Hotel operation virtual simulation analysis method and system and storage medium

Abstract

The invention belongs to the technical field of hotel operation virtual simulation analysis, and particularly discloses a hotel operation virtual simulation analysis method and system and a storage medium, and the method comprises the steps: integrating construction data, historical operation logs and other multi-source data, and carrying out the multi-dimensional correlation analysis through the simulation initial data; the problem of decision deviation caused by the fact that a traditional method depends on artificial experience is solved, and operation bottleneck problems such as a service efficiency threshold value and resource allocation conflicts can be accurately recognized through a three-dimensional simulation model, so that high-precision data support is provided for optimization decision. Competition pricing data are collected in real time through a web crawler tool, competition influence factors are monitored, the check-in waiting loss probability is analyzed, in combination with environment monitoring data, competition opponent strategy change and market change data can be synchronized in real time, dynamic pricing weight parameters are loaded in a three-dimensional simulation model, the customer waiting duration and the loss rate are reduced, and the user experience is improved. And the technical efficiency of service resource scheduling is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of hotel operation virtual simulation analysis, and relates to a hotel operation virtual simulation analysis method, system and storage medium. Background Art

[0002] With the rapid development of the global tourism industry, the market competition environment faced by the hotel industry is becoming increasingly complex. The growth of tourism demand has driven a sharp increase in the number of hotels. However, traditional operation decision-making methods rely on manual experience and static historical data analysis, making it difficult to cope with dynamic market changes. In the prior art, for example, Chinese Patent CN118411090A proposes a virtual simulation experiment system for hotel operation management based on artificial intelligence, which generates a hotel model by presetting parameters and iteratively optimizes operation strategies. However, this solution still has the following technical limitations:

[0003] Insufficient technology for monitoring competition dynamics: The existing system does not integrate a real-time data collection module and an algorithm for dynamically analyzing competition factors, and cannot track competitors' strategies in real time through multi-source data (such as pricing on online sales platforms and service feature scores), resulting in a lag in market response. For example, when a competitor adjusts pricing or launches innovative services, there is a lack of an automated monitoring and analysis mechanism, making it difficult to generate response decisions in a timely manner.

[0004] Defects in customer churn risk modeling: During peak check-in periods, the prior art does not combine real-time environmental parameters (such as meteorological conditions and regional personnel endurance scores) with service efficiency indicators (such as waiting times feedback from video surveillance), and cannot construct a churn probability prediction model through multi-dimensional data fusion. For example, the impact of extreme weather or price fluctuations of surrounding hotels on customers' waiting tolerance has not been quantified, resulting in the inability to accurately optimize resource allocation and dynamic pricing strategies.

[0005] The above technical problems result in the operation decisions output by the existing virtual simulation system lacking real-time nature and pertinence, making it difficult to effectively reduce the customer churn rate and improve service efficiency. Therefore, there is an urgent need for a virtual simulation technical solution that integrates real-time data collection, dynamic competition analysis, and multi-factor churn probability modeling to solve the technical defects of the existing system. Summary of the Invention

[0006] In view of this, in order to solve the problems raised in the above background art, a hotel operation virtual simulation analysis method, system and storage medium are now proposed.

[0007] The object of the present invention can be achieved by the following technical solutions: The present invention provides a method for virtual simulation analysis of hotel operation, and the method includes the following steps: S1. Collect the construction data of each hotel location through a collection terminal, and call the historical operation logs of each hotel location in the historical database, extract the operation service data and operation result data, generate the initial simulation data, and construct a three-dimensional simulation model of each hotel location based on the simulation software.

[0008] S2. Analyze the purchase costs of each hotel location in each operation period, integrate the regional environment data of each hotel location in the geographic information system, determine the basic room pricing of each hotel location in each operation period, and establish a daily reception operation mode for the services of each hotel location.

[0009] S3. Collect the competitive influencing factors of each hotel location in each operation period through web crawlers, and analyze the probability of occupancy waiting loss of each hotel location in each operation period in the three-dimensional simulation model.

[0010] S4. Set the regional environmental conditions of each hotel location in the three-dimensional simulation model, determine the optimization decisions of each hotel location, export the simulation operation effect data of each hotel location, and judge the expected results of the optimization decisions of the simulation operation of each hotel location.

[0011] The second aspect of the present invention provides a virtual simulation analysis system for hotel operation, including: a model data generation module, which is used to obtain the construction data of each hotel location, and investigate the historical operation logs of each hotel location, including operation service data and operation result data, generate the initial simulation data of each hotel location, and construct a three-dimensional simulation model of each hotel location through the simulation software.

[0012] An operation mode establishment module, which is used to analyze the purchase costs of each hotel location in each operation period, accumulate the regional environment data of each hotel location, determine the basic room pricing of each hotel location in each operation period, and establish a daily reception operation mode for the services of each hotel location.

[0013] A competition analysis and loss probability evaluation module, which is used to monitor the competitive influencing factors of each hotel location in each operation period, and analyze the probability of occupancy waiting loss of each hotel location in each operation period.

[0014] An operation decision judgment module, which is used to set the regional environmental conditions of each hotel location in the three-dimensional simulation model, determine the optimization decisions of each hotel location, export the simulation operation effect data of each hotel location, and judge the expected results of the optimization decisions of the simulation operation of each hotel location.

[0015] The third aspect of the present invention provides a storage medium storing one or more programs, which can be executed by one or more processors to implement the steps in the virtual simulation analysis method for hotel operation described in the present invention.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0017] 1. By integrating and constructing multi-source data such as data and historical operation logs, and using simulation initial data for multi-dimensional correlation analysis, the present invention solves the problem of decision-making deviation caused by traditional methods relying on manual experience, and can accurately identify operation bottlenecks such as service efficiency thresholds and resource allocation conflicts through a three-dimensional simulation model, thereby providing high-precision data support for optimization decisions.

[0018] 2. Based on the integration of regional environmental data of the geographic information system and combined with cost calculation, the present invention quantifies the impact of the flow convergence factor on pricing through association rule mining technology, enables the basic room pricing model to adapt to changes in the regional environment, realizes the dynamic adjustment of resource allocation parameters, and thus improves the prediction accuracy of simulation operation revenue.

[0019] 3. By using a web crawler tool to collect competitive pricing data in real time, monitor competitive influencing factors and analyze the probability of occupancy waiting loss, and combining with environmental monitoring data, the present invention can synchronize the changes in competitors' strategies and market changes in real time, and load dynamic pricing weight parameters in the three-dimensional simulation model, reduce the customer waiting time and loss rate, and improve the technical efficiency of service resource scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0021] Figure 1 It is a schematic flow chart of the implementation steps of the method of the present invention.

[0022] Figure 2 It is a schematic diagram of the connection of system modules of the present invention.

[0023] Figure 3 It is a schematic diagram of the corresponding data construction module of the simulation software of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0025] Please refer to Figure 1 As shown, the present invention provides a virtual simulation analysis method for hotel operation, and the method includes the following steps: S1. Obtain the construction data of each hotel location, including the hotel address, the number of hotel rooms, the floor area, etc., and investigate the historical operation logs of each hotel location, including operation service data and operation result data. The operation service data includes the number of daily received guests, the number of service staff, the service duration, and the room price during each operation period. The operation result data includes the proportion of the loss of checked-in guests and the average waiting time of checked-in guests per day during each operation period. Generate the simulation initial data of each hotel location, and construct a three-dimensional simulation model of each hotel location through simulation software, where the service staff can refer to the cleaning staff.

[0026] The proportion of the loss of checked-in guests refers to the proportion of the number of guests who are lost because the hotel rooms cannot be cleaned or are not cleaned in time during the peak housing period, resulting in a too long waiting time for check-in. Checking in means providing a room card and the guest can enter the guest room. During the peak check-in and peak demand periods, the hotel may not have enough cleaners and the front desk may not have enough time to verify the room inspection and modify the room status to clean and available for sale, resulting in the inability to clean the guest rooms and the rooms that are not cleaned and available for sale. Guests need to wait for check-in. At this time, the waiting guests will search for nearby hotels of the same type with available rooms and lower or the same price. Especially when multiple people need to check into multiple rooms, for example, if they wait for 1 hour, some customers will definitely be lost.

[0027] The average waiting time of checked-in guests per day refers to the average waiting time for multiple checked-in guests to complete the check-in procedures and for the guest rooms to be cleaned and converted into the status of available for sale.

[0028] In the embodiment, the generation of the simulation initial data of each hotel location includes: obtaining, from the operation result data of the historical operation logs of each hotel location, the operation periods in which the proportion of the loss of checked-in guests in each corresponding operation period of each hotel location exceeds the preset loss proportion threshold, and recording them as the operation congestion periods of each hotel location. For example, the preset loss proportion threshold is 10%, that is, when the proportion of the loss of checked-in guests in a certain period exceeds 10%, it is recorded as the operation congestion period.

[0029] Analyze the operational congestion level of each hotel location, and determine the number of service staff and the daily reception capacity corresponding to the operational service data during the operational congestion period for each hotel location.

[0030] According to market demand and forecasts, divide the proportion of the occupancy loss rate into different intervals, and determine the appropriate operational congestion level for each interval of the occupancy loss rate. For example: when the occupancy loss rate interval is 10%-30%, the operational congestion level is low. At this time, set the number of room cleaning staff for the corresponding operational service data of the hotel location to 1 person, and the daily reception capacity to 10 people; when the occupancy loss rate interval is 30%-60%, the operational congestion level is medium. At this time, set the number of room cleaning staff for the corresponding operational service data of the hotel location to 2 people, and the daily reception capacity to 15 people; when the occupancy loss rate interval is 60%-100%, the operational congestion level is high. At this time, set the number of room cleaning staff for the corresponding operational service data of the hotel location to 3 people, and the daily reception capacity to 20 people.

[0031] Obtain the number of service staff and the daily reception capacity corresponding to the operational service data during the operational congestion period for each hotel location, and adjust and set them as the corresponding simulation initial data for each hotel location. For example: if the operational service data corresponding to the operational congestion period of a hotel location is 3 room cleaning staff and an occupancy of 20 people, then set the number of room cleaning staff in the corresponding simulation initial data of this hotel location to 3 people and the occupancy to 20 people.

[0032] Based on the historical logs of hotel operations, establish simulation data to make the operational state of the simulation data closer to the actual situation, and the results of the simulation analysis more in line with actual needs; setting the simulation operation conditions based on the data during the congestion period helps to increase the test validity of the simulation data.

[0033] If the proportion of the loss rate of a hotel location during multiple operational periods continues to be higher than the industry average level or the threshold set by the hotel itself, or the average waiting time for daily reception at the hotel always exceeds the reasonable range, it indicates that there may be problems with the hotel's reception process, and thus it may be necessary to optimize the marketing strategy, such as providing more attractive promotional activities to improve customer loyalty.

[0034] For special instructions, please refer to Figure 3As shown in the figure, in simulation software (such as AnyLogic, Simul8, Arena, etc.), a model is constructed through a data collection module, a congestion judgment module, and a simulation data import module according to the following steps: In the data collection module, after monitoring the arrival of customers at the hotel through a monitoring device, data such as the status of customers and room cleaning staff completing the room status, and the waiting time and processing time of the front desk staff confirming and adjusting the room status are collected; in the congestion judgment module, it is analyzed whether the check-in period of customers is during the operation congestion period. When it is during the operation congestion period, the collected data is imported into the simulation model, and the initial simulation data is adjusted; furthermore, in the simulation data import module, by detecting the regional environmental data, competitive influencing factors, etc. in the subsequent steps, a complete operation simulation model is established to judge the expected result of the optimization decision of the hotel location simulation operation.

[0035] The present invention can provide a large amount of objective and accurate information for hotel managers by comprehensively collecting multi-source data such as construction data and historical operation logs of each hotel location, conducting in-depth analysis and simulation, which helps to discover potential problems and bottlenecks in the operation process, and further helps to analyze reasonable operation decisions. For example, through simulation, it can be observed whether the hotel reception process is smooth and whether the personnel allocation is reasonable during different operation periods. Based on these findings, the hotel can optimize the reception process and adjust the personnel arrangement accordingly to improve operation efficiency and service quality.

[0036] S2. Analyze the purchase costs of each hotel location during each operation period, accumulate the regional environmental data of each hotel location, determine the basic room pricing of each hotel location during each operation period, and establish the daily reception operation mode of each hotel location service.

[0037] In the embodiment, the analysis of the purchase costs of each hotel location during each operation period includes: obtaining the number of service personnel of each hotel location during each operation period, and determining the service costs of each hotel location during each operation period. For example, the number of service personnel of a certain hotel location during the operation period from 16:00 to 22:00 is 3, and the hourly wage of the hotel service personnel is set at 15 yuan / hour. Then, the service cost of this hotel location during this operation period is determined as: hourly wage of service personnel × number of service personnel × duration of operation period = 15 yuan / hour × 3 × 6 hours = 270 yuan, to ensure that the room cleaning is completed and converted into a sellable state.

[0038] Based on the construction data of each hotel location, taking the revenue demand cost during the operation period as a unit, determine the basic construction cost of each hotel location, and accumulate it with the service cost of the corresponding hotel location during each operation period to obtain the acquisition cost of each hotel location during each operation period. For example, the basic construction cost of a certain hotel location is 50 yuan per period, and accumulate it with the service cost of 45 yuan of the corresponding hotel location during a certain operation period to obtain the acquisition cost of 95 yuan of this hotel location during this operation period.

[0039] The basic construction cost of each hotel location is professionally calculated by professionals based on the hotel address, the number of hotel rooms, the floor area of the hotel construction data, and by investigating the local regional land construction costs.

[0040] In the embodiment, accumulate the regional environment data of each hotel location to determine the basic room price of each hotel location during each operation period. The content includes: through research methods such as OTA platforms, official websites, and on-site inspections, research the regional environment data of each hotel location, including scenic area scale data samples, meteorological law data samples, competition data samples, and personnel consumption levels.

[0041] The scenic area scale data samples such as the tourist carrying capacity of the scenic area, the types of scenic area buildings (such as plant viewing areas, building viewing areas, activity performance exhibition halls), etc.; the meteorological law data samples such as sunny weather, extreme weather; the competition data samples such as the number, type, star rating, room price, occupancy rate, etc. of surrounding hotels; the personnel consumption levels such as the consumption amounts, consumption frequencies, etc. of different customer source groups (business travel groups, leisure vacation groups) in aspects such as accommodation, catering, and entertainment in the hotel location area.

[0042] Use association rule mining technology to mine the association effect factors between the regional environment data of each hotel location and the room pricing, including a first type of passenger flow convergence effect factor a1 j 、a second type of passenger flow convergence effect factor a2 j and a passenger flow diffusion effect factor b j , where j represents the number of each hotel location, j = 1, 2,..., z.

[0043] Research the room prices of surrounding competing hotels in the area where each hotel location is located, including the prices of different room types (such as standard rooms, luxury rooms, suites). At the same time, collect the changes in market demand in different seasons and holidays, determine the price floating range during peak and off-peak periods, and determine the market basic pricing of each hotel location during each operation period. Different periods such as the peak customer volume stage, the normal customer volume stage, and the off-peak customer volume stage. When the hotel is in the peak customer volume stage, slightly increase the market basic pricing of the hotel location; when the hotel is in the off-peak customer volume stage, slightly decrease the market basic pricing of the hotel location.

[0044] Combined with the acquisition costs of each hotel location during each operation period and each associated influencing factor, construct the formula for the basic room pricing relationship of each hotel location during each operation period, and determine the basic room pricing of each hotel location during each operation period.

[0045] Specifically, the formula for constructing the basic room pricing relationship of each hotel location during each operation period is designed by hotel operation managers according to operation requirements. Exemplarily, based on the fact that the hotel scenic area building type is affected by factors such as tourist dates, meteorological environment, and consumption levels during the operation period, the formula is set as follows: Derive the basic room pricing Y of each hotel location during each operation period jk , where k represents the number of each operation period, k = 1, 2,..., c, and y1 jk represents the acquisition cost of the jth hotel location during the kth operation period, reflecting the influence degree of the self-paid cost of the hotel location during the operation period on the basic room pricing. y2 jk represents the market basic pricing of the jth hotel location during the kth operation period, reflecting the floating degree of the market basic pricing caused by the influence of each associated influencing factor on the hotel location during the operation period. It is set within the range of (-1, 1). At the same time, the acquisition cost is restricted within the range of (0, 1) through to limit the final determined value of the market basic pricing from exceeding the normal range.

[0046] Determining the basic room pricing of each hotel location during each operation period based on the acquisition cost and the market basic pricing can ensure that the hotel gradually recovers these costs during long-term operation, and can accurately position the hotel at an appropriate market level, avoiding losses caused by blind price cuts, and thus maintaining the normal operation and sustainable development of the hotel.

[0047] When considering the acquisition cost, the basic room pricing of the hotel needs to take into account the budget cost. Compare the acquisition cost of the hotel location with the budget cost. When the acquisition cost of the hotel location is relatively high compared to the budget cost, the basic room pricing can be appropriately increased within the range of the market basic pricing.

[0048] In the embodiment, the associated influencing factors between the regional environment data of each hotel location and the room pricing are mined through the association rule mining technology. The content includes: investigating the scenic area building type corresponding to each hotel location, and mining the association rules between it and the extreme weather in the meteorological regular data sample of the corresponding hotel location according to the association rule mining technology, and constructing the dependence proportion between the scenic area building type corresponding to each hotel location and the extreme weather in the meteorological regular data sample of the corresponding hotel location, which is recorded as a type of passenger flow convergence influencing factor of each hotel location.

[0049] The described dependence proportion refers to the degree of association between data.

[0050] The described association rule mining is a data mining technique aimed at discovering interesting associations or correlations from large datasets. It involves a series of specific algorithm steps for finding frequent item sets from the dataset and generating association rules. These algorithms generally follow certain computational and search patterns to discover the associations between different items in the dataset. When the building type and meteorological data exist in a categorical form, such as different types of buildings (seaside hotels, mountain-view hotels) and extreme weather (snowy days, rainy days that are not conducive to people traveling), it is possible to construct various frequent item sets between the scenic area building types corresponding to each hotel location and the extreme weather in the meteorological law data samples, derive the probabilities of the occurrence of these frequent item sets, and accumulate the comprehensive probabilities of the frequent item sets between the scenic area building types corresponding to each hotel location and the extreme weather in the meteorological law data samples corresponding to the hotel location. This is the dependence proportion between the scenic area building types corresponding to each hotel location and the extreme weather in the meteorological law data samples corresponding to the corresponding hotel location.

[0051] Investigate the consumption levels of people corresponding to each hotel location, and mine the dependence proportion between them and the competition data samples corresponding to the hotel location, which is recorded as the secondary population flow convergence factor for each hotel location.

[0052] Specifically, organize the consumption level data of people in the areas corresponding to each hotel location. At the same time, collect the competition data of each hotel location. Use the association rule mining algorithm to mine various frequent item sets between the consumption levels of people corresponding to each hotel location and the competition data samples. For example, it may be found that two item sets, such as "the accommodation consumption frequency of a certain customer group" and "a certain star-rated or certain type of hotel in the vicinity", often appear simultaneously for a certain hotel location, forming a frequent item set for that hotel location. Derive the occurrence probabilities of the various frequent item sets between the consumption levels of people corresponding to each hotel location and the competition data samples, and accumulate the comprehensive probabilities of the frequent item sets between the consumption levels of people corresponding to each hotel location and the competition data samples. This is recorded as the dependence proportion between the consumption levels of people corresponding to each hotel location and the competition data samples.

[0053] Collect holiday data samples and count the sunny weather in the meteorological law data samples of each hotel location, including sunny days and cloudy weather that are conducive to people going out. Mine the dependence proportion between them and the holiday data samples, which is recorded as the population flow diffusion factor for each hotel location.

[0054] Specifically, the association rule mining algorithm is used to mine the occurrence probabilities of the frequent itemsets between the holiday data samples and the meteorological regular data samples of each hotel location in sunny weather. For example, the occurrence probability of the frequent itemset where the two itemsets of "sunny day" and "National Day" appear simultaneously. The comprehensive probability of the frequent itemsets between the holiday data samples and the meteorological regular data samples of each hotel location in sunny weather is accumulated and denoted as the dependence proportion between the holiday data samples and the meteorological regular data samples of each hotel location in sunny weather.

[0055] By analyzing the acquisition costs and regional environmental data of each hotel location, the present invention can help hotels rationally allocate resources, thereby improving operational revenue. For example, when determining the basic room price, the acquisition costs and regional environmental data are comprehensively considered, avoiding the blindness of simply relying on experience for pricing, making the pricing strategy more in line with the actual market situation and the hotel's own operational needs, and thus making more scientific and reasonable decisions.

[0056] S3. Monitor the competitive influencing factors of each hotel location during each operation period, and analyze the probability of occupancy waiting loss of each hotel location during each operation period.

[0057] In the embodiment, the content of monitoring the competitive influencing factors of each hotel location during each operation period and analyzing the probability of occupancy waiting loss of each hotel location during each operation period includes: using a web crawler tool to crawl the online sales platform of the hotel, and investigating the competitive influencing factors of each hotel location, including the service characteristics and their audience rating g1 of the hotels near each hotel location j , obtaining the personalized service characteristics and their audience rating g2 of each hotel location j , including brand competition, room preference theme, diet restrictions, etc., and comparing to generate the service competition rate of each hotel location Among them, ep1 represents that the service characteristics of the hotels near the hotel location are the same as the personalized service characteristics of the corresponding hotel location, and ep2 represents that the service characteristics of the hotels near the hotel location are different from the personalized service characteristics of the corresponding hotel location.

[0058] The audience ratings of the service characteristics of the hotels near each hotel location and the audience ratings of the personalized service characteristics of each hotel location are both integrated and calculated by the online sales platform based on the scores independently given by multiple customers. For example, if the scores independently given by multiple customers for the personalized service characteristics of a certain hotel location are 4 points, 5 points, and 3 points, then the customer audience rating of the personalized service characteristics of this hotel location can be integrated into an average score of 4 points.

[0059] Detect the regional environmental conditions of each hotel location through a meteorological platform, including extreme weather and sunny weather. Import the regional environmental conditions of each hotel location into the 3D simulation model, and set the endurance score g3 of the personnel belonging to the regional environmental conditions of each hotel location. j g3 j belongs to 1 - 5 points. For example, when the meteorological platform detects that the regional environmental condition of a hotel location is extreme weather, due to travel obstacles, the check-in personnel may be more willing to wait for check-in at the hotel where they are currently located. The endurance score of the personnel belonging to the regional environmental condition of the hotel location can be adjusted to 4 points. When the meteorological platform detects that the regional environmental condition of a hotel location is sunny weather, the check-in personnel may be more willing to visit and compare nearby hotels before making a check-in decision. Therefore, the endurance score of the personnel belonging to the regional environmental condition of the hotel location can be adjusted to 2 points.

[0060] Use a web crawler tool to crawl the room prices of each nearby hotel corresponding to each hotel location during each operation period, and compare and screen to select the minimum value as the competitive price Y′ of each nearby hotel corresponding to each hotel location during each operation period. jk Compare it with the basic room price of the corresponding hotel location during the corresponding operation period, and combine the service competition rate and the endurance score of the personnel belonging to the regional environmental condition of each hotel location. Analyze the probability Loss of check-in waiting loss of each hotel location during each operation period by constructing a formula. jk .

[0061] Exemplarily, the constructed formula is Among them, To map the preferential degree between the room price of the hotel location itself and the room prices of nearby hotels, g′ represents a preset reference endurance score. To map the endurance degree corresponding to the endurance score of the personnel belonging to the regional environmental condition of each hotel location, it can be set to 1 point. w1 and w2 respectively represent the preset weight coefficients corresponding to the service competition rate and the personnel endurance score, which are set according to the hotel operation requirements. If the hotel operation pays more attention to the popularity of personalized services, w1 can be set to 0.6 and w2 can be set to 0.4. If the hotel operation pays more attention to the check-in service business, w1 can be set to 0.4 and w2 can be set to 0.6.

[0062] S4. Set the regional environmental conditions of each hotel location in the 3D simulation model, determine the optimization decisions of each hotel location, export the simulation operation effect data of each hotel location, and judge the expected results of the optimization decisions of the simulation operations of each hotel location, including positive and negative.

[0063] In an embodiment, setting the regional environmental conditions of each hotel location in the 3D simulation model and determining the optimization decisions for each hotel location includes: real-time monitoring of the daily connection waiting time of the occupants at each hotel location during each operation period through video surveillance, taking into account the occupancy waiting loss probability at each hotel location during each operation period, integrating and processing to obtain the occupancy waiting pricing preference level weight at each hotel location during each operation period, and generating the room pricing for the occupancy waiting personnel at each hotel location during each operation stage.

[0064] For example: If the video surveillance shows that the daily connection waiting time of a certain occupant at a certain hotel location during a certain operation period is 0.5 hours, and at this time the occupancy waiting loss probability of this hotel location during this operation period is obtained as 0.32, the occupancy waiting pricing preference level weight can be obtained through the integration formula: occupancy waiting pricing preference level weight = (daily connection waiting time of the occupant / preset reference waiting time) × occupancy waiting loss probability = (0.5 hours / 0.1 hours) × 0.32 = 1.6, and the occupancy waiting pricing preference level weight of 1.6 for this occupant at this hotel location during this operation period is obtained.

[0065] Obtain the basic room pricing of this hotel location during this operation period. If it is 130 yuan per room, then according to the formula: room pricing for the occupancy waiting personnel = basic room pricing × [occupancy waiting pricing preference level weight / (occupancy waiting pricing preference level weight + 1)], generate the room pricing for the occupancy waiting personnel at this hotel location during this operation period.

[0066] When the hotel operation stage is in the peak customer volume stage, there may be a conflict between the hotel service time and the inflow time of people, resulting in the loss of customers due to excessive waiting time. Therefore, the hotel service strategy can be adjusted to ensure the hotel occupancy rate.

[0067] In an embodiment, judging the expected result of the optimization decision for the simulation operation of each hotel location includes: importing the room pricing for the occupancy waiting personnel at each hotel location during each operation stage into the 3D simulation model for trial operation, exporting the proportion of the occupancy loss of the corresponding occupants during each operation period in the trial operation stage for each hotel location, and calculating the average proportion of the occupancy loss of the occupants during the trial operation stage for each hotel location through mean value calculation.

[0068] Similarly, calculate the average proportion of the occupancy loss of the occupants in the operation result data in the historical operation log of each hotel location through mean value calculation, and compare it with the average proportion of the occupancy loss of the occupants during the trial operation stage of the corresponding hotel location. If the average proportion of the occupancy loss of the occupants in the operation result data in the historical operation log of a certain hotel location is lower than the average proportion of the occupancy loss of the occupants during the trial operation stage of the corresponding hotel location, it is judged that the expected result of the optimization decision for the simulation operation of this hotel location is positive.

[0069] If the mean proportion of the occupancy loss volume of the operation result data in the historical operation log of each hotel location selection is higher than the average proportion of the occupancy loss volume during the trial operation stage of the corresponding hotel location selection, it is determined that the expected result of the optimization decision of the hotel location selection simulation operation is negative.

[0070] Specifically, judging the expected result of the optimization decision of the hotel location selection simulation operation helps the enterprise to make auxiliary decisions on hotel operation optimization. When the expected result of the optimization decision of the hotel location selection simulation operation is positive, it indicates that the simulation operation optimization decision is an effective measure, and further optimization and improvement can be carried out on the basis of this simulation model. When the expected result of the optimization decision of the hotel location selection simulation operation is negative, it indicates that the simulation operation optimization decision is an ineffective measure, and other decision settings are required.

[0071] Through monitoring competitive influencing factors and analyzing the probability of occupancy waiting loss, the hotel can timely understand the dynamics of competitors and market change trends. For example, when it is found that a competitor launches a new preferential activity or service feature, the hotel can quickly adjust its own operation strategy according to the simulation results, such as adjusting room prices, optimizing service content, etc., to improve its market competitiveness and attract more customers. Furthermore, by optimizing the operation mode and decision-making, the hotel can reduce the occupancy waiting time and loss probability of customers, and improve service quality and efficiency. For example, reasonable room prices and high-quality reception services can enable customers to experience better consumption, thereby enhancing customer satisfaction and loyalty and establishing a good brand image for the hotel.

[0072] Please refer to Figure 2 As shown, a hotel operation virtual simulation analysis system provided by the second aspect of the present invention includes: a model data generation module, an operation mode establishment module, a competition analysis and loss probability evaluation module, and an operation decision judgment module.

[0073] The model data generation module is connected to the operation mode establishment module, the operation mode establishment module is connected to the competition analysis and loss probability evaluation module, and the competition analysis and loss probability evaluation module is connected to the operation decision judgment module.

[0074] The model data generation module is used to obtain the construction data of each hotel location selection, investigate the historical operation log of each hotel location selection, including operation service data and operation result data, generate the simulation initial data of each hotel location selection, and construct a three-dimensional simulation model of each hotel location selection through simulation software.

[0075] The operation mode establishment module is used to analyze the purchase cost of each hotel location selection in each operation period, accumulate the regional environment data of each hotel location selection, determine the basic room price of each hotel location selection in each operation period, and establish the daily reception operation mode of each hotel location selection service.

[0076] The competition analysis and churn probability evaluation module is used to monitor the competition influencing factors of each hotel location during each operation period and analyze the occupancy waiting churn probability of each hotel location during each operation period.

[0077] The operation decision-making judgment module is used to set the regional environmental conditions of each hotel location in the 3D simulation model, determine the optimization decisions of each hotel location, export the simulation operation effect data of each hotel location, and judge the expected results of the optimization decisions of the simulation operation of each hotel location.

[0078] The third aspect of the present invention provides a storage medium storing one or more programs, which can be executed by one or more processors to implement the steps in a virtual simulation analysis method for hotel operation according to the present invention.

[0079] The above content is only an example and illustration of the concept of the present invention. Those skilled in the art of the present technology can make various modifications or supplements to the described specific embodiments or use similar methods for substitution, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. A virtual simulation analysis method for hotel operation, characterized in that: The method comprises the following steps: S1. Collect the construction data of each hotel site through the collection terminal, call the historical operation log of each hotel site in the historical database, extract the operation service data and operation result data, generate the simulation initial data, and build the three-dimensional simulation model of each hotel site based on the simulation software; S2. Analyze the acquisition cost of each hotel site in each operating period, integrate the regional environmental data of each hotel site in the geographic information system, determine the basic room pricing of each hotel site in each operating period, and establish the daily reception operation model of each hotel site service; S3. Collect the competitive influencing factors of each hotel location in each operating period through a web crawler, and analyze the probability of occupancy waiting loss of each hotel location in each operating period in a three-dimensional simulation model; S4. Set the regional environmental conditions for each hotel site in the three-dimensional simulation model, determine the optimal decision for each hotel site, export the simulation operation effect data for each hotel site, and determine the expected results of the optimal decision for each hotel site simulation operation.

2. A hotel operation virtual simulation analysis method according to claim 1, characterized in that: The generation of the simulation initial data for each hotel location includes: obtaining the proportion of occupancy loss in each operation period of each hotel location from the operation result data of the historical operation log of each hotel location, and obtaining the operation period in which the proportion of occupancy loss exceeds the preset threshold value, which is recorded as the operation congestion period of each hotel location; Analyze the operational congestion level of each hotel location, and determine the number of service personnel and daily reception staff corresponding to the operational service data during the operational congestion period of each hotel location; The number of service personnel and the number of daily reception staff in the corresponding operation service data during the operation congestion period of each hotel location are obtained, and set as the corresponding simulation initial data for each hotel location.

3. A hotel operation virtual simulation analysis method according to claim 2, characterized in that: The analysis of the purchase cost of each hotel site in each operating period includes: obtaining the number of service personnel of each hotel site in each operating period, and determining the service cost of each hotel site in each operating period; Based on the construction data of each hotel site, the basic construction cost of each hotel site is determined in units of revenue demand cost during the operating period. The basic construction cost is then accumulated with the service cost of the corresponding hotel site in each operating period to obtain the purchase cost of each hotel site in each operating period.

4. A hotel operation virtual simulation analysis method according to claim 1, characterized in that: The accumulated regional environmental data of each hotel site is used to determine the basic room pricing of each hotel site during each operating period, including: Investigate the regional environmental data of each hotel site, including scenic area scale data samples, meteorological law data samples, competition data samples, and personnel consumption levels; Through association rule mining technology, the correlation factors between the regional environmental data of each hotel location and room pricing are mined, including the first-class crowd flow convergence factor, the second-class crowd flow convergence factor and the crowd flow diffusion factor; Determine the market-based pricing for each hotel location during each operating period; Based on the purchase cost of each hotel location in each operating period and various related factors, a formula for the basic room pricing relationship of each hotel location in each operating period is constructed to determine the basic room pricing of each hotel location in each operating period.

5. A hotel operation virtual simulation analysis method according to claim 4, characterized in that: The association rule mining technology is used to mine the regional environmental data of each hotel location and the various correlation factors of room pricing, including: Investigate the scenic area building types corresponding to each hotel location, and use the association rule mining technology to mine the association rules between the scenic area building types corresponding to each hotel location and the extreme weather in the meteorological law data samples of the corresponding hotel location, and construct the dependency coefficient between the scenic area building types corresponding to each hotel location and the extreme weather in the meteorological law data samples of the corresponding hotel location, which is recorded as a type of crowd convergence factor for each hotel location; Investigate the consumption level of people corresponding to each hotel location, and explore the dependency ratio between it and the competitive data samples of the corresponding hotel location, which is recorded as the second type of passenger flow convergence factor of each hotel location; Collect holiday data samples, and count the sunny weather in the meteorological law data samples of each hotel location, and mine the dependency coefficient between it and the holiday data samples, which is recorded as the crowd diffusion factor of each hotel location.

6. A hotel operation virtual simulation analysis method according to claim 1, characterized in that: The monitoring of the competitive factors affecting each hotel location during each operating period and the analysis of the probability of occupancy waiting loss of each hotel location during each operating period include: By using web crawler tools to crawl the hotel's online sales platform, investigate the competitive factors affecting the location of each hotel, including the service characteristics and audience ratings of the corresponding nearby hotels of each hotel, obtain the corresponding personalized service characteristics and audience ratings of each hotel, and compare and generate the service competition rate of each hotel; The regional environmental conditions of each hotel location are detected through the meteorological platform, including extreme weather and sunny weather. The regional environmental conditions of each hotel location are imported into the 3D simulation model, and the endurance score of the personnel belonging to the regional environmental conditions of each hotel location is set; The competitive pricing of nearby hotels at each hotel location during each operating period is crawled and compared with the basic room pricing of the corresponding hotel location during the corresponding operating period. In combination with the service competition rate of each hotel location and the endurance score of the personnel under the regional environmental conditions, the probability of occupancy waiting loss of each hotel location during each operating period is analyzed.

7. A hotel operation virtual simulation analysis method according to claim 1, characterized in that: The regional environmental conditions of each hotel location are set in the three-dimensional simulation model to determine the optimal decision for each hotel location, including: real-time monitoring of the daily waiting time of occupants at each hotel location in each operating period through video surveillance, taking into account the probability of occupancy waiting loss at each hotel location in each operating period, integrating and processing to obtain the occupancy waiting pricing benefit weights of each hotel location in each operating period, and generating the occupancy waiting room pricing for each hotel location in each operating stage.

8. A hotel operation virtual simulation analysis method according to claim 7, characterized in that: The content of judging the expected results of the optimization decision of the simulated operation of each hotel site selection includes: importing the room pricing of the waiting staff of each hotel site selection in each operation stage into the three-dimensional simulation model, conducting trial operation, deriving the proportion of the corresponding staff loss of each hotel site selection in each operation period in the trial operation stage, and calculating the average to obtain the average proportion of the staff loss of each hotel site selection in the trial operation stage; Similarly, the average percentage of occupant turnover belonging to the operation result data in the historical operation log of each hotel location is calculated, and it is compared with the average percentage of occupant turnover of the corresponding hotel location during the trial operation stage to determine the expected results of the optimization decision of each hotel location simulation operation, including positive and negative results.

9. A hotel operation virtual simulation analysis system, characterized in that: include: The model data generation module is used to obtain the construction data of each hotel site, investigate the historical operation logs of each hotel site, including operation service data and operation result data, generate the initial simulation data of each hotel site, and construct a three-dimensional simulation model of each hotel site through simulation software; The operation model establishment module is used to analyze the acquisition cost of each hotel site in each operation period, accumulate the regional environmental data of each hotel site, determine the basic room pricing of each hotel site in each operation period, and establish the daily reception operation model of each hotel site service; Competition analysis and churn probability assessment module, used to monitor the competitive factors affecting each hotel location during each operating period, and analyze the occupancy waiting churn probability of each hotel location during each operating period; The operation decision judgment module is used to set the regional environmental conditions of each hotel site in the three-dimensional simulation model, determine the optimal decision of each hotel site, export the simulation operation effect data of each hotel site, and judge the expected results of the optimal decision of each hotel site simulation operation.

10. A storage medium, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the hotel operation virtual simulation analysis method as described in any one of claims 1-8.

Images