Intelligent hotel environment governance evaluation method integrating ESG indexes

Abstract

The invention discloses a hotel environment governance intelligent evaluation method integrating ESG indexes, and relates to the technical field of hotel environment monitoring, and the method comprises the following steps: collecting multi-source environment data in real time, and obtaining hotel data and guest room check-in information by deploying Internet of Things sensing equipment and docking with an existing hotel management system; based on the obtained guest room check-in state information, the number of check-in rooms is counted according to set time slices, and the real-time check-in rate of each time slice is calculated; performing standard unit conversion on the acquired environment data, and combining the obtained occupancy rate information to form a total environment load vector; matching a preset parameter according to the hotel type, and if no matching type exists, calculating to obtain an optimal parameter group of the hotel; on the basis of the parameters, the load efficiency of each time slice is calculated firstly, and then a DO-ELE coefficient is obtained through calculation and serves as an evaluation index; and according to the calculated DO-ELE coefficient, determining the ESG governance grade of the hotel by comparing with a preset grade division standard, and generating a visual evaluation report of a related data curve.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of hotel environment monitoring, in particular relates to a hotel environment governance intelligent evaluation method based on comprehensive ESG indicators. BACKGROUND

[0002] The current hotel industry environment governance evaluation mainly relies on static reports and manual audits, and it is difficult to realize dynamic monitoring. The traditional method cannot associate the operation state with the change of environmental load, resulting in lagging and distorted evaluation results. The previous evaluation system uses annual or quarterly total energy consumption statistics, which cannot reflect the dynamic load characteristics of hotel operation, resulting in the homogenization of resource utilization efficiency in high and low occupancy periods. The environmental load data is disconnected from the real-time operation state, and the basic energy consumption of vacant guest rooms is not considered, resulting in systematic bias in the calculation of unit guest room environmental efficiency. There is a lack of fusion mechanism for multi-source heterogeneous data, and different dimensional environmental indicators such as electricity, water resources and refrigerants are difficult to be unified and quantified, and the manual collection method leads to insufficient data timeliness and credibility. The existing evaluation model ignores the differences between hotel types and uses fixed parameters to calculate the theoretical load value, which cannot meet the actual needs of different operation modes. Therefore, we propose a hotel environment governance intelligent evaluation method based on comprehensive ESG indicators. SUMMARY

[0003] To solve the above technical problems, the present application is realized by the following technical scheme:

[0004] The present application is a hotel environment governance intelligent evaluation method based on comprehensive ESG indicators, comprising the following steps:

[0005] Step S1: Real-time collection of multi-source environmental data, through deployment of Internet of Things sensing devices and docking with existing hotel management systems, obtain hotel environmental related data and guest room occupancy state information;

[0006] Step S2: Based on the obtained guest room occupancy state information, count the number of effective occupied rooms according to the set time slice, and then calculate the real-time occupancy rate of each time slice to reflect the operation load of the hotel in different periods;

[0007] Step S3: Standard unit conversion of the collected environmental data of different types and different units, combined with the obtained occupancy rate information, integrate to form a total environmental load vector;

[0008] Step S4: According to the hotel type, match the preset parameters, if there is no matching type, use the historical occupancy rate data obtained in step S2 and the historical environmental load data obtained in step S3 to calculate the optimal parameter group of the hotel;

[0009] Step S5: Based on the normalized environmental load data, occupancy rate and calibrated parameters, first calculate the load efficiency of each time slice, and then comprehensively calculate the DO-ELE coefficient as an evaluation index;

[0010] Step S6: According to the calculated DO-ELE coefficient, determine the ESG management level of the hotel according to the preset grade division standard, and generate a visual evaluation report containing related data curves.

[0011] Further, the step S1 includes the following steps:

[0012] Step S11, deploy an Internet of Things sensor network, install metering devices for recording power consumption in different functional areas of each room and all public areas of the hotel, install devices for monitoring water resource flow in the main pipe and branch pipe of the water supply pipe, and install sensors for monitoring refrigerant leakage in the total circuit of the air conditioning system;

[0013] Step S12, establish data connection through the API interface of the hotel property management system, and obtain real-time information about the occupancy state of the room according to the set frequency;

[0014] Step S13, synchronize the various environmental data collected by the sensors and the room occupancy data obtained from the property management system at fixed time intervals, and transmit them to the blockchain storage database for storage. In the storage process, the data is encrypted using the SHA-256 encryption algorithm.

[0015] Further, the step S2 includes the following steps:

[0016] Step S21, define the duration of the evaluation time slice, and divide the time of one day into multiple consecutive time units according to the duration;

[0017] Step S22, to count the number of rooms with guests staying in each time slice, judge the occupancy state of all rooms by time slice, and count the rooms in the occupied state. The formula is as follows:

[0018]

[0019] In the formula, N occupied,t is the number of effective occupied rooms in time slice t, R is the total number of rooms in the hotel, δ i,t is a binary variable, δ i,t is 1 when room i is occupied at time t, otherwise it is 0, and i is the i-th room;

[0020] Step S23, establish the correlation between environmental load and operation state, and calculate the real-time occupancy rate r tThe number of effective rooms N in the time slice obtained is divided by the total number of rooms R of the hotel, and the formula is as follows: occupied,t

[0021]

[0022] Further, the step S3 comprises the following steps:

[0023] Step S31, converting the environmental data into standard units, converting the collected power consumption data into a unified electric energy measurement unit, converting the water resource consumption data into an equivalent carbon emission measurement unit, and converting the refrigerant leakage data into a weighted value based on the ozone depletion potential value;

[0024] Step S32, integrating the environmental load data of each time period to generate a total environmental load vector, arranging the actual environmental load data of all time slices after normalization processing in chronological order, and the formula is as follows:

[0025]

[0026] In the formula, E actual,T represents the actual environmental load data of the tth time slice after normalization processing.

[0027] Further, the step S4 comprises the following steps:

[0028] Step S41, matching the preset parameter library according to the hotel type, storing the environmental evaluation parameters corresponding to different types of hotels in the preset parameter library, and obtaining the corresponding evaluation parameters by comparing the type of the hotel to be evaluated with the types in the preset parameter library;

[0029] Step S42, if there is no matching type, starting machine learning calibration, inputting the occupancy rate data set of each time slice in the past period of time and the corresponding actual environmental load data set after normalization processing;

[0030] The optimization goal is to minimize the difference between the actual environmental load and the load value calculated based on the parameters, and the formula is as follows:

[0031]

[0032] In the formula, min is the minimization operation, ∑ t is the summation operation of the corresponding items of all time slices t, α, β, γ are environmental evaluation parameters, r t is the real-time occupancy rate of the tth time slice, is the βth power of the real-time occupancy rate of the tth time slice, is the theoretical load value calculated based on the parameters and the occupancy rate.

[0033] ​Further, the step S5 comprises the following steps:

[0034] Step S51, quantifying the environmental load efficiency under the unit occupancy rate, dividing the actual environmental load data of the tth time slice after normalization processing by the theoretical load value calculated based on the occupancy rate and evaluation parameters of the time slice, and the formula is as follows:

[0035]

[0036] In the formula, ELE t represents the load efficiency of the tth time slice;

[0037] Step S52, calculating the core evaluation index in the period based on the dynamic occupancy rate decay model, and the formula is as follows:

[0038]

[0039] In the formula, DO-ELE is a coefficient for evaluating the environmental governance efficiency of the hotel, is the sum of all time slices in the evaluation period, T is the total number of time slices in the evaluation period, BASE eff is the industry benchmark efficiency value.

[0040] Further, the step S6 comprises the following steps:

[0041] Step S61, dividing the ESG governance level according to the DO-ELE value, comparing the DO-ELE value with a plurality of preset intervals, and each interval corresponds to a specific ESG governance level;

[0042] Step S62, generating a visual evaluation report, and the report contains a fluctuation curve of the load efficiency ELE t of each time slice in chronological order.

[0043] The present application has the following beneficial effects:

[0044] 1. The present application collects multi-source environmental data such as power, water resources and refrigerants in real time through Internet of Things devices, combines the guest room occupancy state information synchronized by the property management system, and constructs a dynamic operation load model. The time slice division mechanism is used to calculate the real-time occupancy rate, the environmental load and the operation state are associated, the lag problem of the traditional static report is solved, the resource utilization efficiency difference of high / low peak period is tracked at minute / hour level granularity, the evaluation distortion caused by homogenization processing is avoided, and data support is provided for dynamic adjustment of energy strategy of the hotel.

[0045] 2、The present application converts different types and different units of environmental data into a unified standard unit and integrates them. The key is to compare the actual environmental load with the theoretical expected load calculated based on the real-time occupancy rate, effectively eliminating the influence of the energy consumption of empty guest rooms. This comparison mechanism can accurately quantify the actual environmental load efficiency under the unit occupancy rate, avoiding the calculation deviation of the unit guest room environmental efficiency caused by the traditional method due to the neglect of operation fluctuations and empty energy consumption.

[0046] 3、The present application is aimed at the difference of hotel types, and the method presets a standard parameter library, and uses machine learning technology to automatically optimize key evaluation parameters according to the historical data of a specific hotel, ensuring that the model can adapt to hotels of different scales and operation modes. At the same time, the blockchain technology is used to ensure the authenticity and non-tamperability of multi-source heterogeneous data in the transmission and storage process, and to improve the data credibility. Through comprehensive calculation of the core environmental governance efficiency coefficient, the ESG level is divided by comparing with the preset standard, and a visual report containing the efficiency fluctuation curve is generated, so that the evaluation result is objective and powerful to support the hotel environmental governance decision.

[0047] Of course, implementing any product of the present application does not necessarily require all the advantages described above. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0049] Figure 1 The present application is a kind of comprehensive ESG index hotel environment governance intelligent evaluation method. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present application will be described in detail below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0051] Please refer to Figure 1 The present application is a kind of comprehensive ESG index hotel environment governance intelligent evaluation method, comprising the following steps:

[0052] Step S1: Real-time acquisition of multi-source environmental data, through deployment of Internet of Things sensing devices and docking with existing hotel management systems, obtain hotel environmental data and guest room occupancy state information;

[0053] Step S2: Based on the obtained guest room occupancy state information, the number of effective occupied rooms is counted according to the set time slice, and then the real-time occupancy rate of each time slice is calculated to reflect the operation load situation of the hotel in different time periods;

[0054] Step S3: The different types and different units of environmental data collected are converted into standard units, and the obtained occupancy rate information is combined to form a total environmental load vector;

[0055] Step S4: According to the hotel type, the preset parameters are matched, if there is no matching type, the historical occupancy rate data obtained in step S2 and the historical environmental load data obtained in step S3 are used to calculate the optimal parameter group of the hotel;

[0056] Step S5: Based on the normalized environmental load data, the occupancy rate and the calibrated parameters, the load efficiency of each time slice is calculated first, and then the DO-ELE coefficient is calculated comprehensively to serve as an evaluation index;

[0057] Step S6: According to the calculated DO-ELE coefficient, the ESG management level of the hotel is determined by comparing with the preset grade division standard, and a visual evaluation report containing related data curves is generated.

[0058] Step S1 includes the following steps:

[0059] Step S11, deploy an Internet of Things sensor network, install metering equipment for recording power consumption in different functional areas of each guest room and all public areas of the hotel, install equipment for monitoring water resource flow in the main pipe and branch pipe of the water supply pipe, and install sensors for monitoring refrigerant leakage in the total circuit of the air conditioning system;

[0060] Step S12, establish data connection through the API interface of the hotel property management system, and obtain real-time guest room occupancy state related information according to the set frequency;

[0061] Step S13, synchronize the various types of environmental data collected by the sensors and the guest room occupancy data obtained from the property management system according to the fixed time interval, and transmit them to the blockchain storage database for storage. In the storage process, SHA-256 encryption algorithm is used for encryption processing of the data.

[0062] Step S2 includes the following steps:

[0063] Step S21, define the duration of the evaluation time slice, and divide the time of one day into multiple continuous time units according to the duration;

[0064] Step S22, to count the number of rooms with guests staying in each time slice, judge the occupancy status of all guest rooms by time slice, and count the rooms in the occupancy state, the formula is as follows:

[0065]

[0066] In the formula, N occupied,t is the effective occupancy room number in the time slice t, R is the total number of guest rooms in the hotel, δ i,t is a binary variable, when the room i is occupied at t period, δ i,t is 1, otherwise 0, i is the i-th guest room;

[0067] Step S23, establish the correlation between environmental load and operation state, calculate the real-time occupancy rate r t , divide the total number of guest rooms R in the hotel, the formula is as follows: occupied,t

[0068]

[0069] Step S3 includes the following steps:

[0070] Step S31, convert the environmental data into standard units, convert the collected power consumption data into unified electric energy measurement units, convert the water resource consumption data into equivalent carbon emission measurement units, and convert the refrigerant leakage data into weighted values based on ozone depletion potential;

[0071] Step S32, integrate the environmental load data of each period to generate a total environmental load vector, arrange the actual environmental load data of all time slices after normalization processing in time sequence, the formula is as follows:

[0072]

[0073] In the formula, E actual,T represents the actual environmental load data of the t-th time slice after normalization processing.

[0074] Step S4 includes the following steps:

[0075] Step S41, match the preset parameter library according to the hotel type, the preset parameter library stores environmental evaluation parameters corresponding to different types of hotels, and the corresponding evaluation parameters are obtained by comparing the type of the hotel to be evaluated with the types in the preset parameter library;

[0076] ​Step S42, if there is no matching type, start machine learning calibration, input the occupancy rate data set of each time slice in the past period of time, and the corresponding actual environment load data set after normalization processing;

[0077] The optimization target is to minimize the difference between the actual environment load and the load value calculated based on the parameters, and the formula is as follows:

[0078]

[0079] In the formula, min is the minimization operation, ∑ t is the sum operation of the corresponding items of all time slices t, α, β, γ are environment evaluation parameters, r t is the real-time occupancy rate of the tth time slice, is the βth power of the real-time occupancy rate of the tth time slice, is the theoretical load value calculated based on the parameters and occupancy rate.

[0080] Step S5 includes the following steps:

[0081] Step S51, quantize the environment load efficiency under the unit occupancy rate, divide the actual environment load data of the tth time slice after normalization processing by the theoretical load value calculated based on the occupancy rate and evaluation parameters of the time slice, and the formula is as follows:

[0082]

[0083] In the formula, ELE t is the load efficiency of the tth time slice;

[0084] Step S52, based on the dynamic occupancy rate decay model, calculate the core evaluation index in the period, and the formula is as follows:

[0085]

[0086] In the formula, DO-ELE is the coefficient for evaluating the hotel environment management efficiency, is the sum of all time slices in the evaluation period, T is the total number of time slices in the evaluation period, BASE eff is the industry benchmark efficiency value.

[0087] Step S6 includes the following steps:

[0088] Step S61, divide the ESG management level according to the DO-ELE value, compare the DO-ELE value with a plurality of preset intervals, and each interval corresponds to a specific ESG management level;

[0089] Step S62, generating a visual evaluation report containing the fluctuation curve of the load efficiency ELE of each time slice in chronological order. t

[0090] One specific application of the embodiment is:

[0091] Implementation scenario:

[0092] The embodiment takes a mid-end business hotel in a city core business district as the evaluation object. The hotel has 100 guest rooms (total number of guest rooms R = 100), covering public areas such as guest room area, catering area, and meeting area. There are environmental governance problems such as large fluctuations in power and water consumption, and refrigerant leakage risk in daily operation. The environmental governance efficiency of the hotel is evaluated for 1 day (24 hours) by the method of the embodiment;

[0093] Specific implementation steps:

[0094] Step one,

[0095] 1. Install intelligent power metering sensors in the bedrooms, bathrooms, and public areas (catering area, meeting area) of the 100 guest rooms to record real-time power consumption data with a sampling frequency of 1 minute per time;

[0096] Install ultrasonic flow sensors on the hotel water supply main pipeline and guest room and public area branch pipelines to monitor water flow with a sampling frequency of 5 minutes per time;

[0097] Install refrigerant leakage sensors (for R32 refrigerant) on the air conditioning system total circuit to monitor leakage concentration with a sampling frequency of 30 minutes per time;

[0098] 2. Establish data connection through the API interface of the hotel property management system (PMS), synchronize the guest room occupancy status (occupied / empty) every 15 minutes, including guest room number, check-in time, check-out time, etc.

[0099] 3. Synchronize the environmental data collected by the sensors and the occupancy data of PMS at fixed intervals of 15 minutes, transmit them to the blockchain storage database, and use SHA-256 algorithm for encryption processing to ensure data cannot be tampered with.

[0100] Step two,

[0101] 1. Define the evaluation time slice duration as 1 hour, and divide 1 day into 24 consecutive time units;

[0102] 2. Judge the guest room occupancy status in each time slice using the formula:

[0103]

[0104] ​Time slice t = 8 (8:00-9:00), 60 rooms are in the occupancy state, then N occupied,8 = 60;

[0105] 3, the occupancy rate of time slice t = 8 is

[0106] Step three,

[0107] 1, the power consumption data: unified conversion to kWh / time slice, such as: the total power consumption of time slice t = 8 is 200 kWh;

[0108] Water resource data: converted into equivalent carbon emissions according to industry standards (1 ton of water ≈ 0.1 tCO2), the water resource consumption of time slice t = 8 is 50 tons, and the equivalent carbon emissions is 5 tCO2;

[0109] Refrigerant leakage data: based on the ozone depletion potential (ODP = 0.005) of R32, the weighted value is calculated, the leakage of time slice t = 8 is 0.1 kg, and the weighted value is 0.1 × 0.005 = 0.0005;

[0110] 2, the environmental data of each time slice is normalized (eliminate the influence of dimension), and is integrated into the total environmental load vector according to time sequence:

[0111] The normalized actual environmental load E actual,8 of time slice t = 8 is 0.7 (calculated by comprehensive power, water resource and refrigerant data) ;

[0112] Step four,

[0113] 1, the hotel is a medium-end business hotel, which matches the corresponding type in the preset parameter library, and obtains the evaluation parameters: α = 0.8, β = 1.2, γ = 0.1;

[0114] 2, if no type is matched, input the historical occupancy rate data and environmental load data of the past 30 days, and calibrate the parameters through optimization target .

[0115] Step five,

[0116] 1, calculate the load efficiency of each time slice;

[0117] The theoretical load value of time slice t = 8 is: Then

[0118] 2, the evaluation period T = 24, the industry benchmark efficiency value BASE eff = 1.2, and the formula is The ELE of 24 time slices is calculated t The sum is 25.92, the average is 25.92 / 24 = 1.08, and

[0119] Step six,

[0120] The preset grade standard is: DO-ELE≥1.2 is A (excellent), 0.9≤DO-ELE<1.2 is B (good), and DO-ELE<0.9 is C (to be improved). The DO-ELE of the embodiment is 0.9, which corresponds to B

[0121] The report contains: ELE within 24 hours t The fluctuation curve (showing that the efficiency is higher during the morning peak of 8:00-10:00 and lower during the early morning of 2:00-4:00), the time distribution thermodynamic diagram of each environmental index (electricity, water resources, refrigerant), the DO-ELE coefficient and the grade determination result, and the management suggestion for optimizing the air conditioning energy consumption of the empty area in the early morning are provided for the hotel.

[0122] In the description of the present specification, the description referring to the terms "one embodiment", "example", "specific example" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0123] The preferred embodiments of the application disclosed above are only used to help explain the application. The preferred embodiments do not describe all the details and do not limit the application to the specific embodiments described. Obviously, many modifications and changes can be made according to the content of the present specification. The present specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the application, so that those skilled in the art can well understand and utilize the application. The application is limited only by the claims and their entire scope and equivalents.

Claims

1. A smart assessment method for hotel environmental governance based on comprehensive ESG indicators, characterized in that: Includes the following steps: Step S1: Real-time collection of multi-source environmental data. By deploying IoT sensing devices and connecting with the hotel's existing management system, various environmental data and room occupancy status information of the hotel can be obtained. Step S2: Based on the obtained room occupancy status information, count the number of valid occupancy rooms according to the set time slices, and then calculate the real-time occupancy rate for each time slice to reflect the hotel's operational load at different times. Step S3: Convert the collected environmental data of different types and units to standard units, and combine them with the obtained occupancy rate information to form a total environmental load vector; Step S4: Match preset parameters according to hotel type. If no matching type is found, calculate the optimal parameter set for the hotel using the historical occupancy rate data obtained in step S2 and the historical environmental load data obtained in step S3. Step S5: Based on normalized environmental load data, occupancy rate, and calibrated parameters, first calculate the load efficiency for each time slice, and then calculate the DO-ELE coefficient as an evaluation index. Step S6: Based on the calculated DO-ELE coefficient, determine the hotel's ESG governance level according to the preset level classification standard, and generate a visual evaluation report containing relevant data curves.

2. The intelligent assessment method for hotel environmental governance based on comprehensive ESG indicators as described in claim 1, characterized in that, Step S1 includes the following steps: Step S11: Deploy an Internet of Things (IoT) sensor network, install metering devices to record power consumption in different functional areas of each guest room and in all public areas of the hotel, install devices to monitor water flow in the main and branch pipes of the water supply system, and install sensors to monitor refrigerant leaks in the main circuit of the air conditioning system. Step S12: Establish a data connection through the API interface of the hotel property management system and obtain relevant information on the occupancy status of guest rooms in real time at the set frequency; Step S13: At fixed time intervals, synchronize the various environmental data collected by the sensors with the guest room occupancy data obtained from the property management system, and transmit them to the blockchain evidence database for storage. During the storage process, the data is encrypted using the SHA-256 encryption algorithm.

3. The intelligent assessment method for hotel environmental governance based on comprehensive ESG indicators according to claim 1, characterized in that, Step S2 includes the following steps: Step S21: Define the duration of the evaluation time slice and divide a day into multiple consecutive time units according to the duration. Step S22: To count the number of rooms occupied by guests in each time slot, determine the occupancy status of all rooms according to the time slot, and count the rooms that are occupied, using the following formula: In the formula, N occupied,t R represents the number of rooms occupied within time slice t, and R represents the total number of hotel rooms. δ i,t For a binary variable, δ represents the number of people who check into room i during time period t. i,t The value is 1 if it is not 0 otherwise, and i is the i-th guest room; Step S23: Establish the correlation between environmental load and operational status, and calculate the real-time occupancy rate r. t The number of valid rooms N within that time slice will be obtained. occupied,t Divide by the total number of hotel rooms R, as shown in the formula below:

4. The intelligent assessment method for hotel environmental governance based on comprehensive ESG indicators according to claim 1, characterized in that, Step S3 includes the following steps: Step S31: Convert environmental data into standard units. Convert the collected power consumption data into a unified power metering unit, convert the water resource consumption data into an equivalent carbon emission metering unit, and convert the refrigerant leakage data into a weighted value based on ozone depletion potential. Step S32: Integrate the environmental load data from each time period to generate a total environmental load vector. Arrange the normalized actual environmental load data of all time slices in chronological order, as shown in the following formula: In the formula, E actual,T This represents the actual environmental load data after normalization for the t-th time slice.

5. The intelligent assessment method for hotel environmental governance based on comprehensive ESG indicators according to claim 1, characterized in that, Step S4 includes the following steps: Step S41: Match the preset parameter library according to the hotel type. The preset parameter library stores environmental assessment parameters corresponding to different types of hotels. By comparing the type of the hotel to be assessed with the type in the preset parameter library, the corresponding assessment parameters are obtained. Step S42: If there is no matching type, start machine learning calibration, input the occupancy rate data set of each time slice in the past period, and the corresponding normalized actual environmental load data set. The optimization objective is to minimize the difference between the actual environmental load and the load value calculated based on the parameters, as shown in the following formula: In the formula, min represents the minimization operation, and ∑ t To perform a summation operation on the corresponding terms for all time slices t, α, β, γ are environmental assessment parameters, and r t To represent the real-time occupancy rate for the t-th time slice, Let β represent the real-time occupancy rate raised to the power of β in the t-th time slice. This is the theoretical load value calculated based on parameters and occupancy rate.

6. The intelligent assessment method for hotel environmental governance based on comprehensive ESG indicators according to claim 1, characterized in that, Step S5 includes the following steps: Step S51: Quantify the environmental load efficiency per unit occupancy rate. Divide the normalized actual environmental load data for the t-th time slice by the theoretical load value calculated based on the occupancy rate and evaluation parameters for that time slice, as shown in the following formula: In the formula, ELE t Let this represent the load efficiency of the t-th time slice; Step S52: Based on the dynamic occupancy rate decay model, calculate the core evaluation indicators within the period, using the following formula: In the formula, DO-ELE is a coefficient for comprehensively evaluating the efficiency of hotel environmental governance. To sum over all time slices within the evaluation period, where T is the total number of time slices within the evaluation period, BASE eff This is the industry benchmark efficiency value.

7. The intelligent assessment method for hotel environmental governance based on comprehensive ESG indicators according to claim 1, characterized in that, Step S6 includes the following steps: Step S61: Divide ESG governance levels according to DO-ELE values, compare DO-ELE values ​​with multiple preset intervals, and each interval corresponds to a specific ESG governance level. Step S62: Generate a visual evaluation report, which includes the load efficiency (ELE) of each time slice displayed in chronological order. t The fluctuation curve.

Images