Hotel intelligent guest room one-key deep sleep scene control system and method

Abstract

The invention discloses a hotel intelligent guest room one-key deep sleep scene control system and method, and relates to the technical field of hotel guest room control, and the method comprises the steps: obtaining a reference interval to which a real-time person belongs according to the age, height and body shape image of the real-time person, and obtaining the one-key deep sleep scene of the real-time person according to the bedside light reference brightness and indoor reference temperature corresponding to the reference interval; and the pre-adjustment parameter value is used as a pre-adjustment parameter value corresponding to the guest room where the person is located in the one-key deep sleep scene in real time, so that the technical problem that a real personalized deep sleep environment cannot be provided for each guest due to neglect of individual differences among different guests when the guest room environment is adjusted based on a unified preset parameter in a traditional method is solved; by collecting and analyzing the age, height and figure data of the check-in and combining the reference interval groups divided by the historical data, the reference interval group most matched with the features of the check-in can be quickly found, the guest room environment is automatically adjusted according to the reference interval group, and the comfort and satisfaction of the check-in are remarkably improved.

Description

Technical Field

[0001] The invention belongs to the technical field of hotel guest room control, and in particular is a one-button deep sleep scene control system and method for a hotel smart guest room. Background Art

[0002] With the rapid development of technologies such as mobile Internet, big data mining, and the Internet of Things, and their wide application in various fields, concepts such as smart cities, smart transportation, and smart homes have gradually emerged in people's vision. Smart hotels, which are the combination of "Internet +" and hotels, have provided new impetus for the development of the hotel industry.

[0003] With the improvement of people's living standards and the booming tourism industry, the hotel industry is facing increasingly fierce market competition. In order to attract and retain customers, hotels need to continuously improve service quality and customer experience. Among them, providing personalized accommodation experience has become one of the important means for hotels to differentiate their competition. Therefore, the one-button deep sleep scene control solution for hotel smart rooms came into being, aiming to provide guests with a more comfortable and convenient deep sleep environment through intelligent means.

[0004] However, since hotel guests have diverse backgrounds and needs, different guests have different requirements for sleeping environments. For example, the elderly may be more sensitive to light brightness than young people, and guests of different body shapes may feel the indoor temperature differently. The traditional fixed guest room environment setting is difficult to meet such diverse needs. Traditional methods usually adjust the guest room environment based on unified preset parameters, ignoring the individual differences between different guests, such as age, height, body shape, etc., resulting in the inability to provide a truly personalized deep sleep environment for each guest, reducing the adaptability and comfort of the guest room environment, and reducing service efficiency and customer satisfaction. Based on this, a one-button deep sleep scene control system and method for hotel smart guest rooms is proposed. Summary of the invention

[0005] The purpose of the present invention is to provide an information interaction method for power field operations, which solves the technical problem that the traditional method adjusts the guest room environment based on unified preset parameters, ignores the individual differences between different occupants, and makes it impossible to provide a truly personalized deep sleep environment for each occupant.

[0006] A one-button deep sleep scene control method for a hotel smart room comprises the following steps:

[0007] Step 1: Obtain the age, height and body shape images of the historical occupants of the hotel's single rooms;

[0008] Step 2: Determine the first-level age range, first-level height range, and first-level heat range;

[0009] Step 3: Obtain multiple secondary age intervals, secondary height intervals, and secondary heat intervals;

[0010] Step 4: Combine different secondary age intervals, secondary height intervals, and secondary heat intervals to generate multiple reference interval groups;

[0011] Step 5: Obtain the bedside light reference brightness and indoor reference temperature corresponding to each reference interval group in the one-key deep sleep scene when staying in a hotel single room;

[0012] Step 6: Obtain the reference interval to which the real-time person belongs based on the age, height and body shape image of the real-time person, and use the bedside light benchmark brightness and indoor benchmark temperature corresponding to the reference interval as the pre-adjusted parameter values ​​corresponding to the one-key deep sleep scenario of the guest room where the real-time person is located.

[0013] As a further solution of the present invention: the specific method of determining the first-level age interval and the first-level height interval is:

[0014] Get the maximum age BA1 and minimum BA2 and the maximum height BB1 and minimum BB2 corresponding to each historical occupant in the hotel single room in the past n days, and generate the first-level age range [BA2, BA1] and first-level height range [BB2, BB1] corresponding to the occupants of the hotel single room, where n refers to the preset number of days, n is a positive integer, and n≥1.

[0015] As a further solution of the present invention: the specific method of determining the first-level heat range is:

[0016] The body image data of the guests staying in the hotel single room in the past n days are obtained from the portrait data of the guests staying in the hotel single room in the past n days, and the body image data of each historical guest is analyzed to obtain the heat area corresponding to each historical guest, and the maximum value BC1 and the minimum value BC2 of the body heat area of ​​each historical guest are obtained, and the first-level heat interval [BC2, BC1] corresponding to the guests staying in the hotel single room is generated.

[0017] As a further solution of the present invention, the specific method of analyzing the body image data of each occupant to obtain the heat area corresponding to each occupant is:

[0018] A two-dimensional coordinate system is established in the body image of each occupant to obtain the shoulder calibration points DAa and DBa corresponding to each occupant. The shoulder calibration line length LAa corresponding to each historical occupant is obtained through the coordinates of the shoulder calibration points DAa and DBa corresponding to each occupant. The highest point and the lowest point in the body image of each occupant are obtained and marked as EAa and EBa respectively. The height calibration line length LBa corresponding to each historical occupant is obtained through the coordinates of points EAa and EBa, where a refers to the different occupants of the hotel single room in the past n days, and a is a positive integer a≥1. The product of the shoulder calibration line length LAa and the height calibration line length LBa corresponding to each occupant and the half of the calibration conversion coefficient T is defined as the thermal area Ma corresponding to each occupant.

[0019] As a further solution of the present invention: the specific method of obtaining the calibration conversion coefficient T is:

[0020] The height values ​​corresponding to each historical occupant are obtained and marked as Ga. The ratio between the height value Ga corresponding to each occupant and the length LBa of the height calibration line is defined as the image conversion coefficient Ra corresponding to each occupant. The average of the sum of the maximum and minimum values ​​of the image conversion coefficient Ra is used as the calibration conversion coefficient T.

[0021] As a further solution of the present invention: a specific method of obtaining multiple secondary age intervals, secondary height intervals and secondary heat intervals is as follows:

[0022] The first-level age interval [BA2, BA1] is divided into multiple second-level age intervals UAb according to the preset age interval J1, and the first-level height interval [BB2, BB1] is divided into multiple second-level height intervals UBc according to the preset height interval J2, where c refers to different second-level age intervals, and the first-level heat interval [BC2, BC1] is divided into multiple second-level heat intervals UCe according to the preset heat interval J3, where b refers to different second-level age intervals, e refers to different second-level heat intervals, b=1, 2, ..., r1, r1 is the number corresponding to the second-level age intervals, c=1, 2, ..., r2, r2 is the number corresponding to the second-level height intervals, c=1, 2, ..., r2, e=1, 2, ..., r3, r3 is the number corresponding to the second-level heat intervals, r1, r2 and r3 are all positive integers and are all greater than or equal to 1.

[0023] As a further solution of the present invention: the specific method of combining and generating multiple reference interval groups is:

[0024] Combine each secondary age interval UAb with each secondary height interval UBc and each secondary temperature interval UCe to generate multiple reference interval groups Wg(UAb, UBc, UCe), where g is a different reference interval group, g=1, 2, ..., t, where t is the number of reference interval groups, t=r1×r2×r3.

[0025] As a further solution of the present invention, the specific method of obtaining the bedside light reference brightness and indoor reference temperature corresponding to each reference interval group in the one-key deep sleep scene when staying in a single room of a hotel is:

[0026] S1: Select one group from each reference interval group as the analysis group;

[0027] S2: Mark the bedside light brightness and indoor temperature corresponding to the one-key deep sleep scenario when multiple analysis groups of people check into a single room in a hotel as HAu and HBu respectively, where u refers to different people in the analysis group, obtain the value HAv in HAu that satisfies |HAu-HAp|≥Y2, where Y2 is a preset value, when the number v is greater than the preset threshold value Y1, define the mean HAp of HAu as the bedside light reference brightness CT1 corresponding to the analysis group, when the number v is less than or equal to the preset threshold value Y1, define the mean of the maximum and minimum values ​​in HAu as the bedside light reference brightness CT1 corresponding to the analysis group; adopt the same method to analyze the values ​​of the indoor temperature HBu that satisfies |HBu-HBp|≥Y4, and then obtain the indoor reference temperature CL1 corresponding to the analysis group, where Y4 is a preset value and HBp is the mean of HBu;

[0028] S3: Repeat steps S1-S2 to obtain the bedside light reference brightness CTg and indoor reference temperature CLg corresponding to each reference interval group.

[0029] As a further solution of the present invention: the specific method of obtaining the reference interval to which the real-time personnel belong is:

[0030] According to the age, height and heat area corresponding to the real-time personnel, a comparison parameter group corresponding to the real-time personnel is generated, and the comparison parameter group corresponding to the real-time personnel is compared and analyzed with each reference interval group to obtain the reference interval to which the comparison parameter group belongs, and thus the reference interval to which the real-time personnel belongs can be obtained.

[0031] A one-button deep sleep scene control method for a hotel smart guest room is implemented, comprising:

[0032] The data acquisition module collects historical occupant information and portrait data of hotel single rooms, providing basic data for subsequent analysis, including key information such as age, height, and body shape;

[0033] The data analysis module analyzes the historical occupant information and portrait data to determine the first-level age range, first-level height range, and first-level heat range;

[0034] The interval division module divides the first-level age interval, the first-level height interval and the first-level heat interval into multiple second-level age intervals, second-level height intervals and second-level heat intervals;

[0035] A reference interval group generation module combines different secondary age intervals, secondary height intervals and secondary heat intervals to generate multiple reference interval groups;

[0036] The benchmark control parameter value acquisition module analyzes the bedside light brightness and indoor temperature of the occupants in each reference interval group in the one-key deep sleep scenario to obtain the benchmark control parameter value;

[0037] The reference interval matching module obtains the personal information and portrait data of the real-time occupants staying in the hotel's single room, compares and analyzes them with each reference interval group, finds the matching reference interval group, and adjusts the bedside light brightness and indoor temperature of the room where the real-time occupants are located in the one-button deep sleep scenario according to the corresponding benchmark control parameters.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The present invention can provide each occupant with a customized deep sleep environment by collecting and analyzing the age, height, and body shape data of the occupants and combining the reference interval groups divided by historical data. This personalized setting can significantly improve the comfort and satisfaction of the occupants. By using intelligent matching algorithms and real-time data collection technology, it can quickly find the reference interval group that best matches the occupant's characteristics and automatically adjust the room environment accordingly, which not only improves service efficiency, but also reduces the possibility of manual intervention and erroneous operation, solving the problems of insufficient personalization, poor adaptability, and low efficiency in the actual application of one-button deep sleep scene control in hotel smart rooms. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0041] Figure 2 It is a schematic diagram of the system framework structure of the present invention;

[0042] Figure 3 It is a structural schematic diagram of the data analysis module of the present invention. DETAILED DESCRIPTION

[0043] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Embodiment 1

[0045] See also Figure 1 The present application provides a one-key deep sleep scene control system and method for a hotel smart room, comprising the following steps:

[0046] Step 1: Obtain the historical occupant information of the hotel single room and the corresponding occupant portrait data;

[0047] It should be noted that the historical check-in information includes the name, age and place of origin of the check-in personnel, which is obtained based on the identity information provided by the check-in personnel when the check-in personnel check-in. It is a conventional technical means and is therefore not described in detail here. The check-in personnel portrait data corresponding to the historical check-in personnel includes the check-in personnel's height and body shape image data, which is obtained through the monitoring equipment set up in the corridor of the Volcano Hotel at the front desk. It is a conventional technical means and is therefore not described in detail here.

[0048] Step 2: Analyze the hotel's historical check-in information and the corresponding check-in portrait data, and obtain the first-level age range, first-level height range, and first-level heat range corresponding to the hotel's single room check-ins based on the analysis results;

[0049] The specific method of obtaining the first-level age interval and corresponding to the hotel single room occupants is to obtain the ages of each historical occupant in the hotel single room in the past n days, obtain the maximum and minimum ages of each historical occupant, and use them as the upper and lower limits of the first-level age interval, and generate the first-level age interval [BA2, BA1] corresponding to the hotel single room occupants according to the upper and lower limits of the first-level age interval, where BA1 and BA2 are the maximum and minimum ages of each historical occupant, respectively, and n refers to the preset number of days, n is a positive integer, n≥1, and the value of n is 365 days;

[0050] For example, the ages of the historical check-ins in the hotel single room in the past n days are marked as Aa, where a refers to the different check-ins in the hotel single room in the past n days, and a is a positive integer a≥1. The maximum value Amax and the minimum value Amin of the ages Aa of the historical check-ins are obtained, and the maximum value Amax and the minimum value Amin are used as the upper limit BA1 and the lower limit BA1 of the first-level age interval corresponding to the check-ins in the hotel single room, respectively, so as to obtain the first-level age interval [Amin, Amax] corresponding to the check-ins in the hotel single room;

[0051] The specific method of obtaining the first-level height interval corresponding to the occupants of the hotel single room is to obtain the heights of the occupants in the past n days from the portrait data of the historical occupants of the hotel single room in the past n days, obtain the maximum and minimum values ​​of the heights of each historical occupant, and use them as the upper limit and lower limit values ​​corresponding to the first-level height interval respectively, and generate the first-level height interval [BB2, BB1] corresponding to the occupants of the hotel single room according to the upper limit and lower limit values ​​corresponding to the first-level height interval, where BB1 ​​and BB2 are the maximum and minimum values ​​of the heights of each historical occupant respectively;

[0052] The specific method of obtaining the first-level heat interval corresponding to the occupant of the hotel single room is to obtain the body image data of the occupants in the past n days from the portrait data of the historical occupants in the hotel single room in the past n days, and analyze the body image data of each historical occupant to obtain the heat area corresponding to each historical occupant, obtain the maximum value and the minimum value of the body heat area of ​​each historical occupant, and use them as the upper limit value and the lower limit value corresponding to the first-level heat interval, and generate the first-level heat interval [BC2, BC1] corresponding to the occupant of the hotel single room according to the upper limit value and the lower limit value corresponding to the first-level heat interval, wherein BC1 and BC2 are the maximum value and the minimum value of the body heat area of ​​each historical occupant respectively;

[0053] The specific method of analyzing the body image data of each occupant to obtain the heat area corresponding to each occupant is as follows:

[0054] A two-dimensional coordinate system is established in the body image of each occupant to obtain the shoulder calibration points DAa and DBa corresponding to each occupant, where a refers to the different occupants of the hotel single room in the past n days, and a is a positive integer a≥1. The shoulder calibration line length LAa corresponding to each historical occupant is obtained through the coordinates of the shoulder calibration points DAa and DBa corresponding to each occupant;

[0055] When the coordinates of the shoulder calibration points DAa and DBa are DAa (DAax, DAay) and DBa (DBax, DBay) respectively, the distance calculation formula is used: , calculate and obtain the shoulder calibration line length LAa corresponding to each occupant;

[0056] The highest and lowest points in the body image of each occupant are obtained, marked as EAa and EBa, respectively, and the height calibration line length LBa corresponding to each historical occupant is obtained through the coordinates of point EAa and point EBa;

[0057] When the coordinates of point EAa and point EBa are EAa (EAax, EAay) and EBa (EBax, DBay) respectively;

[0058] According to the distance calculation formula, , calculate and obtain the height calibration line length LBa corresponding to each occupant;

[0059] Obtain the height values ​​corresponding to each historical occupant and mark them as Ga, define the ratio between the height value Ga corresponding to each occupant and the height calibration line length LBa as the image conversion coefficient Ra corresponding to each occupant, take the average of the sum of the maximum and minimum values ​​in the image conversion coefficient Ra as the calibration conversion coefficient T, and define the product between the shoulder calibration line length LAa and the height calibration line length LBa corresponding to each occupant and half of the calibration conversion coefficient T as the thermal area Ma corresponding to each occupant, that is, Ma=½×T(LAa×LBa), T=½×(Rmax+Rmin), Rmax and Rmin are the maximum and minimum values ​​of the image conversion coefficient Ra respectively;

[0060] Step 3: Divide the first-level age range, first-level height range, and first-level heat range corresponding to the hotel single room occupants into multiple second-level age ranges, second-level height ranges, and second-level heat ranges respectively. The specific method is as follows:

[0061] Divide the primary age interval [BA2, BA1] into multiple secondary age intervals UAb according to the preset age interval J1, where b refers to different secondary age intervals, b=1, 2, ..., r1, where r1 is the number of secondary age intervals, r1 is a positive integer, r1≥1;

[0062] Divide the first-level height interval [BB2, BB1] into multiple second-level height intervals UBc according to the preset height interval J2, where c refers to different second-level age intervals, c=1, 2, ..., r2, where r2 is the number of second-level height intervals, r2 is a positive integer, r2≥1;

[0063] Divide the first-level heat interval [BC2, BC1] into multiple second-level heat intervals UCe according to the preset heat interval J3, where e refers to different second-level heat intervals, e=1, 2, ..., r3, where r3 is the number of second-level heat intervals, r3 is a positive integer, r3≥1;

[0064] The specific values ​​of the preset age interval J1, preset height interval J2 and preset temperature interval J3 are all formulated by relevant personnel according to actual needs;

[0065] Step 4: Combine multiple secondary age intervals, secondary height intervals, and secondary heat intervals corresponding to the primary age intervals, height intervals, and heat intervals to obtain multiple reference interval groups. The specific method is as follows:

[0066] Combine each secondary age interval UAb with each secondary height interval UBc and each secondary heat interval UCe to generate multiple reference interval groups Wg(UAb, UBc, UCe), where g is a different reference interval group, g=1, 2, ..., t, where t is the number of reference interval groups, t=r1×r2×r3;

[0067] Step 5: Obtain and analyze the control data corresponding to each reference interval group in the one-key deep sleep scenario when they check into a single hotel room, and then obtain the benchmark control parameter values ​​corresponding to each reference interval group in the one-key deep sleep scenario when they check into a single hotel room. The control data include the bedside light brightness and the indoor temperature, and the benchmark control parameter values ​​include the bedside light benchmark brightness and the indoor benchmark temperature. The specific method is as follows:

[0068] S1: Select one group from each reference interval group as the analysis group;

[0069] S2: The corresponding bedside light brightness and indoor temperature in the one-key deep sleep scenario when multiple analysis group members stay in a single hotel room are marked as HAu and HBu, where u refers to different analysis group members;

[0070] The value HAv of the bedside light brightness HAu that meets the preset screening condition X1 is obtained, where v is the number of values ​​in HAu that meet the preset screening condition X1, v≥1, and the number v is compared with the preset value Y1. When the number v is greater than the preset threshold value Y1, it means that the number of values ​​in HAu that meet the preset screening condition X1 is large, and the mean value of HAu is representative, and then the mean value HAp of HAu is defined as the bedside light reference brightness CT1 corresponding to the analysis group. When the number v is less than or equal to the preset threshold value Y1, it means that the number of values ​​in HAu that meet the preset screening condition X1 is small, and the mean value of HAu is not representative, and then the mean of the maximum and minimum values ​​in HAu is defined as the bedside light reference brightness CT1 corresponding to the analysis group. Here, the preset condition X1 is specifically: |HAu-HAp|≥Y2, where Y2 is the preset value, and the specific values ​​of Y1 and Y2 are all formulated by relevant personnel according to actual needs;

[0071] At the same time, obtain the value HAz of the indoor temperature HBu that meets the preset filtering condition X2, where z is the number of values ​​in HBu that meet the preset filtering condition X2, z≥1, compare the number z with the preset value Y3, when the number z is greater than the preset threshold value Y3, it means that the number of values ​​in HBu that meet the preset filtering condition X2 is large, the mean value of HBu is representative, and then the mean value HBp of HBu is defined as the indoor reference temperature CL1 corresponding to the analysis group, when the number z is less than the preset threshold value Y3, it means that the number of values ​​in HBu that meet the preset filtering condition X2 is small, the mean value of HBu is not representative, and then the mean of the maximum and minimum values ​​in HBu is defined as the indoor reference temperature CL1 corresponding to the analysis group; here, the preset condition X2 is specifically: |HBu-HBp|≥Y4, where Y4 is the preset value, and the specific values ​​of Y3 and Y4 are all formulated by relevant personnel according to actual needs;

[0072] S3: Repeat steps S1-S2 to obtain the bedside light reference brightness CTg and indoor reference temperature CLg corresponding to each reference interval group, and bind the obtained bedside light reference brightness CTg and indoor reference temperature CLg corresponding to each reference interval group with the corresponding reference interval group, thereby generating the reference control parameter values ​​corresponding to each reference interval group in the one-key deep sleep scene when staying in a single room in a hotel;

[0073] By clarifying the bedside light benchmark brightness and indoor benchmark temperature corresponding to different reference interval groups, accurate control of hotel guest room energy consumption can be achieved. Hotels can reasonably adjust the light brightness and indoor temperature based on these benchmark values ​​to avoid excessive waste of energy. For example, under the premise of meeting guests' sleep needs, for those guests in the reference interval group with lower requirements for light brightness, the hotel can reduce the light power. For guests with a narrow temperature adaptation range and lower temperature requirements, the energy output of heating or cooling can be appropriately reduced, thereby reducing the hotel's operating costs and enabling the hotel to automatically adjust the guest room environment according to the characteristics of the guests, thereby improving the overall intelligence level of the hotel and enhancing the hotel's competitiveness in the market.

[0074] Embodiment 2

[0075] As the second embodiment of the present invention, when the present application is implemented, compared with the first embodiment, the technical solution of the present embodiment is different from the first embodiment only in that the present embodiment further includes step six;

[0076] Step 6: Acquire and analyze the personnel information and portrait data of the real-time personnel staying in the single room of the hotel, and then obtain the age, height and thermal area corresponding to the real-time personnel, and then generate a comparison parameter group corresponding to the real-time personnel, compare and analyze the comparison parameter group corresponding to the real-time personnel with each reference interval group, obtain the reference interval to which the comparison parameter group belongs, and obtain the benchmark control parameter value corresponding to the reference interval to which the comparison parameter group belongs, and use it as the pre-adjustment parameter value corresponding to the one-key deep sleep scenario of the room where the real-time personnel is located;

[0077] When the real-time person presses the one-key deep sleep button, the bedside light brightness and indoor temperature of the room where the real-time person is located are adjusted accordingly according to the pre-adjusted parameter values ​​corresponding to the one-key deep sleep scene in the room where the real-time person is located;

[0078] By collecting and analyzing the age, height, and body shape data of the guests, and combining the reference interval groups divided by historical data, a customized deep sleep environment can be provided for each guest. This personalized setting can significantly improve the comfort and satisfaction of the guests. By using intelligent matching algorithms and real-time data collection technology, it can quickly find the reference interval group that best matches the characteristics of the guests, and automatically adjust the room environment accordingly, which not only improves service efficiency, but also reduces the possibility of manual intervention and erroneous operation, solving the problems of insufficient personalization, poor adaptability, and low efficiency in the actual application of one-button deep sleep scene control in hotel smart rooms.

[0079] Embodiment 3

[0080] As the third embodiment of the present invention, please refer to Figure 2-Figure 3The present application provides a one-key deep sleep scene control system for a hotel smart room, which is operated by the one-key deep sleep scene control method for a hotel smart room disclosed above, including:

[0081] The data acquisition module collects historical occupant information and portrait data of hotel single rooms, providing basic data for subsequent analysis, including key information such as age, height, and body shape;

[0082] The data analysis module analyzes the historical occupant information and portrait data to determine the first-level age range, first-level height range, and first-level heat range;

[0083] The primary age interval is obtained by analyzing the ages of historical occupants through the primary age interval determination unit;

[0084] The height of historical occupants is analyzed through the first-level height interval determination unit to obtain the first-level age interval;

[0085] The first-level heat interval determination unit analyzes the portrait data of historical check-in personnel to obtain the first-level heat interval;

[0086] The interval division module divides the first-level age interval, the first-level height interval and the first-level heat interval into multiple second-level age intervals, second-level height intervals and second-level heat intervals;

[0087] A reference interval group generation module combines different secondary age intervals, secondary height intervals and secondary heat intervals to generate multiple reference interval groups;

[0088] The benchmark control parameter value acquisition module analyzes the bedside light brightness and indoor temperature of the occupants in each reference interval group in the one-key deep sleep scenario and calculates the benchmark control parameter value;

[0089] The reference interval matching module obtains the real-time personnel information and portrait data of the single room in the hotel, compares and analyzes them with the reference interval groups, finds the matching reference interval group, and adjusts the bedside light brightness and indoor temperature of the room where the real-time personnel is located in the one-key deep sleep scene according to its corresponding benchmark control parameters;

[0090] The entire process builds an efficient and intelligent one-button deep sleep scene control system for hotel single rooms through steps such as data collection, analysis, interval division, generation of reference interval groups, acquisition of benchmark control parameter values, and real-time personnel reference interval matching. The system can not only meet the personalized needs of different guests, but also improve the hotel's service quality and market competitiveness.

[0091] Embodiment 4

[0092] As the fourth embodiment of the present invention, when the present application is specifically implemented, compared with the first, second and third embodiments, the technical solution of this embodiment is to combine and implement the solutions of the first, second and third embodiments.

[0093] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0094] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A one-button deep sleep scene control method for a hotel smart room, characterized in that: The following steps are involved: Step 1: Obtain the age, height and body shape images of the historical occupants of the hotel's single rooms; Step 2: Determine the first-level age range, first-level height range, and first-level heat range; Step 3: Obtain multiple secondary age intervals, secondary height intervals, and secondary heat intervals; Step 4: Combine different secondary age intervals, secondary height intervals, and secondary heat intervals to generate multiple reference interval groups; Step 5: Obtain the bedside light reference brightness and indoor reference temperature corresponding to each reference interval group in the one-key deep sleep scene when staying in a hotel single room; Step 6: Obtain the reference interval to which the real-time person belongs based on the age, height and body shape image of the real-time person, and use the bedside light benchmark brightness and indoor benchmark temperature corresponding to the reference interval as the pre-adjusted parameter values ​​corresponding to the one-key deep sleep scenario of the guest room where the real-time person is located.

2. A one-key deep sleep scene control method for a hotel smart room according to claim 1, characterized in that: The specific method for determining the first-level age range and the first-level height range is as follows: Get the maximum age BA1 and minimum BA2 and the maximum height BB1 and minimum BB2 corresponding to each historical occupant in the hotel single room in the past n days, and generate the first-level age range [BA2, BA1] and first-level height range [BB2, BB1] corresponding to the occupants of the hotel single room, where n refers to the preset number of days, n is a positive integer, and n≥1.

3. A one-key deep sleep scene control method for a hotel smart room according to claim 2, characterized in that: The specific method for determining the first-level heat range is: The body image data of the guests staying in the hotel single room in the past n days are obtained from the portrait data of the guests staying in the hotel single room in the past n days, and the body image data of each historical guest is analyzed to obtain the heat area corresponding to each historical guest, and the maximum value BC1 and the minimum value BC2 of the body heat area of ​​each historical guest are obtained, and the first-level heat interval [BC2, BC1] corresponding to the guests staying in the hotel single room is generated.

4. A one-key deep sleep scene control method for a hotel smart room according to claim 3, characterized in that: The specific method of analyzing the body image data of each occupant to obtain the heat area corresponding to each occupant is as follows: A two-dimensional coordinate system is established in the body image of each occupant to obtain the shoulder calibration points DAa and DBa corresponding to each occupant. The shoulder calibration line length LAa corresponding to each historical occupant is obtained through the coordinates of the shoulder calibration points DAa and DBa corresponding to each occupant. The highest point and the lowest point in the body image of each occupant are obtained and marked as EAa and EBa respectively. The height calibration line length LBa corresponding to each historical occupant is obtained through the coordinates of points EAa and EBa, where a refers to the different occupants of the hotel single room in the past n days, and a is a positive integer a≥1. The product of the shoulder calibration line length LAa and the height calibration line length LBa corresponding to each occupant and the half of the calibration conversion coefficient T is defined as the thermal area Ma corresponding to each occupant.

5. A one-key deep sleep scene control method for a hotel smart room according to claim 4, characterized in that: The specific method of obtaining the calibration conversion coefficient T is: The height values ​​corresponding to each historical occupant are obtained and marked as Ga. The ratio between the height value Ga corresponding to each occupant and the length LBa of the height calibration line is defined as the image conversion coefficient Ra corresponding to each occupant. The average of the sum of the maximum and minimum values ​​of the image conversion coefficient Ra is used as the calibration conversion coefficient T.

6. A one-key deep sleep scene control method for a hotel smart room according to claim 5, characterized in that: The specific method of obtaining multiple secondary age intervals, secondary height intervals and secondary heat intervals is as follows: The first-level age interval [BA2, BA1] is divided into multiple second-level age intervals UAb according to the preset age interval J1, and the first-level height interval [BB2, BB1] is divided into multiple second-level height intervals UBc according to the preset height interval J2, where c refers to different second-level age intervals, and the first-level heat interval [BC2, BC1] is divided into multiple second-level heat intervals UCe according to the preset heat interval J3, where b refers to different second-level age intervals, e refers to different second-level heat intervals, b=1, 2, ..., r1, r1 is the number corresponding to the second-level age intervals, c=1, 2, ..., r2, r2 is the number corresponding to the second-level height intervals, c=1, 2, ..., r2, e=1, 2, ..., r3, r3 is the number corresponding to the second-level heat intervals, r1, r2 and r3 are all positive integers and are all greater than or equal to 1.

7. A one-key deep sleep scene control method for a hotel smart room according to claim 6, characterized in that: The specific method of combining and generating multiple reference interval groups is as follows: Combine each secondary age interval UAb with each secondary height interval UBc and each secondary temperature interval UCe to generate multiple reference interval groups Wg(UAb, UBc, UCe), where g is a different reference interval group, g=1, 2, ..., t, where t is the number of reference interval groups, t=r1×r2×r3.

8. A one-key deep sleep scene control method for a hotel smart room according to claim 7, characterized in that: The specific method for obtaining the bedside light reference brightness and indoor reference temperature corresponding to each reference interval group in the one-key deep sleep scene when staying in a hotel single room is: S1: Select one group from each reference interval group as the analysis group; S2: Mark the bedside light brightness and indoor temperature corresponding to the one-key deep sleep scenario when multiple analysis groups of people check into a single room in a hotel as HAu and HBu respectively, where u refers to different people in the analysis group, obtain the value HAv in HAu that satisfies |HAu-HAp|≥Y2, where Y2 is a preset value, when the number v is greater than the preset threshold value Y1, define the mean HAp of HAu as the bedside light reference brightness CT1 corresponding to the analysis group, when the number v is less than or equal to the preset threshold value Y1, define the mean of the maximum and minimum values ​​in HAu as the bedside light reference brightness CT1 corresponding to the analysis group; adopt the same method to analyze the values ​​of the indoor temperature HBu that satisfies |HBu-HBp|≥Y4, and then obtain the indoor reference temperature CL1 corresponding to the analysis group, where Y4 is a preset value and HBp is the mean of HBu; S3: Repeat steps S1-S2 to obtain the bedside light reference brightness CTg and indoor reference temperature CLg corresponding to each reference interval group.

9. A one-key deep sleep scene control method for a hotel smart room according to claim 8, characterized in that: The specific method of obtaining the reference interval to which the real-time personnel belong is: According to the age, height and heat area corresponding to the real-time personnel, a comparison parameter group corresponding to the real-time personnel is generated, and the comparison parameter group corresponding to the real-time personnel is compared and analyzed with each reference interval group to obtain the reference interval to which the comparison parameter group belongs, and thus the reference interval to which the real-time personnel belongs can be obtained.

10. A one-key deep sleep scene control system for a hotel smart room, the system is operated based on a one-key deep sleep scene control method for a hotel smart room according to any one of claims 1 to 9, characterized in that: include; The data acquisition module collects historical occupant information and portrait data of hotel single rooms, providing basic data for subsequent analysis, including key information such as age, height, and body shape; The data analysis module analyzes the historical occupant information and portrait data to determine the first-level age range, first-level height range, and first-level heat range; The interval division module divides the first-level age interval, the first-level height interval and the first-level heat interval into multiple second-level age intervals, second-level height intervals and second-level heat intervals; A reference interval group generation module combines different secondary age intervals, secondary height intervals and secondary heat intervals to generate multiple reference interval groups; The benchmark control parameter value acquisition module analyzes the bedside light brightness and indoor temperature of the occupants in each reference interval group in the one-key deep sleep scenario to obtain the benchmark control parameter value; The reference interval matching module obtains the personal information and portrait data of the real-time occupants staying in the hotel's single room, compares and analyzes them with each reference interval group, finds the matching reference interval group, and adjusts the bedside light brightness and indoor temperature of the room where the real-time occupants are located in the one-button deep sleep scenario according to the corresponding benchmark control parameters.

Images