is encoded into a matrix QR code and divided into three data areas. A device node index network is constructed through a dynamic position matching algorithm, and the spatial coordinates of the nearest available device are returned in real time.

[0027] As a preferred solution of the Internet of Things-based hotel self-service equipment collaborative management system described in the present invention, the user interaction module includes pushing a QR code and the device's spatial location to the user terminal. When the device receives at least two data zone fragments and successfully decrypts them, it collects user biometrics and behavioral data in real time to generate a dynamic trust score, and executes user requests based on the score and device status.

[0028] In a second aspect, the present invention provides a collaborative management method for hotel self-service equipment based on the Internet of Things, comprising:

[0029] The time-of-flight sensor array scans the density, movement speed, and height of people within the device's operating radius in real time, calculates the overlapping area of ​​multiple device operating areas, and generates a regional congestion signal if it exceeds a preset threshold;

[0030] Respond to congestion signals, postpone non-urgent tasks, prioritize high-priority requests, control the physical displacement of scalable equipment, and package the adjusted channel space, personnel trajectory, and equipment status into space status data, which is input into the scheduling engine module;

[0031] The physical space is divided into dynamic virtual grids. The service pressure index is calculated based on the number of people waiting in the grid, the task priority coefficient, the device response delay and the task complexity. If the service pressure index exceeds the service pressure threshold;

[0032] The high-load area functions are decomposed into independent, relocatable service units. A weighted cosine similarity model is used to select alternative equipment and output a migration strategy. A three-dimensional decision space is constructed and a Q-learning algorithm is used to dynamically determine the equipment status, avoiding high-risk scenarios and optimizing energy consumption.

[0033] Collect device operating indicators and generate a health baseline for similar devices through cluster analysis. When the indicators of a single device deviate from the baseline, the encryption verification mechanism is triggered to generate a fragmented QR code containing the device code and risk level. Combined with user biometrics and behavioral data, a dynamic trust score is generated to control device service activation permissions.

[0034] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of a hotel self-service equipment collaborative management system based on the Internet of Things as described in the first aspect of the present invention.

[0035] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of a hotel self-service equipment collaborative management system based on the Internet of Things as described in the first aspect of the present invention.

[0036] The beneficial effects of the present invention are as follows: the present invention monitors the personnel density distribution in the equipment operation area in real time through the spatial overlap perception unit of the perception module, generates a congestion signal when it is detected that the overlapping area of ​​multiple equipment operation areas exceeds the threshold, and dynamically adjusts the equipment layout and task priority by the morphological adaptive control unit, solving the problem that the traditional system cannot adaptively optimize the physical space layout and service response sequence; the scheduling engine module divides the expanded channel space into a dynamic virtual grid, identifies high-load areas based on the service pressure index and disassembles them into migratable service units, and selects alternative equipment through the weighted cosine similarity model, breaking through the static resource allocation mode and realizing flexible scheduling of service capabilities; the equipment collaboration module establishes a dynamic health baseline for the equipment through cluster analysis, uses a multi-device encryption verification mechanism to identify the fault risk level, and combines the three-dimensional decision space training Q-learning model to output equipment status instructions, while ensuring service reliability and optimizing energy costs; the user interaction module takes into account both service convenience and security through sharded QR code verification and dynamic trust scoring mechanism. The system realizes the full-link collaboration of hotel self-service equipment from physical environment to digital resources through closed-loop management of dynamic reconstruction of physical space → intelligent migration of service load → collaborative optimization of equipment status → precise response to user requests, effectively solving the problem of low service efficiency caused by rigid layout, uneven load and fault propagation. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 This is a flow chart of a hotel self-service equipment collaborative management system based on the Internet of Things. DETAILED DESCRIPTION

[0039] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0040] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0041] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it constitute a separate or selective embodiment that is mutually exclusive with other embodiments.

[0042] Reference Figure 1 , is an embodiment of the present invention, which provides a hotel self-service equipment collaborative management system based on the Internet of Things, including the following steps:

[0043] M1, perception module, is used to monitor the distribution and behavior characteristics of people within the equipment operation radius in real time through a multi-source sensor network to generate spatial status data.

[0044] Specifically, the perception module includes a spatial overlap perception unit and a morphology adaptive control unit;

[0045] The spatial overlap sensing unit deploys a time-of-flight sensor array and scans the density distribution of people, their movement speed, and estimated height of people within the operating radius of the device in real time.

[0046] The overlapping area of ​​multiple equipment operation areas is monitored in real time based on the distribution of personnel density. When the overlapping area of ​​multiple equipment operation areas is detected to exceed the preset spatial overlap threshold, a regional congestion signal is generated. If the preset spatial overlap threshold is exceeded, the scheduling engine processes the tasks according to the default task sequence (such as first-come, first-served) without priority adjustment.

[0047] Among them, it should be explained that the setting of the preset spatial overlap threshold takes into account the following factors: based on the correlation between personnel density and movement speed; ensuring the minimum operating space between devices; the total time from detecting congestion to completing equipment adjustment (for example, the system needs to respond within 10 seconds, and the threshold needs to reserve buffer space); and inferring the critical point of overlapping area through historical congestion events (for example, data from a hotel shows that the complaint rate increases by 50% when the overlapping area is ≥35%). The specific calculation is: S th =θ·(D max ·v avg ·t response ), where D max is the maximum permissible occupant density (e.g. 1.2 persons / m2), v avg is the average moving speed (such as 0.8m / s), t responseis the system response time, and θ is the safety factor.

[0048] The morphology adaptive control unit responds to the regional congestion signal, the perception module responds to the regional congestion signal, and controls the adjustable morphology device to perform physical displacement; at the same time, the regional congestion signal is output to the scheduling engine module.

[0049] The scheduling engine module evaluates the urgency and importance of tasks, generates an initial reconstruction task execution sequence, and sends it to each self-service device to expand the channel space through mechanical structure adjustment;

[0050] It should be noted that the initial reconstructed task execution sequence is based on the current service task list. The scheduling engine evaluates the urgency and importance of each task. When a regional congestion signal appears, it automatically postpones non-urgent tasks (such as cleaning, maintenance, etc.) below the preset emergency threshold, and gives priority to high-priority user requests (such as check-in, check-out, etc.) above the preset emergency threshold; the reconstructed task sequence is fed back to each self-service device in the system to ensure that all self-service devices execute in the new priority order.

[0051] It should also be noted that the physical displacement of adjustable morphology equipment is controlled by the fact that when the perception module detects a regional congestion signal, the morphology adaptive control unit is immediately activated. The system evaluates the environment around the equipment, including the location of existing equipment, the density of people, and the best adjustment plan. By controlling adjustable morphology equipment such as retractable self-service counters, specifically:

[0052] Based on the assessment results, counters or other equipment will be moved sideways to expand the main aisle and guide the flow of people;

[0053] The morphology adaptive control unit changes the height of the device based on the estimated height of the person, so that users of different heights can perform self-service operations.

[0054] The perception module packages the adjusted device height and expansion channel into space status data and outputs it to the scheduling engine module as the initial input parameters for virtual grid division, ensuring that the grid boundaries are synchronized with real-time physical space changes.

[0055] In summary, the spatial overlap perception unit scans the overlapping status of the personnel density distribution and the equipment operation area in real time, and generates a congestion signal when the overlapping area exceeds the threshold, which solves the technical problem that traditional systems cannot dynamically perceive physical space congestion; after the morphological adaptive control unit responds to the signal, on the one hand, it postpones non-urgent tasks (such as cleaning) and gives priority to high-priority requests (such as check-in), directly optimizing the efficiency of service resource allocation; on the other hand, it controls the physical displacement of the retractable equipment (such as moving the counter sideways to expand the channel) and height adjustment, realizing the dynamic reconstruction of the physical space, alleviating crowd congestion while improving the operational convenience of users of different heights, and synchronizing the real-time spatial status data to the scheduling engine to provide accurate physical environment mapping for dynamic grid division.

[0056] M2, the scheduling engine module, is used to receive space status data, divide the physical space into virtual grids, calculate the service pressure index, and generate the equipment status control strategy.

[0057] M3, the device collaboration module, is used to respond to device status control strategies, establish a dynamic health baseline for the device cluster, and perform cross-device microtask scheduling and verification.

[0058] Specifically, the expanded channel space is divided into virtual grids with adjustable side lengths, and a hierarchical partitioning method is used to generate multiple virtual grids. The specific process is to create a preliminary uniform grid, which is then adjusted based on the population density. When there is still a regional congestion signal in any grid, the grid is further subdivided into smaller sub-grids to better manage the flow of people.

[0059] Based on the historical service time of device response delay, the real-time number of people waiting in the current grid, the personnel flow in the environment of each grid, the priority coefficient P in the initial reconstruction task execution sequence, and the preset task complexity weight table, the service pressure index of each grid is calculated:

[0060]

[0061] Where W is the current number of waiting people, P is the priority coefficient of the urgency calculation in the initial reconstruction task execution sequence, R is the device response delay, T avg is the weighted average of the historical service processing time, and C is the complexity of the current task.

[0062] After all grids have calculated the service pressure index, the scheduling engine module determines whether the service pressure index of each grid exceeds the preset service pressure threshold. When the service pressure index exceeds the preset pressure threshold, it is automatically marked as a high-load area and the high-load area function is decomposed into migratable service units. The alternative device is selected as the migration target. The migration strategy generated after selecting the alternative device is directly output to the device collaboration module.

[0063] It should be noted that the preset service pressure threshold is set based on multi-dimensional dynamic balance requirements: by statistically analyzing the historical service data of the equipment cluster (such as average task processing time and congestion frequency during peak hours), the maximum tolerable load of the system in a stable state is determined; if historical data shows that when W ≥ 5 people and R ≥ 2 minutes, user satisfaction drops by 20%, then the threshold needs to be set before this critical point.

[0064] High-priority tasks (such as check-in / check-out) have a low tolerance for response delays (for example, when P ≥ 0.8, R ≤ 1 minute), and require a threshold to trigger immediate resource migration. If P·R > 1.5, which may lead to complaints, the preset service pressure threshold is set to 1.5.

[0065] It should be noted that the disassembly into migratable service units is to identify the functional modules it supports, such as payment, identity authentication, order management, etc. Each function will be defined as an independent service unit to ensure that each module has the ability to run independently and a standard interface.

[0066] It should also be noted that the selection of replacement devices as migration targets uses a weighted cosine similarity model to calculate the similarity between devices. The selection of replacement devices follows the following principles: multiple devices with a similarity higher than 80% and no load are given priority, and the selected devices are sorted from large to small according to similarity, excluding devices that are currently in dormant state, and the device with the highest similarity is selected as the migration target.

[0067] After the scheduling engine module outputs the migration strategy, the device collaboration module immediately responds by collecting operational indicators of similar devices. These indicators include device operating rate (the ratio of active to inactive time of a device), failure rate (the number of device failures within a certain period of time), service response time (the time from user request to response), user interaction count (the frequency of user operations on the device), and resource usage (such as CPU and memory usage).

[0068] By clustering and analyzing historical data of devices of the same model, the mean of performance indicators is dynamically generated as a health benchmark, generating a dynamic health baseline;

[0069] Specifically, we extract historical data using an improved DBSCAN algorithm, density-based clustering, and a time series sliding window. We segment data by hour or day, dynamically identifying normal clusters and abnormal outliers in device status, and introducing a dynamic attenuation factor to give more weight to recent data. For example, the weight of the past 24 hours' data is 0.7, while that of historical data is 0.3. This enhances sensitivity to sudden performance fluctuations.

[0070] Calculate the mean and confidence interval of each indicator for the normal cluster after clustering as the dynamic health baseline: service response time baseline = normal cluster mean ± 2 times standard deviation;

[0071] The Mahalanobis distance is used to measure the deviation of new data points from the baseline to resolve the interference caused by the correlation between indicators. The exponentially weighted moving average model is used to continuously adjust the baseline and set the forgetting factor so that the baseline can slowly adapt to the natural degradation of device performance.

[0072] When the difference between the operating indicators of a single device and the dynamic health baseline exceeds the preset deviation threshold, the multi-device collaborative verification mechanism is triggered. The monitored deviation is transmitted to the device collaboration module, and the parallel verification process is started. The encryption verification task is distributed to three similar devices. The target device executes the original task for encryption, and the remaining devices execute the transformed task for encryption. The encrypted results are returned for homomorphic encryption comparison. When the verification is successful, the health baseline weight is updated and the device is marked as normal.

[0073] When verification fails, calculate the deviation index DI of the three devices:

[0074]

[0075] in, is the encryption result between the target device and the i-th verification device, M i is the maximum theoretical deviation value of the i-th task, Corr(T i ,T ist ) is the current task timing T i Comply with historical timing T ist Pearson correlation coefficient, NoiseW(S i ) is the environmental noise weight.

[0076] Mark the risk level of the equipment, specifically:

[0077] When the deviation index is less than or equal to the first deviation threshold, check whether the timing is compliant. If the timing is not compliant, it is medium risk. If the timing is compliant, check whether the noise is matched. If the noise is not matched, it is high risk.

[0078] When the deviation index is less than or equal to the second deviation threshold and greater than the first deviation threshold, it is judged as low risk;

[0079] When the deviation index is less than or equal to the third deviation threshold and greater than the second deviation threshold, it is judged as medium risk;

[0080] When the deviation index is greater than the third deviation threshold, it is judged as high risk.

[0081] It should be noted that the deviation threshold is based on a dual analysis of the device's functional safety level and the historical deviation distribution: high-risk functions (such as payment authentication) require stricter thresholds, while low-risk functions (such as information query) can be relaxed; the 90% (high risk), 75% (medium risk), and 50% (low risk) quantiles of the deviation index of similar devices are statistically used as the initial threshold.

[0082] For example, in a payment authentication scenario, the first deviation threshold (low risk) can be set to 0.1, allowing slight clock drift; the second deviation threshold (medium risk) can be set to 0.3, which may be caused by temporary network delays; the third deviation threshold (high risk) can be set to 0.5. Exceeding this value is very likely a hardware failure or malicious attack.

[0083] The risk level of the target device is output to the scheduling engine module. At the same time, the risk level is fed back into the migration strategy, and devices with medium and high risk levels are marked as high-risk devices and excluded from the optional migration target pool.

[0084] Furthermore, the scheduling engine module further executes the system to combine equipment health risk levels, crowd flow forecast data, and real-time electricity price signals to construct a three-dimensional decision space;

[0085] Dimension 1: Risk level of all devices; Dimension 2: Crowd flow prediction data from the perception module; Dimension 3: Real-time electricity price signals provided by the power grid;

[0086] The discrete risk level is calculated by α r =e -λ·Level Converted to risk attenuation coefficient α r As the X-axis, the crowd flow prediction data is passed through Convert the crowd pressure index as the Y axis and use the real-time electricity price signal Convert the electricity price cost factor as the Z axis to construct a three-dimensional decision space;

[0087] Among them, α r is the risk attenuation coefficient, with a continuous value of 0 to 1; λ is the preset risk sensitivity coefficient, and Level is the equipment risk level, with discrete values ​​of: low risk = 1, medium risk = 2, high risk = 3; P h is the crowd pressure index, k is the crowd growth slope, W is the real-time number of people waiting, W0 is the preset crowd inflection point threshold (set by collecting crowd density data of the hotel at different time periods for a long time and counting the spatial saturation critical point of the distribution of personnel), β e is the electricity price cost factor, normalized value; E real is the real-time electricity price, E base is the preset benchmark electricity price, μ is the basic electricity price weight, γ is the peak-valley electricity price penalty coefficient, I peak It is the peak and valley period indicator, 1 = peak, 0 = valley.

[0088] A three-dimensional decision model is trained using the Q-learning algorithm to switch device states, including sleep, active, and power-limited.

[0089] It should be noted that the vectors of the three-dimensional decision space are collected in real time and input into the pre-trained Q-network. The network outputs the expected long-term benefits of each action and selects the action that maximizes the benefits.

[0090] When the risk attenuation coefficient is greater than the risk threshold and the crowd pressure index is less than the demand threshold, avoid high-risk and low-demand scenarios and output a sleep command;

[0091] When the crowd pressure index is greater than or equal to the demand threshold and the electricity price cost factor is less than the cost threshold, in a high-demand, low-cost scenario, an activation instruction is output;

[0092] When the risk attenuation coefficient and the crowd pressure index are both in the middle range, balance the risk and demand and output power limit instructions for each device;

[0093] It should be noted that the risk threshold refers to ISO 13849 (machinery safety) or the financial industry's fault tolerance requirements for critical equipment.

[0094] The demand threshold is based on the service level agreement, ensuring that 95% of users have a waiting time of less than 2 minutes, and the crowd pressure index threshold corresponding to the required number of device activations is inferred.

[0095] The cost threshold is based on the energy budget constraint. Based on the hotel's operating budget, an upper limit on the electricity cost ratio is set to calculate the cost threshold; at the same time, dynamic electricity price response is combined with the grid's time-of-use electricity price.

[0096] When the three-dimensional decision space outputs a sleep instruction, a service interruption signal with a timestamp is generated, which is pushed to the device collaboration module through a low-latency message queue, and the task receiving port of the target device is synchronously locked to reject new task injection.

[0097] Analyze the tasks interrupted by the service interruption signal and decompose them into the smallest atomic units according to the smallest migratable operation units (for example, the check-out task is decomposed into: [identity authentication → bill query → deduction → invoice generation]). Generate a directed acyclic graph based on the execution order of the atomic units and the data flow, and save the path order. The migration strategy can reuse the saved directed acyclic graph (DAG) to ensure the consistency of the atomic unit order during task migration. When the same instruction is issued again, it is directly decomposed according to the directed acyclic graph.

[0098] According to the different instructions output by the three-dimensional decision space and the activation instructions, the device to be activated is directly marked as an available device. A verification token is constructed according to the current instruction. The verification token includes the device identification code of the available device, the current timestamp, and the device risk level. The verification token is encoded as a matrix QR code, which is divided into three data areas. At least two fragments need to be decrypted to restore it.

[0099] While encoding into a QR code, a dynamic location matching algorithm is used to build an index network with each device as a node. Each node is connected to its real-time location and status value. Available devices adjust status information in real time based on active status and fault conditions. The user's location is obtained through the sensor network, and the index network is queried in real time. The spatial coordinates of the nearest available device are returned, and the spatial location of the available device is output. The QR code and spatial location are pushed to the user's mobile phone through the hotel APP or SMS.

[0100] In summary, adaptive virtual grids are divided based on spatial status data, and the load of each area is quantified through the service pressure index, breaking through the limitations of static area management. When the service pressure index exceeds the service pressure threshold, the functions of the high-load area are disassembled into independent migratable service units (such as payment and identity authentication), and the weighted cosine similarity model is used to select alternative devices, realizing the elastic migration of service capabilities, avoiding system bottlenecks caused by overload of a single device, and ensuring migration reliability by excluding high-risk devices.

[0101] A dynamic health baseline is established through cluster analysis. When a single device's operating indicators deviate from the baseline, a multi-device collaborative verification mechanism is triggered. Encrypted tasks are distributed for homomorphic encryption comparison, eliminating the risk of misjudgment in traditional single-point fault detection. Device risks are graded (low, medium, and high) based on deviation indexes, enabling refined fault warnings. A Q-learning model is trained to output device status commands (sleep / activate / limit power) based on a three-dimensional decision space (risk level, traffic pressure, and real-time electricity prices), optimizing energy costs while ensuring service continuity. For example, high-risk, low-demand devices can be put into hibernation to reduce O&M risks, while high-demand, low-cost devices can be activated to improve resource utilization.

[0102] M4, user interaction module, is used to integrate biometric and behavioral data to generate dynamic trust scores and control device service activation.

[0103] After the user obtains the QR code, the user shows the QR code to the corresponding device. The decryption module embedded in the device receives the fragments through at least two data areas, merges them into complete information, and confirms the user's device request.

[0104] When the QR code is successfully unlocked, the user's biometric features (such as fingerprints and facial recognition) and behavioral data (such as operating habits) are collected in real time. At the same time, privacy protection mechanisms (such as data anonymization) are used to protect user information. A dynamic trust score is generated based on the device location and time period. The system decides whether the device will execute the user request based on the trust score and the current device status, and finally outputs the processing results to the user.

[0105] In summary, the sharded QR code verification token and dynamic location matching algorithm ensure that users can quickly locate the nearest available device and complete security authentication; the integration of biometric and behavioral data generates a dynamic trust score to control service activation, achieving a balance between convenience and security, preventing unauthorized access while reducing the operation steps for legitimate users.

[0106] This embodiment also provides a hotel self-service equipment collaborative management method based on the Internet of Things, including:

[0107] The time-of-flight sensor array scans the density, movement speed, and height of people within the device's operating radius in real time, calculates the overlapping area of ​​multiple device operating areas, and generates a regional congestion signal if it exceeds a preset threshold;

[0108] Respond to congestion signals, postpone non-urgent tasks, prioritize high-priority requests, control the physical displacement of scalable equipment, and package the adjusted channel space, personnel trajectory, and equipment status into space status data, which is input into the scheduling engine module;

[0109] The physical space is divided into dynamic virtual grids. The service pressure index is calculated based on the number of people waiting in the grid, the task priority coefficient, the device response delay and the task complexity. If the service pressure index exceeds the service pressure threshold;

[0110] The high-load area functions are decomposed into independent, relocatable service units. A weighted cosine similarity model is used to select alternative equipment and output a migration strategy. A three-dimensional decision space is constructed and a Q-learning algorithm is used to dynamically determine the equipment status, avoiding high-risk scenarios and optimizing energy consumption.

[0111] Collect device operating indicators and generate a health baseline for similar devices through cluster analysis. When the indicators of a single device deviate from the baseline, the encryption verification mechanism is triggered to generate a fragmented QR code containing the device code and risk level. Combined with user biometrics and behavioral data, a dynamic trust score is generated to control device service activation permissions.

[0112] This embodiment also provides a computer device, which is suitable for a hotel self-service equipment collaborative management system based on the Internet of Things, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement a hotel self-service equipment collaborative management system based on the Internet of Things as proposed in the above embodiment.

[0113] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0114] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements a hotel self-service equipment collaborative management system based on the Internet of Things as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0115] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A hotel self-service equipment collaborative management system based on the Internet of Things, characterized by: include, The perception module is used to monitor the distribution and behavior characteristics of people within the equipment's operating radius in real time through a multi-source sensor network to generate spatial status data; a scheduling engine module, configured to receive the space status data, divide the physical space into virtual grids, calculate the service pressure index, and generate a device status control strategy; A device collaboration module, configured to respond to the device status control strategy, establish a dynamic health baseline for the device cluster, and perform cross-device microtask scheduling and verification; The user interaction module is used to integrate biometric and behavioral data to generate dynamic trust scores and control device service activation.

2. The hotel self-service equipment collaborative management system based on the Internet of Things according to claim 1, characterized in that: The sensing module includes a spatial overlap sensing unit, which is equipped with a time-of-flight sensor array to scan the density distribution, movement speed and height of people in real time, and generates a regional congestion signal when the overlapping area of ​​multiple device operation areas exceeds a preset spatial overlap threshold; a morphology adaptive control unit, in response to the regional congestion signal, executing an initial reconstruction task execution sequence, controlling the adjustable morphology device to perform physical displacement and mechanical structure adjustment to expand the channel space; wherein the initial reconstruction task execution sequence evaluates the urgency of tasks through a scheduling engine, defers non-urgent tasks below an urgency threshold, and prioritizes tasks above the urgency threshold; The physical displacement includes moving the equipment expansion channel sideways according to the environmental assessment results and adjusting the equipment height according to the estimated height of the personnel; The perception module packages the adjusted equipment height and expansion channel into space status data and outputs it to the scheduling engine module.

3. The hotel self-service equipment collaborative management system based on the Internet of Things as claimed in claim 2, characterized in that: The scheduling engine module includes dividing the expanded channel space into virtual grids with adjustable side lengths, and using a hierarchical partitioning method to subdivide the grids based on personnel density; Calculate the service pressure index of each grid based on device response delay, historical service processing time, the number of people currently waiting in the grid, the priority coefficient in the task execution sequence, and the complexity of the current task. When the service pressure index exceeds the preset pressure threshold, the high-load area functions are decomposed into migratable service units, and the weighted cosine similarity model is used to select alternative devices to generate a migration strategy and output it to the device collaboration module.

4. The hotel self-service equipment collaborative management system based on the Internet of Things as claimed in claim 3, characterized in that: The equipment collaboration module includes collecting operating indicators of similar equipment and generating a dynamic health baseline through cluster analysis of historical data of equipment of the same model; When the operating indicators of a single device deviate from the dynamic health baseline by more than the preset deviation threshold, the multi-device collaborative verification mechanism is triggered. If the verification succeeds, the health baseline weight is updated; if the verification fails, the deviation index is calculated; The equipment risk level is marked according to the deviation index and fed back to the scheduling engine module.

5. The hotel self-service equipment collaborative management system based on the Internet of Things according to claim 4, characterized in that: The scheduling engine module further includes converting the equipment risk level into a risk attenuation coefficient as an X-axis, converting the crowd flow prediction data into a crowd flow pressure index as a Y-axis, and converting the real-time electricity price signal into an electricity price cost factor as a Z-axis, and constructing a three-dimensional decision space based on the X-axis, Y-axis, and Z-axis; Generate device status instructions in a three-dimensional decision space using the Q-learning algorithm. When a sleep instruction is executed, a service interrupt signal with a timestamp is generated, locking the target device task port and rejecting new tasks. The tasks interrupted by the service interruption signal are decomposed into the smallest migratable operation units, and a directed acyclic graph is generated according to the execution order and data flow.

6. The hotel self-service equipment collaborative management system based on the Internet of Things according to claim 5, characterized in that: The device collaboration module further includes, in response to the device status instruction, constructing a verification token including a device identification code, a timestamp, and a risk level; The verification token is encoded into a matrix QR code and divided into three data areas. A device node index network is constructed through a dynamic position matching algorithm, and the spatial coordinates of the nearest available device are returned in real time.

7. The hotel self-service equipment collaborative management system based on the Internet of Things according to claim 6, characterized in that: The user interaction module includes pushing the QR code and the device's spatial location to the user terminal. When the device receives at least two data zone fragments and successfully decrypts them, it collects the user's biometric and behavioral data in real time to generate a dynamic trust score, and executes the user request based on the score and device status.

8. A collaborative management method for hotel self-service equipment based on the Internet of Things, based on the collaborative management method for hotel self-service equipment based on the Internet of Things according to any one of claims 1 to 7, characterized in that: include, The time-of-flight sensor array scans the density, movement speed, and height of people within the device's operating radius in real time, calculates the overlapping area of ​​multiple device operating areas, and generates a regional congestion signal if it exceeds a preset threshold; Respond to congestion signals, postpone non-urgent tasks, prioritize high-priority requests, control the physical displacement of scalable equipment, and package the adjusted channel space, personnel trajectory, and equipment status into space status data, which is input into the scheduling engine module; The physical space is divided into dynamic virtual grids. The service pressure index is calculated based on the number of people waiting in the grid, the task priority coefficient, the device response delay and the task complexity. If the service pressure index exceeds the service pressure threshold; The high-load area functions are decomposed into independent, relocatable service units. A weighted cosine similarity model is used to select alternative equipment and output a migration strategy. A three-dimensional decision space is constructed and a Q-learning algorithm is used to dynamically determine the equipment status, avoiding high-risk scenarios and optimizing energy consumption. Collect device operating indicators and generate a health baseline for similar devices through cluster analysis. When the indicators of a single device deviate from the baseline, the encryption verification mechanism is triggered to generate a fragmented QR code containing the device code and risk level. Combined with user biometrics and behavioral data, a dynamic trust score is generated to control device service activation permissions.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the hotel self-service equipment collaborative management system based on the Internet of Things according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a hotel self-service equipment collaborative management system based on the Internet of Things according to any one of claims 1 to 7 are implemented.

Images