A method, apparatus, electronic device, and storage medium for hotel booking

Abstract

This application provides a method, apparatus, electronic device, and storage medium for hotel booking. The method includes: booking a first hotel based on first scenario data before a trip; booking a second hotel based on temporary accommodation request text, emotional data, and the second scenario data during the trip; and adjusting the booking to a third hotel after check-in. This application considers the changing needs of tourists during their trip, providing a more flexible booking method. By incorporating scenario data and emotional data during booking, it more accurately matches hotels to tourists, thus enhancing their travel experience.

Description

Technical Field

[0001] This application relates to the field of hotel reservation technology, and more specifically, to a method, apparatus, electronic device, and storage medium for hotel reservation. Background Technology

[0002] With the gradual improvement of living standards, tourism has become an important part of daily leisure activities. To ensure a better travel experience, itinerary planning is generally necessary before departure. This planning typically includes selecting travel routes and hotels.

[0003] In current technology, hotel reservations are typically made based on the planned visit time and travel time to each attraction on the tourist itinerary. After booking, guests generally stay at the reserved hotel, which lacks flexibility and limits the travel experience. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method, apparatus, electronic device and storage medium for hotel booking to overcome the problems in the prior art.

[0005] In a first aspect, embodiments of this application provide a method for hotel booking, the method comprising:

[0006] Before tourists travel according to the preset tour route, based on the tourists' personal characteristics, multiple first attractions where they need to stay after the tour are identified in the preset tour route, and first scene data of the first attraction's check-in time period is predicted based on the first historical scene data of the first attraction.

[0007] Based on the tourist's initial accommodation requirements text before the visit and the first scene data, a first booked hotel is matched for the first attraction in the first overall hotel list; wherein, the first overall hotel list consists of all hotels obtained from different platforms within a first preset range of the location of the first attraction;

[0008] When a tourist is visiting various attractions along a pre-set tour route and a text requesting temporary accommodation is received, the tourist's current emotional data and second-scene data showing how the tourist's current location affects the accommodation are obtained.

[0009] Based on the temporary accommodation request text, the emotional data, and the second scenario data, a second booked hotel is matched for the current attraction from the second overall hotel list; wherein, the second overall hotel list is obtained from all hotels on different platforms within a second preset range for the current attraction;

[0010] After the tourist checks into the second booked hotel, the first attraction following the current attraction in the preset tour route is adjusted according to the tourist's personal characteristics to obtain the adjusted second attraction;

[0011] Based on the target accommodation demand text and the second scenario data, a third booking hotel is matched for the second attraction in the second overall hotel; the second overall hotel is all hotels obtained from different platforms within a third preset range of the location of the second attraction.

[0012] In some technical solutions of this application, the aforementioned first historical scene data includes first sub-data with a first change frequency and second sub-data with a second change frequency; wherein, the first change frequency is greater than the second change frequency;

[0013] The method of predicting the first scene data for the check-in period of the first scenic spot based on the first historical scene data of the first scenic spot includes:

[0014] The first sub-data is predicted using a first-quantity prediction method to obtain a first prediction result;

[0015] The second sub-data is predicted using a prediction method based on the second quantity to obtain a second prediction result; wherein the first quantity is greater than the second quantity;

[0016] The first prediction result and the second prediction result are fused to obtain the first scene data.

[0017] In some technical solutions of this application, the above method matches the first preset range in the following ways:

[0018] The first initial range is determined based on the historical distance between historical sites and historical hotels during the tourists' historical tourism process;

[0019] Based on the first scene data, the first initial range is adjusted to obtain the adjusted first preset range.

[0020] In some technical solutions of this application, the above-mentioned adjustment of the first initial range based on the first scene data to obtain the adjusted first preset range includes:

[0021] Based on the distance from the location of the first scenic spot, the first initial range is divided into multiple first sub-regions;

[0022] The first scene data is subjected to feature encoding processing to obtain the first scene feature vector corresponding to the first scene data;

[0023] Based on the feature vector of the first scene, calculate the risk score of each of the first sub-regions;

[0024] Based on the risk score of each of the first sub-regions, the first initial range is adjusted to obtain the adjusted first preset range.

[0025] In some technical solutions of this application, the above method determines the second preset range in the following ways:

[0026] The second initial range is determined based on the historical distances between historical sites and historical hotels during the tourists' historical travels.

[0027] The tourist's current mobility is assessed to determine their degree of mobility restriction.

[0028] The second initial range is adjusted according to the movement restriction to obtain the adjusted second preset range.

[0029] In some technical solutions of this application, the above-mentioned matching of a second booked hotel for the current attraction from the second overall hotel list based on the temporary accommodation request text, the sentiment data, and the second scene data includes:

[0030] The temporary accommodation request text, the sentiment data, and the second scene data are mapped onto a three-dimensional decision space, serving as the decision axes of the three-dimensional decision space;

[0031] Based on the temporary accommodation demand text, the sentiment data, and the second scenario data, determine the decision parameters corresponding to each decision axis;

[0032] Based on the temporary accommodation request text, the sentiment data, the second scenario data, and the corresponding decision parameters, a second booked hotel is matched for the current attraction from the second overall hotel list.

[0033] In some technical solutions of this application, the above method determines the target accommodation requirement text in the following manner:

[0034] Determine whether the tourist has submitted a new accommodation request text; if the new accommodation request text exists, merge the new accommodation request text and the initial accommodation request text to obtain the target accommodation request text;

[0035] If the new accommodation requirement text does not exist, the initial accommodation requirement text will be used as the target accommodation requirement text.

[0036] Secondly, embodiments of this application provide a hotel booking device, the device comprising:

[0037] The prediction module is used to determine, based on the tourist's personal characteristics, multiple first attractions in the preset tourist route where the tourist needs to stay after the tour, before the tourist starts to travel according to the preset tourist route, and to predict the first scene data of the first attraction's check-in time based on the first historical scene data of the first attraction.

[0038] The first matching module is used to match a first booked hotel for the first attraction in the first overall hotel list based on the tourist's initial accommodation request text before the visit and the first scene data; wherein, the first overall hotel list consists of all hotels obtained from different platforms within a first preset range of the location of the first attraction;

[0039] The acquisition module is used to acquire the tourist's current emotional data and second scene data of the tourist's current attraction affecting the accommodation when the tourist receives the tourist's temporary accommodation request text during the tourist's visit to various attractions in the preset tourist route.

[0040] The second matching module is used to match a second booked hotel for the current attraction from the second overall hotel list based on the temporary accommodation request text, the emotional data, and the second scene data; wherein the second overall hotel list is obtained from all hotels obtained from different platforms within a second preset range of the current attraction.

[0041] An adjustment module is used to adjust the first attraction after the tourist checks into the second booked hotel, based on the tourist's personal characteristics, to obtain the adjusted second attraction.

[0042] The third matching module, used by the prediction module, is used to match a third booked hotel for the second attraction within the second overall hotel list based on the target accommodation demand text and the second scenario data; the second overall hotel list consists of all hotels obtained from different platforms within a third preset range of the location of the second attraction.

[0043] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described hotel booking method.

[0044] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the hotel booking method described above.

[0045] The technical solutions provided by the embodiments of this application may include the following beneficial effects:

[0046] This application method includes, before a tourist begins their visit according to a preset tour route, identifying multiple first attractions along the preset tour route based on the tourist's personal characteristics, where accommodation is required after the visit, and predicting first scene data for the check-in period of the first attractions based on first historical scene data of the first attractions; matching a first booked hotel for the first attractions from a first overall hotel list based on the tourist's initial accommodation request text before the visit and the first scene data; wherein, the first overall hotel list comprises all hotels obtained from different platforms within a first preset range of the location of the first attractions; and, during the tourist's visit to the various attractions along the preset tour route, when a temporary accommodation request text from the tourist is received, acquiring the tourist's current emotional data and... The second scenario data shows how the tourist's current location affects accommodation. Based on the temporary accommodation request text, the emotional data, and the second scenario data, a second booked hotel is matched for the current location from a second overall hotel list. The second overall hotel list includes all hotels obtained from different platforms within a second preset range of the current location. After the tourist checks into the second booked hotel, the first attraction following the current location in the preset travel route is adjusted based on the tourist's personal characteristics to obtain an adjusted second attraction. Based on the target accommodation request text and the second scenario data, a third booked hotel is matched for the second attraction from the second overall hotel list. The second overall hotel list includes all hotels obtained from different platforms within a third preset range of the second attraction's location.

[0047] This application takes into account the changing needs of tourists during their trip, and develops more flexible booking methods for tourists. It considers scene data and emotional data when booking, and matches hotels more accurately for tourists, thereby improving their travel experience.

[0048] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0049] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 A schematic flowchart of a hotel booking method provided in an embodiment of this application is shown;

[0051] Figure 2 This illustration shows a schematic diagram of a first initial range provided by an embodiment of this application;

[0052] Figure 3 A schematic diagram of a hotel booking device provided in an embodiment of this application is shown;

[0053] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0055] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0056] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0057] With the gradual improvement of living standards, tourism has become an important part of daily leisure activities. To ensure a better travel experience, itinerary planning is generally necessary before departure. This planning typically includes selecting travel routes and hotels.

[0058] In current technology, hotel reservations are typically made based on the planned visit time and travel time to each attraction on the tourist itinerary. After booking, guests generally stay at the reserved hotel, which lacks flexibility and limits the travel experience.

[0059] Based on this, embodiments of this application provide a method, apparatus, electronic device, and storage medium for hotel booking, which are described below through embodiments.

[0060] Figure 1 The diagram illustrates a flowchart of a hotel booking method provided in an embodiment of this application, wherein the method includes steps S101-S106; specifically:

[0061] S101. Before tourists travel according to the preset tour route, based on the tourists' personal characteristics, multiple first attractions in the preset tour route that require accommodation after the tour are determined, and the first scene data of the first attraction's accommodation period is predicted based on the first historical scene data of the first attraction.

[0062] S102. Based on the tourist's initial accommodation requirements text before the visit and the first scene data, match a first booked hotel for the first attraction in the first overall hotel list; wherein, the first overall hotel list consists of all hotels obtained from different platforms within a first preset range of the location of the first attraction;

[0063] S103. When the tourist receives a text requesting temporary accommodation during the tourist's visit to various attractions along the preset tour route, the tourist's current emotional data and second scene data showing the tourist's current location affecting accommodation are obtained.

[0064] S1044. Based on the temporary accommodation request text, the emotional data, and the second scene data, match a second booked hotel for the current attraction from the second overall hotel list; wherein, the second overall hotel list is obtained from all hotels obtained from different platforms within a second preset range of the current attraction;

[0065] S105. After the tourist checks into the second booked hotel, the first attraction after the current attraction in the preset tour route is adjusted according to the tourist's personal characteristics to obtain the adjusted second attraction.

[0066] S106. Based on the target accommodation requirement text and the second scenario data, match a third booked hotel for the second attraction in the second overall hotel; the second overall hotel is all hotels obtained from different platforms within a third preset range of the location of the second attraction.

[0067] This application takes into account the changing needs of tourists during their trip, and develops more flexible booking methods for tourists. It considers scene data and emotional data when booking, and matches hotels more accurately for tourists, thereby improving their travel experience.

[0068] The following describes some embodiments of this application in detail. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0069] This application provides a hotel booking method, which operates on a travel planner's end. The travel planner's end can be a user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, in-vehicle device, wearable device, etc. The method can be implemented by a processor calling computer-readable instructions stored in memory. Alternatively, the method can be executed by a server. The travel planner's end is connected to the tourist's end and also to the hotel service end. The preset travel route in this application embodiment is formulated by the travel planner's end. For example, it obtains the tourist's travel needs and performs semantic analysis on the travel needs to customize the route. It should be noted that the preset travel route in this application embodiment includes multiple target attractions and multiple first attractions. Here, the target attractions are attractions that are only visited, and the first attractions are attractions where a hotel stay is required after visiting them. When determining the first attractions, this application embodiment is based on the tourist's personal characteristics. Specifically, by analyzing the tourist's historical travel history, the relationship between the historical travel time period and the historical accommodation time period is determined. Then, based on the sightseeing time and travel time of each target attraction in the preset route, the first attraction is determined from the target attractions.

[0070] Current technology for booking hotels at the first tourist attraction only considers the tourist's initial needs and the distance to the attraction. For example, if a tourist requests a three-star hotel, current technology typically selects the three-star hotel closest to the attraction in a straight line. This approach, relying solely on straight-line distance, is susceptible to disruptions during actual check-in, such as traffic congestion, unforeseen events, or surges in visitor numbers. These disruptions can impact the hotel booking process, potentially preventing tourists from checking in and affecting their overall travel experience.

[0071] In this embodiment, before tourists follow a preset tour route, when determining the first booked hotel, the distance between the first booked hotel and the first attraction is considered, along with comprehensive consideration of the first scene data of the first booked hotel. Specifically, when considering the distance between the first booked hotel and the first attraction, the basis is primarily the historical distances between historical attractions and historical hotels during the tourist's past travels. The average historical distance is calculated by statistically analyzing these distances. Furthermore, a aging function based on the tourist's own physical functions is established, and the average value is further adjusted based on this function to obtain an adjusted initial range.

[0072] After obtaining the first initial range, this embodiment of the application also considers first scene data. The first initial range is adjusted based on the first scene data to obtain an adjusted first preset range. The first scene data here includes meteorological data, traffic data, and emergency event data, etc. The first scene data here is predicted based on the first historical scene data of the first scenic spot.

[0073] When predicting the first historical scene data, the impact of the scene data varies because the frequency of change of different data within the scene data differs. Specifically, in this embodiment, the first historical scene data is divided into sub-data of different frequencies: first sub-data with a first frequency of change and second sub-data with a second frequency of change. For example, meteorological data and traffic data are divided into first sub-data, and emergencies are divided into second sub-data. To ensure prediction accuracy, this application uses different numbers of prediction methods for the first historical scene data of different frequencies. For example, a first number of prediction methods is used to predict the first sub-data to obtain a first prediction result; a second number of prediction methods is used to predict the second sub-data to obtain a second prediction result; wherein the first number is greater than the second number; the first prediction result and the second prediction result are fused to obtain the first scene data. For data with a high frequency of change, such as weather and traffic data, this embodiment uses multiple prediction methods to make predictions, and then combines the prediction results of each method to obtain a first prediction result. For data with a low frequency of change, such as sudden events, this embodiment uses fewer prediction methods to make predictions, and then combines the prediction results of each method to obtain a second prediction result. For example, five prediction methods are used to predict the first sub-data, and two prediction methods are used to predict the second sub-data.

[0074] When predicting the second sub-data, due to the low frequency and uncertainty of sudden events, there are cases where the second prediction result is empty. To address this, this application embodiment considers a buffer data, that is, when the second prediction result is less than a preset event data threshold, the buffer data is used as the second prediction result. This buffer data can be determined based on historical second sub-data or based on tourists' travel habits. For example, if the second prediction result is expressed as a travel time to the first booked hotel of 2 minutes, which is less than a preset 5 minutes, then 5 minutes is used as the second prediction result.

[0075] After obtaining the first scene data, this embodiment of the application needs to adjust the first initial range based on the first scene data to obtain a first preset range. When adjusting the first initial range, this embodiment of the application divides the first initial range into multiple first sub-regions, and the division is based on travel time. Here, travel time refers to the fastest travel time to reach the region; for example, if it takes 20 minutes by subway and 15 minutes by car, then the travel time to that region is 15 minutes. Figure 2 As shown, the square represents the first scenic spot, and the initial area is divided into regions A, B, C, and D based on travel time. After division, this embodiment adjusts the initial area by eliminating some of the first sub-regions.

[0076] Specifically, in this embodiment of the application, the first scene data is subjected to feature encoding processing to obtain a first scene feature vector corresponding to the first scene data; based on the first scene feature vector, the risk score of each first sub-region is calculated; and according to the risk score of each first sub-region, the first initial range is adjusted to obtain an adjusted first preset range.

[0077] For example, the first scene feature vector is obtained as follows: weather = [35.6, 22.4, 8.3, 2] # rainfall / temperature / wind speed / warning level; traffic = [8.2, 3, 0.91] # congestion index / number of accidents / road network throughput; events = [0.9, 5000, 1] # event severity / influence radius / type encoding. The feature vector is then generated using an encoder.

[0078] scene_vector=scene_encoder(torch.tensor([weather, traffic, events]))

[0079] Output: tensor([0.92,-0.15,...,0.78],dtype=torch.float32) Backpropagation reveals key dimensions: Calculate the contribution of each input feature to the output:

[0080] saliency=torch.autograd.grad(scene_vector.sum(),encoder.parameters()).

[0081] After obtaining the first scene feature vector, each sub-score is calculated based on the first scene feature vector and the hotel feature vectors in each first sub-region. Then, the sub-scores are integrated to obtain the risk score for the first sub-region. Sub-regions with risk scores lower than a preset risk threshold are then eliminated to obtain the first preset range.

[0082] After determining the first preset range, the first booked hotel is matched with the tourist's initial accommodation request text from the first set of hotels within the first preset range. The first set of hotels here refers to all hotels obtained from different platforms within the first preset range. These different platforms include online and offline platforms. Online platforms can be obtained through API calls or web scraping, while offline platforms can be obtained through direct communication with the travel planner.

[0083] After the initial hotel reservation is determined for the tourist using the above method, the tourist may still need temporary accommodations during their trip according to the preset itinerary. When a tourist needs a temporary accommodation, they can send a text message to the travel planner at any time. In this embodiment, a second hotel reservation needs to be matched for the tourist at this point. When determining the second hotel reservation, since the tourist's request is temporary, to ensure a good travel experience, this embodiment considers not only the second scenario data but also the tourist's emotional data. Both the emotional data and the second scenario data are acquired in real time; the specific acquisition method is not limited here.

[0084] When determining the second booked hotel, this embodiment of the application needs to first determine a second preset range. In determining the second preset range, the initial range is first determined based on the historical distances between historical attractions and historical hotels during the tourist's past travels. It should be noted that this initial range is determined based on the tourist's normal emotional state, considering that the tourist's accommodation request is made temporarily and may be subject to emotional fluctuations. After determining the initial range, this embodiment of the application also needs to adjust it. Specifically, this embodiment first narrows down the initial range based on the tourist's current behavioral capabilities, and then considers the second scenario data to remove a second sub-region from the narrowed initial range to obtain the second preset range. The process of removing the second sub-region is the same as the process of removing the first sub-region, and will not be repeated here.

[0085] After determining the second preset range, this embodiment of the application matches a second reserved hotel for the current attraction from the second overall hotel list based on the temporary accommodation request text, the emotional data, and the second scene data. Specifically, the temporary accommodation request text, the emotional data, and the second scene data are mapped onto a three-dimensional decision space as decision axes; decision parameters corresponding to each decision axis are determined based on the temporary accommodation request text, the emotional data, and the second scene data; and a second reserved hotel is matched for the current attraction from the second overall hotel list based on the temporary accommodation request text, the emotional data, the second scene data, and the corresponding decision parameters.

[0086] For example, the temporary accommodation request text, the sentiment data, and the second scene data features are standardized, then cross-modal aligned, and then coordinates are generated: X = cosine_similarity(temporary accommodation request text, hotel feature vector), matching degree dimension; Y = sigmoid(second scene data vector, hotel scene response vector), scene fit; Z = 1 - normalized_euclidean(sentiment vector, hotel sentiment profile), sentiment fit.

[0087] Construct the scoring functions for the three:

[0088] Score = e -λ(1-X) ×(αY+βZ)

[0089] Exponential decay coefficient λ: λ = 0.3 + 0.1·σ(eurgency)

[0090] σ(·): Sigmoid function

[0091] eurgency∈[0,1]: The urgency value output by sentiment analysis.

[0092] Scene weight α and sentiment weight β:

[0093] β=1-α

[0094] Scene confidence (∈scene represents the LSTM-Autoencoder reconstruction error).

[0095] Emotional stability (Var(Ehist)) is the variance of users' historical emotional state.

[0096] λ∈[0.2,0.5]: Exponential decay coefficient, which increases with the user's urgency; α+β=1: Dynamic weighting of scenario and emotion. For every 0.1 increase in urgency, λ increases by 0.05. When the scenario confidence is >0.7, α=0.6; when the emotion fluctuation is >0.3, β=0.5.

[0097] The second hotel reservation is matched from the second overall hotel group using the method described above. After the second hotel reservation is confirmed, the tourist will decide whether to stay at it. After the tourist checks into the second hotel reservation, due to time constraints, the first attraction after the current attraction in the preset tour route (sorted by time) needs to be adjusted. That is, the second attraction for which accommodation is required after the visit is re-determined, and then a third hotel reservation is matched for the second attraction.

[0098] When determining the third hotel booking, considering that tourists may have booked accommodations in advance, additional accommodation request texts may be generated. Apart from the parts identical to the first booking, it is also considered whether the tourist has submitted additional accommodation request texts. If such additional accommodation request texts exist, they are merged with the initial accommodation request texts to obtain the target accommodation request text. If no additional accommodation request texts exist, the initial accommodation request texts are used as the target accommodation request text.

[0099] Figure 3 This application provides a schematic diagram of the structure of a hotel booking device, which includes:

[0100] The prediction module is used to determine, based on the tourist's personal characteristics, multiple first attractions in the preset tourist route where the tourist needs to stay after the tour, before the tourist starts to travel according to the preset tourist route, and to predict the first scene data of the first attraction's check-in time based on the first historical scene data of the first attraction.

[0101] The first matching module is used to match a first booked hotel for the first attraction in the first overall hotel list based on the tourist's initial accommodation request text before the visit and the first scene data; wherein, the first overall hotel list consists of all hotels obtained from different platforms within a first preset range of the location of the first attraction;

[0102] The acquisition module is used to acquire the tourist's current emotional data and second scene data of the tourist's current attraction affecting the accommodation when the tourist receives the tourist's temporary accommodation request text during the tourist's visit to various attractions in the preset tourist route.

[0103] The second matching module is used to match a second booked hotel for the current attraction from the second overall hotel list based on the temporary accommodation request text, the emotional data, and the second scene data; wherein the second overall hotel list is obtained from all hotels obtained from different platforms within a second preset range of the current attraction.

[0104] An adjustment module is used to adjust the first attraction after the tourist checks into the second booked hotel, based on the tourist's personal characteristics, to obtain the adjusted second attraction.

[0105] The third matching module, used by the prediction module, is used to match a third booked hotel for the second attraction within the second overall hotel list based on the target accommodation demand text and the second scenario data; the second overall hotel list consists of all hotels obtained from different platforms within a third preset range of the location of the second attraction.

[0106] The first historical scene data includes first sub-data with a first frequency of change and second sub-data with a second frequency of change; wherein the first frequency of change is greater than the second frequency of change.

[0107] The method of predicting the first scene data for the check-in period of the first scenic spot based on the first historical scene data of the first scenic spot includes:

[0108] The first sub-data is predicted using a first-quantity prediction method to obtain a first prediction result;

[0109] The second sub-data is predicted using a prediction method based on the second quantity to obtain a second prediction result; wherein the first quantity is greater than the second quantity;

[0110] The first prediction result and the second prediction result are fused to obtain the first scene data.

[0111] The first preset range is matched using the following method:

[0112] The first initial range is determined based on the historical distance between historical sites and historical hotels during the tourists' historical tourism process;

[0113] Based on the first scene data, the first initial range is adjusted to obtain the adjusted first preset range.

[0114] Based on the first scene data, the first initial range is adjusted to obtain an adjusted first preset range, including:

[0115] Based on the travel time between the first scenic spot and the first scenic spot location, the first initial range is divided into multiple first sub-regions;

[0116] The first scene data is subjected to feature encoding processing to obtain the first scene feature vector corresponding to the first scene data;

[0117] Based on the feature vector of the first scene, calculate the risk score of each of the first sub-regions;

[0118] Based on the risk score of each of the first sub-regions, the first initial range is adjusted to obtain the adjusted first preset range.

[0119] The second preset range is determined in the following manner:

[0120] The second initial range is determined based on the historical distances between historical sites and historical hotels during the tourists' historical travels.

[0121] The tourist's current mobility is assessed to determine their degree of mobility restriction.

[0122] The second initial range is adjusted based on the movement restriction and the second scene data to obtain the adjusted second preset range.

[0123] The step of matching a second booked hotel for the current attraction from the second overall hotel list based on the temporary accommodation request text, the sentiment data, and the second scene data includes:

[0124] The temporary accommodation request text, the sentiment data, and the second scene data are mapped onto a three-dimensional decision space, serving as the decision axes of the three-dimensional decision space;

[0125] Based on the temporary accommodation demand text, the sentiment data, and the second scenario data, determine the decision parameters corresponding to each decision axis;

[0126] Based on the temporary accommodation request text, the sentiment data, the second scenario data, and the corresponding decision parameters, a second booked hotel is matched for the current attraction from the second overall hotel list.

[0127] The target accommodation requirement text is determined using the following method:

[0128] Determine whether the tourist has submitted a new accommodation request text; if the new accommodation request text exists, merge the new accommodation request text and the initial accommodation request text to obtain the target accommodation request text;

[0129] If the new accommodation requirement text does not exist, the initial accommodation requirement text will be used as the target accommodation requirement text.

[0130] like Figure 4As shown, this application provides an electronic device for executing the hotel booking method described in this application. The device includes a memory, a processor, a bus, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the hotel booking method described above.

[0131] Specifically, the aforementioned memory and processor can be general-purpose memory and processor, without any specific limitations. When the processor runs the computer program stored in the memory, it can execute the aforementioned hotel booking method.

[0132] Corresponding to the hotel booking method in this application, this application embodiment also provides a computer-readable storage medium storing a computer program, which, when run by a processor, executes the steps of the hotel booking method described above.

[0133] Specifically, the storage medium can be a general-purpose storage medium, such as a removable disk or hard disk, and when the computer program on the storage medium is run, it can execute the above-mentioned hotel booking method.

[0134] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. The system embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interface; the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.

[0135] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0136] In addition, the functional units in the embodiments provided in this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0137] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0138] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0139] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method for booking a hotel, characterized in that, The method includes: Before tourists begin their tour according to the preset tour route, based on the tourists' personal characteristics, multiple first attractions where they need to stay after the tour are identified in the preset tour route. Based on the first historical scene data of the first attractions, the first scene data of the first attractions during the check-in period is predicted. The first scene data includes weather data, traffic data, and emergency event data when visiting the first attractions, and the first historical scene data includes weather data, traffic data, and emergency event data before visiting the first attractions. Based on the tourist's initial accommodation requirements text before the visit and the first scene data, a first booked hotel is matched for the first attraction in the first overall hotel list; wherein, the first overall hotel list consists of all hotels obtained from different platforms within a first preset range of the location of the first attraction; When a tourist is visiting various attractions along a pre-set tour route and a text message requesting temporary accommodation is received, the system acquires the tourist's current emotional data and second-scene data showing how the tourist's current location affects the accommodation. The second-scene data includes weather data, traffic data, and emergency data during the visit to the current attraction. Based on the temporary accommodation request text, the sentiment data, and the second scenario data, a second booked hotel is matched for the current attraction from the second overall hotel list; wherein, the second overall hotel list is obtained from all hotels on different platforms within a second preset range for the current attraction; After the tourist checks into the second booked hotel, the first attraction following the current attraction in the preset tour route is adjusted according to the tourist's personal characteristics to obtain the adjusted second attraction; Based on the target accommodation requirement text and the second scenario data, a third booked hotel is matched for the second attraction in the third overall hotel; the third overall hotel is all hotels obtained from different platforms within a third preset range of the location of the second attraction.

2. The method according to claim 1, characterized in that, The first historical scene data includes first sub-data with a first frequency of change and second sub-data with a second frequency of change; wherein, the first frequency of change is greater than the second frequency of change; the first sub-data includes meteorological data and traffic data, and the second sub-data includes emergency data; The method of predicting the first scene data for the check-in period of the first scenic spot based on the first historical scene data of the first scenic spot includes: The first sub-data is predicted using a first-quantity prediction method to obtain a first prediction result; The second sub-data is predicted using a prediction method based on the second quantity to obtain a second prediction result; wherein the first quantity is greater than the second quantity; The first prediction result and the second prediction result are fused to obtain the first scene data.

3. The method according to claim 1, characterized in that, The method matches the first preset range in the following manner: The first initial range is determined based on the historical distance between historical sites and historical hotels during the tourists' historical tourism process; Based on the first scene data, the first initial range is adjusted to obtain the adjusted first preset range.

4. The method according to claim 3, characterized in that, The step of adjusting the first initial range based on the first scene data to obtain the adjusted first preset range includes: Based on the travel time between the first scenic spot and the first scenic spot location, the first initial range is divided into multiple first sub-regions; The first scene data is subjected to feature encoding processing to obtain the first scene feature vector corresponding to the first scene data; Based on the feature vector of the first scene, calculate the risk score of each of the first sub-regions; Based on the risk score of each of the first sub-regions, the first initial range is adjusted to obtain the adjusted first preset range.

5. The method according to claim 1, characterized in that, The method determines the second preset range in the following manner: The second initial range is determined based on the historical distances between historical sites and historical hotels during the tourists' historical travels. The tourist's current mobility is assessed to determine their degree of mobility restriction. The second initial range is adjusted based on the movement restriction and the second scene data to obtain the adjusted second preset range.

6. The method according to claim 1, characterized in that, The step of matching a second booked hotel for the current attraction from the second overall hotel list based on the temporary accommodation request text, the sentiment data, and the second scene data includes: The temporary accommodation request text, the sentiment data, and the second scene data are mapped onto a three-dimensional decision space, serving as the decision axes of the three-dimensional decision space; Based on the temporary accommodation demand text, the sentiment data, and the second scenario data, determine the decision parameters corresponding to each decision axis; Based on the temporary accommodation request text, the sentiment data, the second scenario data, and the corresponding decision parameters, a second booked hotel is matched for the current attraction from the second overall hotel list.

7. The method according to claim 1, characterized in that, The method determines the target accommodation requirement text in the following manner: Determine whether the tourist has submitted a new accommodation request text; if the new accommodation request text exists, merge the new accommodation request text and the initial accommodation request text to obtain the target accommodation request text; If the new accommodation requirement text does not exist, the initial accommodation requirement text will be used as the target accommodation requirement text.

8. A hotel reservation device, characterized in that, The device includes: The prediction module is used to identify multiple first attractions along the preset tour route before tourists begin their tour, based on the tourists' personal characteristics, where they will need to stay overnight after their tour. It then predicts the first scene data for the first attraction during the check-in period based on the first historical scene data of the first attraction. The first scene data includes weather data, traffic data, and emergency event data during the tour of the first attraction, while the first historical scene data includes weather data, traffic data, and emergency event data prior to the tour of the first attraction. The first matching module is used to match a first booked hotel for the first attraction in the first overall hotel list based on the tourist's initial accommodation request text before the visit and the first scene data; wherein, the first overall hotel list consists of all hotels obtained from different platforms within a first preset range of the location of the first attraction; The acquisition module is used to acquire the tourist's current emotional data and second scene data of the tourist's current attraction affecting the accommodation when the tourist receives the tourist's temporary accommodation request text during the tourist's visit to various attractions in the preset tourist route; the second scene data includes weather data, traffic data, and emergency event data when visiting the current attraction; The second matching module is used to match a second booked hotel for the current attraction from the second overall hotel list based on the temporary accommodation request text, the sentiment data, and the second scene data; wherein the second overall hotel list is obtained from all hotels of the current attraction on different platforms within a second preset range; An adjustment module is used to adjust the first attraction after the tourist checks into the second booked hotel, based on the tourist's personal characteristics, to obtain the adjusted second attraction. The third matching module is used by the prediction module to match a third booked hotel for the second attraction in the third overall hotel list based on the target accommodation demand text and the second scenario data; the third overall hotel list consists of all hotels obtained from different platforms within a third preset range of the location of the second attraction.

9. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the hotel booking method as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the hotel booking method as described in any one of claims 1 to 7.

Images