A cross-regional hotel resource scheduling management method for large-scale activities

Abstract

This invention relates to the fields of data processing and hotel resource management, specifically to a cross-regional hotel resource scheduling and management method for large-scale events. By collecting published information from event venues and monitoring event dates and reported scale, the method dynamically adjusts hotel prices based on the venue's size, number of parking lots and spaces, temporary pick-up and drop-off points, the availability of public transportation around the hotel, road conditions, pedestrian flow forecasts, and hotel resource information. During the event, the method dynamically updates forecast model parameters and adjusts scheduling strategies by comparing actual data with forecast results, forming a closed-loop optimization mechanism that continuously improves the accuracy and adaptability of scheduling.

Description

Technical Field

[0001] This invention relates to the fields of data processing and hotel resource management technology, specifically to a cross-regional hotel resource scheduling and management method for large-scale events. Background Technology

[0002] During the period when various large-scale events (such as large-scale exhibitions, sports events, concerts, expos, etc.) are held in a city, a large number of people from outside the city will flock to the host city in a short period of time, generating concentrated accommodation demand and putting great pressure on hotel resources around the event venue and within the city.

[0003] In existing technologies, hotel resource management is usually conducted on a per-hotel or fixed-area basis, lacking a systematic scheduling mechanism for large-scale events. On the one hand, hotels near event venues often experience abnormal price increases and room shortages during events, while hotels in other regions far from the venues have a large number of vacant rooms, resulting in a highly uneven distribution of resources. On the other hand, existing management methods are mostly reactive, meaning that manual intervention is only carried out after hotels are fully booked or prices are abnormal, making it impossible to predict and scientifically schedule resources in advance based on the scale and popularity of the event.

[0004] Furthermore, existing technologies, when determining the scope of hotel control, typically only set a fixed radius centered on the event venue, without considering the differences in parking capacity, temporary pick-up and drop-off points, and public transportation connections among different event venues. This results in control areas that are either too large, wasting management resources, or too small, failing to cover actual accommodation demand. When conducting cross-regional hotel scheduling, there is also a lack of quantitative assessment of surrounding traffic conditions, road capacity, and the hotel's actual carrying capacity. Scheduling decisions lack a scientific basis, impacting users' accommodation experience and travel convenience.

[0005] Therefore, how to predict, dynamically adjust, and scientifically schedule hotel resources around and across regions based on the scale, popularity, and traffic capacity of large-scale events has become a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0006] The purpose of this invention is to address the shortcomings of existing technologies by providing a method and apparatus for cross-regional hotel resource scheduling and management for large-scale events, thereby solving the technical problems of uneven hotel resource allocation, unreasonable control scope, and lack of scientific basis for cross-regional scheduling during large-scale events.

[0007] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0008] Firstly, this invention provides a method for cross-regional hotel resource scheduling and management for large-scale events. The method is executed in six stages: First, information on large-scale event venues within the target urban area is collected to identify the events to be held, and their dates and reported scale are monitored and recorded. Then, during a preset period before the event, the method continuously monitors the event's online popularity and calculates the online popularity index, while simultaneously recording the number of user intentions publicly available on ticketing platforms. Based on the collected event reporting scale, online popularity index, and number of intentions, a passenger flow prediction model is used to predict the passenger flow during the event and map it to accommodation demand. On this basis, the temporary transportation capacity of the event venue is used as the core criterion to dynamically delineate the hotel control range, and hotel prices within the control range are dynamically adjusted based on supply and demand ratio classification. Finally, by calculating the scheduling coefficient of each candidate hotel, hotel resources around the event venue and across regions are coordinated and scheduled.

[0009] In one embodiment of the present invention, the pedestrian flow prediction adopts a multiple linear regression model, with the reported scale as the basic parameter and the network popularity index and the number of intentions as correction parameters. The model coefficients are determined by training with historical activity data. The network popularity index is obtained by weighting and normalizing the number of mentions on social media, the number of searches on search engines, and the number of discussions on news portals according to preset weights.

[0010] In one embodiment of the present invention, the determination of the hotel control range is based on the exhibition hall transportation capacity index. This index comprehensively considers parameters such as the scale of the exhibition hall, the number of parking lots and parking spaces, the number of temporary parking pick-up and drop-off points, the number of public transportation routes, and the walking distance after getting off public transportation, and is obtained by weighted calculation after standardization. Different hotel control radii are set according to different levels of the capacity index.

[0011] In one embodiment of the present invention, the dynamic adjustment of hotel prices is based on a supply-demand ratio grading mechanism. The supply-demand tension is divided into five levels according to the ratio of the predicted accommodation demand to the total number of rooms within the control range, and each level corresponds to a different price fluctuation range.

[0012] In one embodiment of the present invention, the scheduling coefficient for cross-regional dispatch is calculated by weighting traffic convenience score, road accessibility score, and carrying capacity score according to preset weights. The road accessibility score is further subdivided into three sub-items: elevated expressway distance score, lane quantity score, and bus lane restriction score. When the occupancy rate of hotels near the event venue reaches a preset warning threshold, excess demand is dispatched to distant hotels according to priority.

[0013] In one embodiment of the present invention, the method further includes a closed-loop optimization step, which involves comparing actual data with predicted results during the event, and automatically updating model parameters and adjusting scheduling strategies when the deviation exceeds a threshold.

[0014] Secondly, the present invention provides a cross-regional hotel resource scheduling and management device for large-scale events. The device consists of an event information collection module, a heat monitoring module, a crowd flow prediction module, a hotel range adjustment module, a price control module, a scheduling coefficient calculation module, and a cross-regional scheduling module working together. Each module performs the corresponding steps in the above method.

[0015] Thirdly, the present invention provides a computer-readable storage medium storing at least one piece of program code, which is loaded and executed by a processor to implement the cross-regional hotel resource scheduling and management method for large-scale events as described in any of the above claims.

[0016] Beneficial effects:

[0017] First, by collecting information on the announcements of large-scale event venues and monitoring the event dates and reported scale, and by dynamically recording online popularity and the number of intentions on ticketing platforms in real time for a certain period from before the start of the event to after ticket sales, this invention can make advance predictions of visitor flow based on multi-dimensional information before the event, providing forward-looking data support for hotel resource scheduling and helping to alleviate the lag problem of post-event response management.

[0018] Secondly, this invention dynamically determines the hotel's control range based on temporary transportation capacity parameters such as the size of the event venue, the number and spaces of parking lots, temporary pick-up and drop-off points, the amount of public transportation, and walking distance. It can set control radii differently for the actual traffic capacity of different venues, avoiding the problem of control ranges being too large or too small due to fixed radius methods, which is conducive to improving the accuracy of hotel resource management.

[0019] Third, this invention uses the number of public transportation options around the hotel, road conditions (including distance to elevated expressways, number of lanes, and bus lane restriction times) and the hotel's actual carrying capacity as scheduling coefficients to jointly schedule hotel resources around event venues and across regions. This provides a quantitative basis for cross-regional scheduling decisions and helps to rationally guide accommodation demand to more conveniently located hotels when there is a shortage of rooms around event venues, thus achieving a balanced allocation of hotel resources.

[0020] Fourth, this invention dynamically adjusts hotel prices based on passenger flow forecasts and hotel resource information. By setting reasonable price fluctuation ranges through supply and demand ratio grading, it helps to suppress abnormal fluctuations in hotel prices during events and ensures a good user accommodation experience.

[0021] Fifth, this invention dynamically updates the parameters of the prediction model and adjusts the scheduling strategy by comparing actual data with the predicted results during the event, thus forming a closed-loop optimization mechanism that helps to continuously improve the accuracy and adaptability of scheduling. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of the overall process of a cross-regional hotel resource scheduling and management method for large-scale events provided in an embodiment of the present invention.

[0023] Figure 2 This is a schematic diagram of the sub-processes for predicting passenger flow and determining the scope of hotel control provided in an embodiment of the present invention.

[0024] Figure 3 This is a schematic diagram of the sub-processes for scheduling coefficient calculation and cross-regional hotel resource scheduling provided in an embodiment of the present invention.

[0025] Figure 4 This is a schematic diagram of the structure of a cross-regional hotel resource scheduling and management device for large-scale events provided in an embodiment of the present invention.

[0026] Attached labels: 1. Activity information collection module, 2. Popularity monitoring module, 3. Crowd forecasting module, 4. Hotel range adjustment module, 5. Dispatch coefficient calculation module, 6. Cross-regional dispatching module, 7. Price control module. Detailed Implementation

[0027] To enhance understanding of the present invention, the invention will be further described in detail below with reference to embodiments and accompanying drawings. These embodiments are only for explaining the invention and do not constitute a limitation on the scope of protection of the invention.

[0028] like Figure 1 , 2 As shown in Figures 3 and 4;

[0029] This invention provides a method for cross-regional hotel resource scheduling and management for large-scale events. This method can be applied to servers, cloud platforms, or electronic devices with data processing capabilities to dynamically schedule and manage hotel resources around the event venue and across regions before and during the event.

[0030] like Figure 1 As shown, the method of this embodiment of the invention includes the following steps S101 to S106.

[0031] S101, Activity Information Collection and Monitoring.

[0032] In this step, the system first determines the target urban area, which can be a prefecture-level city, a municipality, or a specific metropolitan area. The system collects information from large-scale event exhibition halls within a preset geographical radius of the target urban area through at least one of the following: official information release platforms, exhibition hall websites, and government information disclosure channels. The preset geographical radius can be set according to city size and management needs, such as a 50-kilometer radius centered on the city center.

[0033] The system performs structured parsing on the collected announcement information, extracting key fields such as event name, venue location, event date, event duration, and reported scale. When the system detects that the announcement information contains a confirmed event status indicator (such as "confirmed" or "tickets available"), it stores the event date and reported scale in the event information database and creates an independent event file for subsequent popularity monitoring, visitor flow prediction, and resource scheduling.

[0034] In a specific application scenario, the system detected that a city's international expo center had issued a notice for an "International Auto Show," specifying that the event would be held from the 15th to the 20th of a certain month, with a registered scale of 500 exhibitors and an estimated 100,000 visitors. After parsing the above information, the system marked the event as confirmed and created an event file recording the event dates and registered scale.

[0035] S102, Dynamic monitoring of online popularity and ticket purchase intentions.

[0036] In this step, the preset time period is set to one month before the start of the event, and the specific duration can be adjusted according to the type of event and management needs. During this preset time period, the system continuously collects mentions, search volume, and discussion volume related to the large-scale event from social media platforms, search engines, and news portals through web crawlers or public data interfaces.

[0037] The system performs weighted calculations and normalization on the above data according to preset weights to obtain the online popularity index. The specific calculation formula is: Online Popularity Index = (Mentions × 0.3 + Searches × 0.5 + Discussions × 0.2) / Historical Maximum Value × 100. The historical maximum value is the maximum value of relevant data from similar activities in the same period over the past three years, used for normalization. The online popularity index ranges from 0 to 100; a higher value indicates higher online attention to the activity.

[0038] Meanwhile, the system collects the number of "want to go" or "favorite" entries for the large-scale event in real time through the public data interface of the ticketing platform. Different ticketing platforms may use different intention indicators, such as "want to see," "want to go," "favorite," and "add to favorites," and the system can adapt the corresponding fields according to the platform characteristics. The system records the change curve of the number of intentions at preset time intervals (such as hourly) to reflect the public's attention trend and changes in ticket purchase intentions for the event.

[0039] The system links and stores the curves showing changes in the network popularity index and the number of intentions, using them as input data for the subsequent pedestrian flow prediction module.

[0040] S103, advance estimation of passenger flow.

[0041] like Figure 2 As shown, this step specifically includes the following sub-steps:

[0042] S1031, Construct a pedestrian flow prediction model.

[0043] In this step, the system uses the reported scale of large-scale events as the basic parameter and the online popularity index and the number of intentions as correction parameters, and constructs a pedestrian flow prediction model using a multiple linear regression model. The model expression is: Predicted pedestrian flow = α × reported scale + β × online popularity index + γ × number of intentions + δ.

[0044] Wherein, α is the base coefficient, with a value of 0.85, representing the basic contribution of the reported scale to the estimated passenger flow; β is the popularity correction coefficient, with a value of 0.12, representing the correction amount for the estimated passenger flow for each unit increase in network popularity; γ is the intention correction coefficient, with a value of 0.03, representing the correction amount for the estimated passenger flow for each unit increase in the number of ticket purchase intentions; and δ is a constant term, with a value of 0. These coefficients are suggested values ​​obtained based on training with historical activity data, and can be further optimized based on more historical data in practical applications.

[0045] S1032 outputs the estimated number of people.

[0046] In this step, the system inputs the real-time updated reported scale, online popularity index, and number of intentions into the crowd flow prediction model. The model outputs the estimated daily crowd flow during the event, as well as the peak crowd flow during the event. Peak crowd flow typically occurs on weekends or specific themed days of the event, and the system can provide more detailed predictions based on the event schedule.

[0047] S1033 is mapped to the number of accommodation needs.

[0048] In this step, the system estimates the proportion of visitors requiring accommodation based on the location information of the event venue and the estimated visitor flow, mapping the estimated visitor flow to the accommodation demand. The specific calculation formula is: Accommodation demand = Estimated visitor flow × Visitor accommodation ratio coefficient × Average number of room nights per person.

[0049] The accommodation ratio coefficient for visitors is determined based on the type of activity, ranging from 0.3 to 0.7: 0.6 to 0.7 for large-scale national or international exhibitions; 0.4 to 0.5 for regional exhibitions or large concerts; and 0.3 to 0.4 for sporting events primarily attended by local audiences. The average number of room nights per person is determined based on the duration of the activity: 0.8 for an activity lasting one day; 1.5 for an activity lasting two to three days; and 2.5 for an activity lasting four days or more.

[0050] S104, The scope of hotel regulation is dynamically determined.

[0051] like Figure 2 As shown, this step specifically includes the following sub-steps:

[0052] S1041, Calculate the exhibition hall's transportation carrying capacity index.

[0053] In this step, the system obtains the temporary transportation capacity parameters of the event venue, including the venue's size, number of parking lots, number of parking spaces, number of temporary parking pick-up and drop-off points, number of public transportation options, and walking distance after disembarking from public transportation. These parameters reflect the temporary transportation capacity that the event venue can handle during the event, i.e., the transportation connection capacity for visitors arriving at and leaving the venue.

[0054] The system standardizes each parameter: the size of the event venue, the number of parking lots, the number of parking spaces, the number of temporary parking pick-up and drop-off points, and the number of public transportation stops are all positively standardized (the larger the parameter value, the higher the standardized value). The walking distance after getting off public transportation is negatively standardized (the shorter the distance, the higher the standardized value). After standardization, each parameter ranges from 0 to 1.

[0055] After standardization, the system calculates the exhibition hall's transportation capacity index using preset weights. The weights are defined as follows: ws = exhibition hall size weight, wp = number of parking lots weight, wsp = number of parking spaces weight, wd = number of passenger pick-up / drop-off points weight, wt = number of public transportation points weight, and ww = walking distance weight. The calculation formula is: Exhibition Hall Transportation Capacity Index = ws × standardized exhibition hall size value + wp × standardized parking lot quantity value + wsp × standardized parking space quantity value + wd × standardized passenger pick-up / drop-off points weight + wt × standardized public transportation quantity value + ww × reverse standardized walking distance value.

[0056] Among them, ws is 0.20, wp is 0.10, wsp is 0.20, wd is 0.15, wt is 0.20, and ww is 0.15. The exhibition hall transportation capacity index ranges from 0 to 1, with higher values ​​indicating stronger temporary transportation capacity of the exhibition hall.

[0057] S1042, determine the hotel's control radius.

[0058] In this step, the system pre-sets a carrying capacity-distance mapping relationship, which reflects the inverse relationship between the exhibition hall's transportation carrying capacity and the hotel's control radius: the stronger the exhibition hall's transportation carrying capacity, the more convenient the visitors can travel from farther away to the exhibition hall, so the hotel's control radius can be relatively small; conversely, the weaker the exhibition hall's transportation carrying capacity, the stronger the visitors' reliance on the proximity of their accommodation, and the hotel's control radius needs to be expanded accordingly.

[0059] The specific grading rules are as follows: when the exhibition hall transportation capacity index is ≥0.75, the hotel control radius is 3 kilometers; when 0.50≤exhibition hall transportation capacity index<0.75, the hotel control radius is 5 kilometers; when 0.30≤exhibition hall transportation capacity index<0.50, the hotel control radius is 8 kilometers; and when the exhibition hall transportation capacity index<0.30, the hotel control radius is 12 kilometers.

[0060] S1043, delineate the hotel regulation area.

[0061] In this step, the system uses the geographical coordinates of the event venue as the center and a defined hotel control radius as the range to delineate a circular or polygonal hotel control area on the map, and includes all hotels within this area in the control scope of this event. Hotels included in the control scope will participate in subsequent dynamic price adjustments and resource allocation.

[0062] S105, Dynamic range adjustment of hotel prices.

[0063] In this step, the system first obtains resource information such as the number of rooms, current occupancy rate, and benchmark price for each hotel within the hotel's control area. Then, it calculates the ratio of the predicted accommodation demand to the total number of rooms within the hotel's control area, i.e., the supply-demand ratio. Supply-demand ratio = Predicted accommodation demand / Total number of rooms within the control area.

[0064] Based on the supply-demand ratio, the system categorizes the degree of supply and demand tension into five levels and sets a corresponding price fluctuation range for each level:

[0065] (1) When the supply-demand ratio is <0.60, the supply and demand tension level is loose, and the price fluctuation range is -5% to +5% of the benchmark price, allowing hotels to flexibly adjust prices within a small range;

[0066] (2) When 0.60≤supply-demand ratio<0.80, the supply and demand tension level is normal, and the price fluctuation range is 0% to +10% of the benchmark price. Moderate upward adjustment is allowed, but it shall not be lower than the benchmark price.

[0067] (3) When 0.80≤supply-demand ratio<1.00, the supply and demand tension level is tight, and the price fluctuation range is +5% to +20% of the benchmark price. The lower limit of the price is raised to reflect the tight supply and demand.

[0068] (4) When 1.00≤supply-demand ratio<1.20, the supply and demand tension level is tight, and the price fluctuation range is +10% to +30% of the benchmark price. At the same time, a price ceiling is set to prevent price surges.

[0069] (5) When the supply-demand ratio is ≥1.20, the supply-demand tension level is extremely tight, the price fluctuation range is +15% to +40% of the benchmark price, and the price ceiling is set at 1.4 times the benchmark price to suppress abnormal price increases.

[0070] The aforementioned price fluctuation range includes both an upper and lower price limit, which allows hotels to adjust prices reasonably based on market supply and demand while preventing abnormal price fluctuations and malicious low-price competition.

[0071] S106, Cross-regional hotel resource scheduling.

[0072] like Figure 3 As shown, this step specifically includes the following sub-steps:

[0073] S1061, Quantitatively score the candidate hotels.

[0074] In this step, candidate hotels include those within the controlled area surrounding the event venue, as well as those located further away across regions. The system quantitatively scores each candidate hotel based on three dimensions: accessibility, road conditions, and carrying capacity.

[0075] (1) Transportation Convenience Score: The score is based on the number of public transportation options around the hotel. The calculation formula is: Transportation Convenience Score = min(Number of subway stations × 30, 40) + min(Number of bus stops × 5, 30) + min(Number of taxi pick-up points × 15, 20) + min(Number of shared bicycle parking spots × 2, 10). Among them, the number of subway stations has the highest weight, with 30 points per station and a maximum of 40 points; each bus stop is worth 5 points, with a maximum of 30 points; each taxi pick-up point is worth 15 points, with a maximum of 20 points; and each shared bicycle parking spot is worth 2 points, with a maximum of 10 points. The maximum score for transportation convenience is 100 points.

[0076] (2) Road traffic score: The score is calculated based on the road traffic conditions around the hotel, and is obtained by weighting three sub-items: distance to elevated expressway, number of lanes, and bus lane restriction score.

[0077] The elevated expressway distance score is determined based on the distance between the hotel and the nearest elevated expressway entrance: 100 when the distance is ≤1 km, 80 when the distance is 1 km < ≤3 km, 60 when the distance is 3 km < ≤5 km, and 40 when the distance is >5 km.

[0078] The lane number score is determined based on the number of one-way lanes on the main roads around the hotel: 100 when there are ≥4 lanes, 80 when there are 3 lanes, 60 when there are 2 lanes, and 40 when there is 1 lane.

[0079] The bus lane restriction score is determined based on the total daily restricted time of the bus lanes around the hotel: 100 for restricted time ≤ 2 hours, 80 for 2 hours < restricted time ≤ 4 hours, 60 for 4 hours < restricted time ≤ 6 hours, and 40 for restricted time > 6 hours.

[0080] Road traffic score = 0.40 × distance score from elevated expressway + 0.35 × number of lanes score + 0.25 × bus lane restriction score.

[0081] (3) Carrying Capacity Score: The score is based on the hotel's actual carrying capacity. The calculation formula is: Carrying Capacity Score = (Total number of hotel rooms / Maximum total number of rooms in candidate hotels) × 60 + (Maximum number of guests / Maximum number of guests in candidate hotels) × 25 + min(Food and Beverage Capacity Score, 15). The Food and Beverage Capacity Score is determined based on the number of seats in the hotel restaurant: 15 for ≥200 seats, 10 for 100-199 seats, and 5 for <100 seats. The maximum score for the carrying capacity score is 100 points.

[0082] S1062, calculate the scheduling coefficient.

[0083] In this step, the system performs a weighted calculation of the traffic convenience score, road accessibility score, and carrying capacity score to obtain the comprehensive scheduling coefficient for each candidate hotel. The calculation formula is: Scheduling coefficient = 0.40 × Traffic convenience score + 0.35 × Road accessibility score + 0.25 × Carrying capacity score.

[0084] The weighting for transportation convenience is 0.40, as it directly affects how easily users can reach the event venue from the hotel; road accessibility is 0.35, reflecting the convenience for users traveling by car; and carrying capacity is 0.25, reflecting the hotel's ability to accommodate large-scale occupancy. The scheduling coefficient ranges from 0 to 100, with higher values ​​indicating better overall conditions and making the hotel more suitable for cross-regional scheduling.

[0085] S1063, allocate accommodation needs according to scheduling coefficient.

[0086] In this step, the system sorts all candidate hotels in descending order based on their scheduling coefficients. When allocating accommodation needs, users are prioritized to be recommended or guided to hotels with higher scheduling coefficients. For hotels near the event venue, they are given priority due to their proximity advantage, provided their scheduling coefficients are similar. For hotels located in distant areas, when nearby hotel resources are scarce, hotels with higher scheduling coefficients (i.e., convenient transportation, good road access, and strong carrying capacity) are recommended as alternatives.

[0087] S1064 triggers cross-regional scheduling.

[0088] In this step, the system monitors the occupancy rates of hotels around the event venue in real time. When the overall occupancy rate of surrounding hotels reaches a preset warning threshold of 85%, the system triggers a cross-regional dispatch mechanism to redirect accommodation demand exceeding the capacity of surrounding hotels to more distant hotels in other regions, according to the following priority:

[0089] First priority: Hotels with a scheduling coefficient of ≥70 and a distance of ≤15 kilometers from the event venue. These hotels have excellent overall conditions and are at a suitable distance, making them the first choice for cross-regional scheduling.

[0090] Second priority: Hotels with a scheduling coefficient of ≥60 and a distance of ≤20 kilometers from the event venue. These hotels have good overall conditions and are the second choice.

[0091] Third priority: Hotels with a scheduling coefficient of ≥50 and a distance of ≤30 kilometers from the event venue. These hotels will be used as a supplementary option when surrounding and nearby hotel resources are exhausted.

[0092] In one embodiment of the present invention, the method further includes a closed-loop optimization step S107:

[0093] S107. During large-scale events, the system collects real-time data on actual visitor flow (such as the number of people entering exhibition halls and ticket checking data) and hotel occupancy (such as actual occupancy rate and number of guests), and compares the actual data with the previous estimates. The comparison deviation is calculated using the formula: Comparison Deviation = |Actual Visitor Flow - Estimated Visitor Flow| / Estimated Visitor Flow × 100%.

[0094] When the comparison deviation exceeds the preset deviation threshold of 20%, it indicates that the parameters of the prediction model need to be corrected. The system automatically updates the coefficient parameters (α, β, γ) of the passenger flow prediction model and dynamically adjusts the hotel control range, price fluctuation range and cross-regional scheduling strategy based on the updated prediction results, forming a closed-loop mechanism for continuous optimization.

[0095] The above is a detailed description of the method embodiments of the present invention. The apparatus embodiments of the present invention will now be described.

[0096] like Figure 4 As shown, this embodiment of the invention provides a cross-regional hotel resource scheduling and management device for large-scale events. The device includes: an event information collection module 1, a heat monitoring module 2, a crowd flow estimation module 3, a hotel range adjustment module 4, a price control module 7, a scheduling coefficient calculation module 5, and a cross-regional scheduling module 6.

[0097] The activity information collection module 1 is used to collect the announcement information of large-scale event venues within the target urban area, monitor and record the activity dates and reported scale of the large-scale events to be carried out, and execute step S101 in the method embodiment.

[0098] The popularity monitoring module 2 is used to monitor the online popularity of the large-scale event during a preset period before the start of the event, and to dynamically record the number of intentions disclosed on the ticketing platform in real time, corresponding to step S102 in the method embodiment.

[0099] The crowd flow prediction module 3 is used to predict the crowd flow of large-scale events in advance based on the reported scale and online popularity of large-scale events recorded in real time, and obtain the crowd flow prediction result, which corresponds to step S103 in the method embodiment.

[0100] Hotel range adjustment module 4 is used to calculate the exhibition hall's transportation capacity index and dynamically determine the hotel control range around the exhibition hall based on the temporary transportation capacity parameters of the event hall, corresponding to step S104 in the method embodiment.

[0101] Price control module 7 is used to dynamically adjust hotel prices based on the estimated flow of people and hotel resource information within the hotel control range, according to the supply-demand ratio classification, corresponding to step S105 in the method embodiment.

[0102] The scheduling coefficient calculation module 5 is used to calculate the scheduling coefficient of each candidate hotel based on the number of public transportation around the hotel, the road conditions for vehicles, and the actual carrying capacity of the hotel, according to a preset weight. This corresponds to the scoring and coefficient calculation part of step S106 in the implementation method embodiment.

[0103] The cross-regional scheduling module 6 is used to sort candidate hotels according to the scheduling coefficient, and when the occupancy rate of surrounding hotels reaches the warning threshold, the excess demand is scheduled to cross-regional long-distance hotels, which corresponds to the demand allocation and cross-regional scheduling part of step S106 in the execution method embodiment.

[0104] The specific functions and implementation methods of each module in the above-mentioned device have been described in detail in the method embodiments, and will not be repeated here.

[0105] This invention also provides a computer-readable storage medium storing at least one piece of program code, which is loaded and executed by a processor to implement the cross-regional hotel resource scheduling and management method for large-scale events as described in any of the above method embodiments.

[0106] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by hardware related to program instructions. The program can be stored in a computer-readable storage medium, and when the program is executed, it includes the steps of the above method embodiments.

[0107] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for cross-regional hotel resource scheduling and management for large-scale events, characterized in that: The method Includes the following steps: S1, Activity Information Collection and Monitoring: Collect information on large-scale activities held within a preset geographical radius of the target city area through at least one of the official information release platforms, the official website of the exhibition hall, and government information disclosure channels. Perform structured parsing on the information to extract the fields of activity name, activity hall location, activity date, activity duration, and reported scale. When the information contains a status identifier of an activity that has been confirmed to be carried out, store the activity date and reported scale in the activity information database and establish an activity file. S2, Dynamic monitoring of online popularity and ticket purchase intention: During a preset period before the start of a large-scale event, the number of mentions, searches, and discussions related to the event are collected from social media platforms, search engines, and news portals through web crawlers or public data interfaces. The online popularity index is obtained by weighting and normalizing the data according to preset weights. At the same time, the number of "want to go" or "favorite" entries for the event is collected in real time through the public data interface of the ticketing platform, and the change curve of the number of intentions is recorded at preset time intervals. S3, Advance prediction of visitor flow: Based on the reported scale of the large-scale event as the basic parameter, and the network popularity index and the number of intentions as correction parameters, a visitor flow prediction model is constructed. The reported scale, network popularity index and the number of intentions recorded in real time are input into the visitor flow prediction model, and the estimated number of visitors and the peak number of visitors for the large-scale event are output. The estimated number of visitors is mapped to the number of accommodation needs based on the location information of the event venue to obtain the accommodation demand prediction result. S4, Dynamic Determination of Hotel Control Scope: Obtain the temporary transportation capacity parameters of the event venue, including the venue size, number of parking lots, number of parking spaces, number of temporary parking pick-up and drop-off points, number of public transportation routes, and walking distance after disembarking from public transportation. After standardizing each parameter, a weighted calculation is performed to obtain the venue's transportation capacity index. Based on the venue's transportation capacity index and a preset capacity-distance mapping relationship, the hotel control radius around the event venue is determined. The hotel control area is delineated with the event venue location as the center and the hotel control radius as the range. Hotels within the hotel control area are included in the control scope. S5, Hotel Price Dynamic Range Adjustment: Obtain the number of rooms, current occupancy rate and benchmark price of each hotel within the hotel control range, calculate the supply-demand ratio of the predicted accommodation demand to the total number of rooms within the hotel control range, determine the supply-demand tension level based on the supply-demand ratio, and set a dynamic floating range including a price upper limit and a price lower limit for the hotels within the hotel control range based on the supply-demand tension level. S6, Cross-regional hotel resource scheduling: The number of public transportation options, road conditions, and actual carrying capacity of candidate hotels are quantitatively scored to obtain the transportation convenience score, road accessibility score, and carrying capacity score of each candidate hotel. The three scores are weighted according to preset weights to obtain the scheduling coefficient of each candidate hotel. The candidate hotels are ranked according to the scheduling coefficient and the accommodation demand is prioritized to the hotels with higher scheduling coefficients. When the occupancy rate of hotels around the event venue reaches a preset warning threshold, the accommodation demand exceeding the carrying capacity of the surrounding area is scheduled to hotels in distant areas across regions. The method further includes a closed-loop optimization step: during the large-scale event, real-time data on actual pedestrian flow and hotel occupancy are collected, and the actual pedestrian flow data is compared with the pedestrian flow prediction results; when the comparison deviation exceeds a preset deviation threshold of 20%, the coefficient parameters of the pedestrian flow prediction model are updated, and the hotel control range, price fluctuation range, and cross-regional scheduling strategy are dynamically adjusted; the comparison deviation = |actual pedestrian flow - predicted pedestrian flow| / predicted pedestrian flow × 100%.

2. The method according to claim 1, characterized in that, The pedestrian flow prediction model constructed in S3 includes: using a multiple linear regression model, the expression of which is: Predicted pedestrian flow = α × Reported scale + β × Network popularity index + γ × Number of intentions + δ; where α is the basic coefficient with a value of 0.85; β is the popularity correction coefficient with a value of 0.12; γ is the intention correction coefficient with a value of 0.03; and δ is a constant term with a value of 0. The network popularity index is calculated using the following formula: Network popularity index = (Mentions × 0.3 + Searches × 0.5 + Discussions × 0.2) / Historical maximum value for the same period × 100; the value range of the network popularity index is 0 to 100.

3. The method according to claim 1, characterized in that, The mapping of the estimated number of people to the accommodation demand in S3 includes: determining the accommodation ratio coefficient for outsiders based on the activity type, wherein the accommodation ratio coefficient for outsiders ranges from 0.3 to 0.7; accommodation demand = estimated number of people × accommodation ratio coefficient for outsiders × average number of room nights per person; wherein the average number of room nights per person is determined based on the duration of the activity, wherein the average number of room nights per person is 0.8 when the activity lasts for 1 day, 1.5 when the activity lasts for 2 to 3 days, and 2.5 when the activity lasts for more than 4 days.

4. The method according to claim 1, characterized in that, The S4 step involves standardizing and weighting the parameters to obtain the exhibition hall transportation capacity index. This includes: forward standardization of the exhibition hall size, number of parking lots, number of parking spaces, number of temporary parking pick-up / drop-off points, and number of public transportation stops; and reverse standardization of the walking distance after disembarking from public transportation. Each standardized parameter ranges from 0 to 1. The weights are defined as follows: w_s = exhibition hall size weight, w_p = number of parking lots weight, w_sp = number of parking spaces weight, w_d = number of pick-up / drop-off points weight, w_t = number of public transportation stops weight, and w_w = walking distance. The exhibition hall transportation capacity index is calculated using the following weighting: w_s × exhibition hall size (standardized value) + w_p × number of parking lots (standardized value) + w_sp × number of parking spaces (standardized value) + w_d × number of pick-up and drop-off points (standardized value) + w_t × number of public transportation points (standardized value) + w_w × walking distance (reverse standardized value); where w_s is 0.20, w_p is 0.10, w_sp is 0.20, w_d is 0.15, w_t is 0.20, and w_w is 0.15; the value range of the exhibition hall transportation capacity index is 0 to 1.

5. The method according to claim 1, characterized in that, The determination of the hotel control radius in S4 based on the exhibition hall transportation capacity index and the preset capacity-distance mapping relationship includes: when the exhibition hall transportation capacity index is ≥0.75, the hotel control radius is 3 kilometers; when 0.50≤the exhibition hall transportation capacity index<0.75, the hotel control radius is 5 kilometers; when 0.30≤the exhibition hall transportation capacity index<0.50, the hotel control radius is 8 kilometers; and when the exhibition hall transportation capacity index<0.30, the hotel control radius is 12 kilometers.

6. The method according to claim 1, characterized in that, The step S5, which determines the supply-demand tension level and sets a dynamic fluctuation range based on the supply-demand ratio, includes the following: when the supply-demand ratio is <0.60, the supply-demand tension level is loose, and the price fluctuation range is -5% to +5% of the benchmark price; when 0.60 ≤ the supply-demand ratio <0.80, the supply-demand tension level is normal, and the price fluctuation range is 0% to +10% of the benchmark price; when 0.80 ≤ the supply-demand ratio <1.00, the supply-demand tension level is slightly tight, and the price fluctuation range is +5% to +20% of the benchmark price; when 1.00 ≤ the supply-demand ratio <1.20, the supply-demand tension level is tight, and the price fluctuation range is +10% to +30% of the benchmark price; when the supply-demand ratio is ≥1.20, the supply-demand tension level is extremely tight, and the price fluctuation range is +15% to +40% of the benchmark price.

7. The method according to claim 1, characterized in that, In step S6, the scheduling coefficient is calculated by weighting the three scores according to preset weights. The weighted coefficient is: scheduling coefficient = 0.40 × traffic convenience score + 0.35 × road accessibility score + 0.25 × carrying capacity score. The traffic convenience score, road accessibility score, and carrying capacity score all range from 0 to 100. The scheduling coefficient also ranges from 0 to 100. The preset warning threshold in step S6 is that the overall occupancy rate of hotels around the event venue reaches 85%. When cross-regional scheduling is triggered, hotels at longer distances are selected according to the following priorities: First priority: hotels with a scheduling coefficient ≥ 70 and a distance ≤ 15 km from the event venue; Second priority: hotels with a scheduling coefficient ≥ 60 and a distance ≤ 20 km from the event venue; Third priority: hotels with a scheduling coefficient ≥ 50 and a distance ≤ 30 km from the event venue.

8. The method according to claim 7, characterized in that, The transportation convenience score is calculated as follows: Transportation Convenience Score = min(Number of subway stations × 30, 40) + min(Number of bus stops × 5, 30) + min(Number of taxi pick-up points × 15, 20) + min(Number of shared bicycle parking spots × 2, 10); The carrying capacity score is calculated as follows: Carrying Capacity Score = (Total number of hotel rooms / Maximum total number of rooms in candidate hotels) × 60 + (Maximum number of guests that can be accommodated / Maximum number of guests that can be accommodated in candidate hotels) × 25 + min(Restaurant reception capacity score, 15); The restaurant reception capacity score is determined based on the number of seats in the hotel restaurant. When the number of seats is ≥200, the score is 15; when the number of seats is 100 to 199, the score is 10; and when the number of seats is <100, the score is 5.

9. The method according to claim 7, characterized in that, The road traffic score is calculated as follows: Road Traffic Score = 0.40 × Elevated Expressway Distance Score + 0.35 × Lane Quantity Score + 0.25 × Bus Lane Restriction Score; The elevated expressway distance score is determined based on the distance between the hotel and the nearest elevated expressway entrance: 100 for distance ≤ 1 km, 80 for 1 km < ≤ 3 km, 60 for 3 km < ≤ 5 km, and 40 for distance > 5 km; The lane quantity score... The score is determined based on the number of one-way lanes on the main roads surrounding the hotel: 100 for ≥4 lanes, 80 for 3 lanes, 60 for 2 lanes, and 40 for 1 lane. The score for bus lane restrictions is determined based on the total daily restricted time of bus lanes surrounding the hotel: 100 for restricted time ≤2 hours, 80 for 2 hours < restricted time ≤4 hours, 60 for 4 hours < restricted time ≤6 hours, and 40 for restricted time >6 hours.

10. A cross-regional hotel resource scheduling and management device for large-scale events, characterized in that: The device includes: an activity information collection module for collecting and monitoring activity information in step S1 of claim 1; a popularity monitoring module for dynamically monitoring network popularity and ticket purchase intentions in step S2 of claim 1; a passenger flow prediction module for predicting passenger flow in advance in step S3 of claim 1; a hotel range adjustment module for dynamically determining the hotel control range in step S4 of claim 1; a price control module for dynamically adjusting the hotel price range in step S5 of claim 1; a scheduling coefficient calculation module for calculating the scheduling coefficient in step S6 of claim 1; and a cross-regional scheduling module for scheduling cross-regional hotel resources in step S6 of claim 1.

Images