House reservation bargaining matching system based on AI hosting

Abstract

The invention relates to the technical field of interconnection big data and artificial intelligence, in particular to a room reservation bargaining matching system based on AI hosting, comprising: a user terminal used for acquiring a hotel reservation demand and an initial bid of a user; the hotel matching module is used for performing hotel matching according to the hotel reservation demand of the user to obtain a target hotel and a corresponding target room type; the AI trusteeship module is used for calculating the recommendation price of the target room type according to the big data and the historical data of the target hotel, and if the initial bid of the user is lower than the recommendation price, the recommendation price is sent to the user terminal of the user; the user terminal is used for obtaining user feedback information including whether the user agrees with the recommended price after receiving the recommended price sent by the AI hosting module; and the AI hosting module is used for receiving user feedback information sent by the user terminal, and automatically booking a target room type for the user when the user agrees to recommend the price. According to the invention, the service efficiency, the user satisfaction and the negotiation price accuracy can be improved.

Description

Technical Field

[0001] The present invention relates to the field of interconnected big data and artificial intelligence technology, and in particular to an AI-hosted hotel booking and bargaining matching system. Background Art

[0002] With the rapid development of internet technology and the booming tourism industry, hotel booking platforms, serving as a bridge between consumers and hoteliers, have gradually become a vital component of the online travel market. These platforms integrate a large number of hotel resources, providing users with a diverse range of accommodation options and incorporating price negotiation mechanisms, aiming to achieve a win-win situation for both users and hotels through price negotiation.

[0003] The basic operating model of a hotel booking negotiation platform is as follows: users enter their booking requirements on the platform, including check-in dates, desired room type, budget range, and special preferences. The platform then screens and displays a list of eligible hotels based on the user's requirements for comparison and selection. After selecting a hotel of their choice, the user can initiate a negotiation request, stating their desired price. Upon receiving the negotiation request, the hotel responds through the platform's customer service or backend management system, accepting or rejecting the user's offer or proposing a new price proposal. Once both parties reach an agreement on the price, the booking process is completed, the user pays a deposit or full payment, and the hotel confirms the reservation.

[0004] While hotel booking platforms offer users more room for price negotiation, the current manual negotiation model, which relies on merchants responding manually, has exposed numerous drawbacks in practice. First, manual responses are limited by work hours, staffing requirements, and communication efficiency, often failing to respond promptly to user bargaining requests. Especially during peak travel seasons and travel times, hotel customer service can be overwhelmed with inquiries and bargaining requests, resulting in long wait times and a poor user experience. Second, during manual negotiation, hotels may offer inconsistent or unreasonable prices due to a lack of a unified pricing strategy or profit maximization. This price opacity not only undermines user trust but can also raise questions about the platform's fairness. Finally, manual negotiation requires multiple rounds of communication, making the process cumbersome and susceptible to emotional and language misunderstandings. During the negotiation process, users and hotels may disagree over different understandings of price, room types, and services, leading to inefficient negotiation services.

[0005] Therefore, how to design a hotel booking bargaining matching system that can improve service efficiency, user satisfaction, and negotiated price accuracy is a technical problem that needs to be solved urgently. Summary of the Invention

[0006] In view of the above-mentioned deficiencies in the existing technology, the technical problem to be solved by the present invention is: how to provide a room booking bargaining matching system based on AI hosting, which obtains user needs through the user terminal, the hotel matching module screens the target hotel, and the AI hosting module combines big data and historical data to calculate the recommended price and automatically negotiate to achieve automatic matching of room booking bargaining, thereby improving service efficiency, user satisfaction, and the accuracy of negotiated prices, thereby increasing the success rate of room booking bargaining matching.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0008] An AI-hosted hotel booking and bargaining matching system, including:

[0009] User terminal, uniquely associated with the user, used to obtain the user's hotel booking needs and initial bid;

[0010] The hotel matching module is used to match hotels according to the user's hotel booking needs and obtain the target hotel and the corresponding target room type;

[0011] The AI hosting module is used to calculate the recommended price of the target room type based on big data and the historical data of the target hotel. If the user's initial bid is lower than the recommended price, the recommended price is sent to the user's user terminal;

[0012] The user terminal is configured to obtain user feedback information including whether the user agrees with the recommended price after receiving the recommended price sent by the AI hosting module, and send the user feedback information to the AI hosting module;

[0013] The AI hosting module is used to receive user feedback information sent by the user terminal. When the user agrees to the recommended price, it automatically books the target room type of the target hotel for the user.

[0014] Preferably, the AI hosting module is used to generate corresponding room type reservation information before automatically reserving the target room type of the target hotel for the user, and send the room type reservation information to the hotel terminal of the target hotel;

[0015] The hotel terminal is used to obtain hotel feedback information including whether the target hotel agrees to the transaction after receiving the room reservation information sent by the AI hosting module, and send the hotel feedback information to the AI hosting module;

[0016] The AI hosting module is used to receive hotel feedback information sent by the hotel terminal. When the target hotel agrees to the transaction, it reserves the target room type of the target hotel for the user and sends the successful booking information to the user's user terminal.

[0017] Preferably, the hotel matching module performs hotel matching based on the user's hotel reservation requirements, including the user's location, reservation date, room type requirements, and number of guests, to obtain a target hotel and a corresponding target room type that meets the user's hotel reservation requirements.

[0018] Preferably, the hotel matching module performs hotel matching processing steps including:

[0019] S01: Obtain the user's location, booking date, room type requirements, and number of guests in the user's hotel booking request;

[0020] S02: Hotels with available rooms on the reservation date are selected as candidate hotels;

[0021] S03: Calculate the straight-line distance d between the user's location and the candidate hotel, and calculate the distance attenuation factor δ of the candidate hotel based on the set attenuation coefficient k. d =e -k·d ;

[0022] S04: Match the room type requirements with the existing room types of the candidate hotels to obtain the room type matching degree m of the candidate hotels: if the room type requirements are consistent with the existing room types of the candidate hotels, the room type matching degree m=1; otherwise, m=0;

[0023] S05: Calculate the candidate hotel's occupancy suitability score based on the number of guests and the maximum room capacity of the candidate hotel.

[0024] S06: Weighting the distance attenuation factor, room type matching degree, and number of people matching degree of the candidate hotel to obtain the matching score S of the candidate hotel;

[0025] The calculation formula of the matching score is expressed as:

[0026] S=ω1·δ n +ω2·m+ω3·s n ;

[0027] Where: ω1, ω2, ω3 represent the dynamic weights set;

[0028] S07: The candidate hotels with matching scores higher than the score threshold are selected as target hotels, and the room types in the target hotels that meet the user's needs are selected as target room types.

[0029] Preferably, in step S06, when the hotel matching module calculates the matching score S of the candidate hotel, the user preference coefficient is introduced into the calculation;

[0030] The calculation formula for the matching score is updated as follows:

[0031] S=(ω1·δ n +ω2·m+ω3·s n )·η;

[0032] Where: η represents the user preference coefficient, which is calculated based on user preferences and the facilities and services of candidate hotels;

[0033] User preferences include any one or more of free internet, free breakfast, free gym, free swimming pool, close to the city center, close to the subway station, and good restaurants;

[0034] When the facilities and services of the candidate hotel meet all user preferences, the user preference coefficient η = 1; when the number of items of the candidate hotel's facilities and services that do not meet user preferences does not exceed one, the user preference coefficient η = 0.9; when the number of items of the candidate hotel's facilities and services that do not meet user preferences is greater than or equal to two, the user preference coefficient η = 0.8.

[0035] Preferably, the AI hosting module calculates the recommended price of the target room type using the following formula:

[0036] P t =a·P c +b·P j ;

[0037] Where: P t Indicates the recommended price of the target room type; P c Indicates the historical lowest quote of the target hotel for the target room type; P j It represents the average quoted price of the same type of room type as the target hotel by hotels of the same type as the target hotel; a and b represent the set weights.

[0038] Preferably, when the AI hosting module calculates the recommended price, it introduces the holiday premium factor parameter into the calculation;

[0039] The calculation formula for the recommended price is updated as follows:

[0040] P t =(a·P c +b·P j )·θ h ;

[0041] Where: θ h It represents the holiday premium factor, which is related to whether the user's booking date is a weekend or a holiday: when the user's booking date is a weekend, the holiday premium factor θ h =1.2, when the user's booking date is a holiday, the holiday premium factor θ h =1.5, when the user's booking date is not a weekend or holiday, the holiday premium factor θ h =1.

[0042] Preferably, when the AI hosting module calculates the recommended price, it introduces the supply and demand factor parameters of the time period into the calculation;

[0043] The calculation formula for the recommended price is updated as follows:

[0044] P t =(a·P c +b·P j )·θ h ·δ t ;

[0045] Where: δ t represents the supply and demand factors for the time period;

[0046]

[0047] Where: λ represents the time period sensitivity coefficient, which is associated with the time period;

[0048] Divide the day into three time periods:

[0049] Time period 1: 0:00 to 8:00, time period sensitivity coefficient λ = 0.1;

[0050] Time period 2: 8:00 to 16:00, time period sensitivity coefficient λ = 0.5;

[0051] Time period three: 16:00 to 24:00, time period sensitivity coefficient λ = 0.3.

[0052] Preferably, when the user disagrees with the recommended price, the AI hosting module negotiates with the user based on an incomplete information dynamic game strategy. The specific processing steps include:

[0053] S11: Calculate price sensitivity E, time sensitivity T, and loyalty L based on the user's historical booking records;

[0054] The formula is:

[0055]

[0056] L=a1·R+a2·F+a3·M;

[0057] Where: T n Indicates the current time; T t Indicates the user's booking date; R, F, and M respectively represent the time, frequency, and amount of the user's recent spending on the system;

[0058] S12: Calculate the marginal cost MC and inventory pressure Y based on the relevant data of the target hotel; the marginal cost MC refers to the additional cost of each additional room order for the target hotel;

[0059] The formula is:

[0060]

[0061] S13: Build a user patience model based on the user's price sensitivity E, time sensitivity T, and loyalty L; build a hotel concession strategy model based on the target hotel's inventory pressure Y;

[0062] The user patience value model is expressed as:

[0063] P u,t =f(E,T,L)·e -μ·t +ε u

[0064] Where: P u,t represents the user patience value in negotiation round t; f represents a function mapping relationship; μ represents the patience value attenuation coefficient; ε u represents the user random perturbation term;

[0065] The hotel concession strategy model is expressed as:

[0066] C t =α·(1-Y)+β·ΔP u +γ·ρ t +χ·C c +ε m ;

[0067] Where: C t represents the concession range in negotiation round t; α represents the inventory pressure coefficient; β represents the weight of the change in user patience value; ΔP u represents the rate of change of user patience value; γ represents the supply-demand ratio weight; ρ t Indicates the real-time supply-demand ratio; C c Indicates the difference between the current quotes of hotels of the same type and the target hotel; ε m represents the random disturbance term of the hotel;

[0068] S14: Calculate the initial bid price P based on the marginal cost MC of the target hotel o,1 ; The initial offer P o,1 Send to the user's terminal and receive the user's feedback: if the user accepts the quotation, execute step S18; otherwise, execute step S15;

[0069] P o,1 =MC·(1+θ)+κ·(1-E)·(1-Y);

[0070] Where: θ represents the minimum profit margin set; k represents the price sensitivity adjustment coefficient;

[0071] S15: Execute negotiation round t=t+1, and update the user patience value P of negotiation round t+1 based on the user patience value model u,t+1 ; Determine whether the user's patience value P is satisfied u,t+1Less than the set patience threshold or the negotiation round t is greater than the set maximum negotiation round t max : If yes, go to step S19; otherwise, go to S16;

[0072] S16: Get the user's current counter-offer P u,c , combined with the current quote P o,t Calculate the user patience value change rate ΔP u ; According to the user's patience value change rate ΔP u Calculate the concession range C based on the hotel concession strategy model t ; According to the concession C t Combined with the current quotation P o,t Calculate the concession price ΔP m,t ;

[0073] The formula is:

[0074]

[0075] C t =α·(1-Y)+β·ΔP u +γ·ρ t ;

[0076] ΔP m,t =P o,t ·C t ;

[0077] S17: Based on the concession price ΔP m,t and the current quote P o,t Calculate the new offer P for negotiation round t+1 o,t+1 ; The new quote P o,t+1 Send to the user's terminal and receive the user's feedback: if the user accepts the quotation, execute step S18; otherwise, return to step S15;

[0078] The formula is:

[0079] P o,t+1 =P o,t -ΔP m,t ;

[0080] S18: The offer accepted by the user is taken as the user's final bid, and the target room type of the target hotel is automatically reserved for the user;

[0081] S19: Bargaining failed.

[0082] Preferably, in step S19, when the bargaining fails, the AI hosting module sends a request message for manual intervention to the hotel terminal of the target hotel and receives feedback from the hotel terminal: when the target hotel agrees to manual intervention, a bargaining communication channel is established between the user terminal and the hotel terminal of the target hotel.

[0083] Compared with the existing technology, the hotel booking bargaining matching system based on AI hosting in the present invention has the following beneficial effects:

[0084] The present invention replaces the traditional manual bargaining model of hotel merchants with an AI hosting module. First, the AI hosting module can achieve uninterrupted operation and can respond immediately whenever the user issues a bargaining request without manual intervention, which greatly improves service efficiency and user satisfaction; at the same time, the AI hosting module is based on preset algorithms and big data processing capabilities, and can complete hotel matching and recommended price calculations in a very short time. Compared with manual processing, it greatly shortens user waiting time and improves user experience. Secondly, the AI hosting module follows preset rules and algorithms to make decisions, ensuring that every user can obtain a consistent and fair service experience, avoiding subjective biases and inconsistencies that may occur in manual processing; at the same time, the AI hosting module effectively reduces booking failures or price calculation errors caused by human negligence or errors, thereby improving the accuracy and reliability of negotiated prices. Finally, the AI hosting module predicts recommended prices based on big data and the hotel's historical data. Through in-depth mining and analysis of big data as well as competitors' pricing strategies and market dynamics, it can predict future price trends for hotel rooms and generate more reasonable and comprehensive recommended prices for users. At the same time, it combines the hotel's historical data to calculate recommended prices, taking into account the hotel's costs and pricing strategies, and generating transaction prices that are acceptable to both users and hotels, thereby improving the success rate of room booking bargaining matches. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] In order to make the purpose, technical solutions and advantages of the invention more clear, the present invention will be further described in detail below with reference to the accompanying drawings, in which:

[0086] Figure 1 This is the logic block diagram of the AI-hosted hotel booking and bargaining matching system. DETAILED DESCRIPTION

[0087] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the invention claimed for protection, but only represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0088] The following is a further detailed description through specific implementation methods:

[0089] Example 1:

[0090] This embodiment discloses a hotel booking bargaining matching system based on AI hosting.

[0091] like Figure 1 As shown, a hotel booking bargaining matching system based on AI hosting includes:

[0092] User terminal, uniquely associated with the user, used to obtain the user's hotel booking needs and initial bid;

[0093] Hotel terminal, uniquely associated with the hotel;

[0094] The hotel matching module is used to match hotels according to the user's hotel booking needs and obtain the target hotel and the corresponding target room type;

[0095] The AI hosting module is used to calculate the recommended price of the target room type based on big data and the historical data of the target hotel. If the user's initial bid is lower than the recommended price, the recommended price will be sent to the user's user terminal after obtaining the corresponding authorization from the target hotel. If the user's initial bid is higher than or equal to the recommended price, the target room type of the target hotel will be automatically booked for the user.

[0096] The user terminal is configured to obtain user feedback information including whether the user agrees with the recommended price after receiving the recommended price sent by the AI hosting module, and send the user feedback information to the AI hosting module;

[0097] The AI hosting module is used to receive user feedback information sent by the user terminal. When the user agrees to the recommended price, it automatically books the target room type of the target hotel for the user.

[0098] Specifically, the AI hosting module is used to generate corresponding room type reservation information before automatically reserving a target room type at a target hotel for a user, and send the room type reservation information to a hotel terminal at the target hotel;

[0099] The hotel terminal is used to obtain hotel feedback information including whether the target hotel agrees to the transaction after receiving the room reservation information sent by the AI hosting module, and send the hotel feedback information to the AI hosting module;

[0100] The AI hosting module is used to receive hotel feedback information sent by the hotel terminal. When the target hotel agrees to the transaction, it reserves the target room type of the target hotel for the user and sends the successful booking information to the user's user terminal.

[0101] The present invention replaces the traditional manual bargaining model of hotel merchants with an AI hosting module. First, the AI hosting module can achieve uninterrupted operation and can respond immediately whenever the user issues a bargaining request without manual intervention, which greatly improves service efficiency and user satisfaction; at the same time, the AI hosting module is based on preset algorithms and big data processing capabilities, and can complete hotel matching and recommended price calculations in a very short time. Compared with manual processing, it greatly shortens user waiting time and improves user experience. Secondly, the AI hosting module follows preset rules and algorithms to make decisions, ensuring that every user can obtain a consistent and fair service experience, avoiding subjective biases and inconsistencies that may occur in manual processing; at the same time, the AI hosting module effectively reduces booking failures or price calculation errors caused by human negligence or errors, thereby improving the accuracy and reliability of negotiated prices. Finally, the AI hosting module predicts recommended prices based on big data and the hotel's historical data. Through in-depth mining and analysis of big data as well as competitors' pricing strategies and market dynamics, it can predict future price trends for hotel rooms and generate more reasonable and comprehensive recommended prices for users. At the same time, it combines the hotel's historical data to calculate recommended prices, taking into account the hotel's costs and pricing strategies, and generating transaction prices that are acceptable to both users and hotels, thereby improving the success rate of room booking bargaining matches.

[0102] The AI hosting module of the present invention needs to obtain the corresponding authorization given by the hotel, and requires confirmation and consent from the hotel before booking a room for the user (locking the order). On the one hand, by obtaining hotel authorization, the operation of the AI hosting module strictly follows the hotel's wishes and rules, avoiding unauthorized booking behavior, maintaining the hotel's operating autonomy and legal rights, and enhancing the hotel's trust in the system. On the other hand, obtaining the hotel's consent before booking a room ensures the validity and availability of room resources, reduces booking failures due to changes in room status, thereby improving the booking success rate and providing users with a more reliable and smooth booking experience.

[0103] In order to better introduce the technical solution of the present invention, this embodiment is described through the following parts.

[0104] 1. Hotel Matching

[0105] In this embodiment, the hotel matching module matches hotels based on the user's hotel reservation requirements (input by the user), the user's location (obtained through an authorized mobile device), the reservation date, the room type requirements, and the number of guests, to obtain a target hotel and a corresponding target room type that meet the user's hotel reservation requirements.

[0106] Specifically, the hotel matching module performs hotel matching processing steps including:

[0107] S01: Obtain the user's location, booking date, room type requirements, and number of guests in the user's hotel booking request;

[0108] S02: Hotels with available rooms on the reservation date are selected as candidate hotels;

[0109] S03: Calculate the straight-line distance d between the user's location and the candidate hotel, and calculate the distance attenuation factor δ of the candidate hotel based on the set attenuation coefficient k. d =e -k·d ;

[0110] S04: Match the room type requirement with the existing room types of the candidate hotel to obtain the room type matching degree m of the candidate hotel: if the room type requirement is consistent with the existing room types of the candidate hotel, the room type matching degree m = 1; otherwise, m = 0; for example, if the user's room type requirement is a king-size bed room, but a hotel only has standard rooms, then the room type matching degree m of the hotel is 0.

[0111] S05: Calculate the candidate hotel's occupancy suitability score based on the number of guests and the maximum capacity of a single room in the candidate hotel. The maximum capacity of a single room in a candidate hotel can be dynamically adjusted according to the hotel policy. For example, if a hotel allows children under 6 years old to use an extra bed free of charge, then when there is a child under 6 years old in the user's occupancy, the maximum capacity of the hotel's room can be increased by one.

[0112] S06: Weighting the distance attenuation factor, room type matching degree, and number of people matching degree of the candidate hotel to obtain the matching score S of the candidate hotel;

[0113] The calculation formula of the matching score is expressed as:

[0114] S=ω1·δ n +ω2·m+ω3·s n ;

[0115] Where: ω1, ω2, ω3 represent the dynamic weights of the settings, which can be obtained through training of user historical behavior data.

[0116] S07: The candidate hotels with matching scores higher than the score threshold (set to 0.8) are selected as target hotels, and the room types in the target hotels that meet the user's needs are selected as target room types.

[0117] The present invention matches hotels based on the user's location, booking date, room type requirements and number of guests. By comprehensively analyzing multi-dimensional needs, it can quickly screen out hotels and rooms that best meet the user's requirements, significantly shortening the user's search time and improving booking efficiency. At the same time, through precise matching of multiple conditions, it reduces information overload and invalid browsing, allowing users to find the rooms they need more quickly, while improving the fit between hotel rooms and user needs and promoting transaction completion.

[0118] Specifically, when the hotel matching module calculates the matching score S of the candidate hotel, the user preference coefficient is introduced into the calculation;

[0119] The calculation formula for the matching score is updated as follows:

[0120] S=(ω1·δ n +ω2·m+ω3·s n )·η;

[0121] Where: η represents the user preference coefficient, which is calculated based on user preferences and the facilities and services of candidate hotels;

[0122] User preferences include any one or more of free internet, free breakfast, free gym, free swimming pool, proximity to the city center (less than 5 km from the city center), proximity to a subway station (less than 500 m from the city center), and the availability of quality restaurants (restaurants with a Meituan or Dianping rating of 4.8 or higher within 1 km);

[0123] When the facilities and services of the candidate hotel meet all user preferences (e.g., the user preferences include five items, and the facilities and services of the candidate hotel meet all five items), the user preference coefficient η = 1; when the number of items of the candidate hotel's facilities and services that do not meet the user preferences does not exceed one (e.g., the user preferences include five items, and the facilities and services of the candidate hotel meet four of them), the user preference coefficient η = 0.9; when the number of items of the candidate hotel's facilities and services that do not meet the user preferences is greater than or equal to two (e.g., the user preferences include five items, and the facilities and services of the candidate hotel meet three, two, or one of them), the user preference coefficient η = 0.8.

[0124] The present invention introduces a user preference coefficient when calculating the matching score of candidate hotels. By considering the weight of user preferences (such as free Internet, free breakfast, fitness facilities, etc.), it can more accurately recommend hotels that meet the user's personalized needs. Personalized matching not only reduces the time cost of users in screening information, but also increases the possibility of users finding ideal accommodation, thereby helping to improve booking success rate and user loyalty.

[0125] 2. Recommended price calculation

[0126] In this embodiment, the AI hosting module calculates the recommended price of the target room type using the following formula:

[0127] P t =a·P c +b·P j ;

[0128] Where: P t Indicates the recommended price of the target room type; P crepresents the historical lowest quote of the target hotel for the target room type (based on the historical data of the target hotel); j The average quoted price (based on online big data) for the same room type as the target hotel by hotels of the same type (same city, same star rating, similar price (no more than 50 yuan)). a and b represent the set weights.

[0129] By introducing the lowest historical quotations, the present invention can grasp the bottom line of hotel price fluctuations and avoid user loss caused by recommended prices that are too high. At the same time, combined with the average quotations of hotels of the same type, it ensures that the recommended prices are market references, neither too high nor too low, thereby enhancing user acceptance and making the recommended prices closer to market reality, which not only protects hotel profits but also increases user booking willingness.

[0130] Specifically, when the AI hosting module calculates the recommended price, it introduces the holiday premium factor parameter into the calculation;

[0131] The calculation formula for the recommended price is updated as follows:

[0132] P t =(a·P c +b·P j )·θ h ;

[0133] Where: θ h It represents the holiday premium factor, which is related to whether the user's booking date is a weekend or a holiday: when the user's booking date is a weekend, the holiday premium factor θ h =1.2, when the user's booking date is a holiday (legal holiday: such as New Year's Day, May Day, Dragon Boat Festival), the holiday premium factor θ h =1.5, when the user's booking date is not a weekend or holiday, the holiday premium factor θ h =1.

[0134] Specifically, when the AI hosting module calculates the recommended price, it introduces the supply and demand factor parameters of the time period into the calculation;

[0135] The calculation formula for the recommended price is updated as follows:

[0136] P t =(a·P c +b·P j )·θ h ·δ t ;

[0137] Where: δ t represents the supply and demand factors for the time period;

[0138]

[0139] Where: λ represents the time period sensitivity coefficient, which is associated with the time period;

[0140] Divide the day into three time periods:

[0141] Time period 1: 0:00 to 8:00, time period sensitivity coefficient λ = 0.1;

[0142] Time period 2: 8:00 to 16:00, time period sensitivity coefficient λ = 0.5;

[0143] Time period three: 16:00 to 24:00, time period sensitivity coefficient λ = 0.3.

[0144] By incorporating a holiday premium mechanism, the present invention can dynamically adjust prices to reflect the surge in demand during special periods, ensuring maximum hotel revenue while reasonably guiding user expectations. At the same time, combined with time period supply and demand analysis (such as price increases during the morning booking peak and price reductions during the nighttime trough), the recommended price can respond to market fluctuations more flexibly, which not only encourages users to book during off-peak hours to obtain more favorable prices, but also helps hotels balance occupancy rates in different time periods and optimize resource allocation, thereby slightly enhancing the market competitiveness of the system and promoting a win-win situation for users and hotels.

[0145] 3. Bargaining Based on Dynamic Game Strategy of Incomplete Information

[0146] In this embodiment, when the user disagrees with the recommended price, the AI hosting module negotiates with the user based on an incomplete information dynamic game strategy. The specific processing steps include:

[0147] S11: Calculate price sensitivity E, time sensitivity T, and loyalty L based on the user's historical booking records; normalize price sensitivity E, time sensitivity T, and loyalty L to [0,1];

[0148] The formula is:

[0149] Among them, the user's maximum budget is entered manually by the user.

[0150]

[0151] L=a1·R+a2·F+a3·M;

[0152] Where: T n Indicates the current time; T t Indicates the user's reservation date; R, F, and M respectively represent the time, frequency, and amount of the user's recent spending on the system (e.g., within a week) (obtained based on the system's historical records);

[0153] S12: Calculate the marginal cost MC and inventory pressure Y based on the relevant data of the target hotel; normalize the marginal cost MC and inventory pressure Y to [0,1]; where marginal cost MC refers to the additional cost (including cleaning fees, utilities) for each additional room order for the target hotel;

[0154] The formula is:

[0155]

[0156] S13: Build a user patience model based on the user's price sensitivity E, time sensitivity T, and loyalty L; build a hotel concession strategy model based on the target hotel's inventory pressure Y;

[0157] The user patience value model is expressed as:

[0158] P u,t =f(E,T,L)·e -μ·t +ε u

[0159] Where: P u,t represents the user's patience value at negotiation round t; f represents a function mapping relationship, which is used to quantify the change pattern of user patience value with price sensitivity E, time sensitivity T, and loyalty L; μ represents the patience value attenuation coefficient, which is linked to E and T: as E increases, μ increases (price-sensitive users are more likely to lose patience); as T decreases, μ increases (user patience decreases faster when time is tight); ε u represents the user random perturbation term, simulating the unpredictability of user behavior;

[0160] The hotel concession strategy model is expressed as:

[0161] C t =α·(1-Y)+β·ΔP u +γ·ρ t +χ·C c +ε m ;

[0162] Where: C t represents the concession range in negotiation round t; α represents the inventory pressure coefficient (0.3); β represents the weight of the change in user patience value (0.5); ΔP u represents the rate of change of user patience value; γ represents the supply-demand ratio weight (0.2); ρ t represents the real-time supply-demand ratio (ρ t = current number of people in demand / current available housing); χ represents the competition coefficient (0.1); C c Indicates the difference between the current quotes of hotels of the same type and the target hotel; ε m represents the random disturbance term of the hotel;

[0163] S14: Calculate the initial bid price P based on the marginal cost MC of the target hotel o,1 ; The initial offer P o,1 Send to the user's terminal and receive the user's feedback: if the user accepts the quotation, execute step S18; otherwise, execute step S15;

[0164] P o,1 =MC·(1+θ)+κ·1-E)·(1-Y);

[0165] Where: θ represents the minimum profit margin set; κ represents the price sensitivity adjustment coefficient;

[0166] S15: Execute negotiation round t=t+1, and update the user patience value P of negotiation round t+1 based on the user patience value model u,t+1 ; Determine whether the user's patience value P is satisfied u,t+1 Less than the set patience threshold (0.2) or the negotiation round t is greater than the set maximum negotiation round t max : If yes, go to step S19; otherwise, go to S16;

[0167] S16: Get the user's current counter-offer P u,c , combined with the current quote P o,t Calculate the user patience value change rate ΔP u ; According to the user's patience value change rate ΔP u Calculate the concession range C based on the hotel concession strategy model t ; According to the concession C t Combined with the current quotation P o,t Calculate the concession price ΔP m,t ;

[0168] The formula is:

[0169]

[0170] C t =α·(1-Y)+β·ΔP u +γ·ρ t ;

[0171] ΔP m,t =P o,t ·C t ;

[0172] S17: Based on the concession price ΔP m,t and the current quote P o,t Calculate the new offer P for negotiation round t+1 o,t+1 ; The new quote P o,t+1Send to the user's terminal and receive the user's feedback: if the user accepts the quotation, execute step S18; otherwise, return to step S15;

[0173] The formula is:

[0174] P o,t+1 =P o,t -ΔP m,t ;

[0175] S18: The offer accepted by the user is taken as the user's final bid, and the target room type of the target hotel is automatically reserved for the user;

[0176] S19: If the bargaining fails, a corresponding bargaining failure report will be generated and the reason for the failure will be marked.

[0177] Specifically, when bargaining fails, the AI hosting module sends a request for manual intervention to the hotel terminal of the target hotel and receives feedback from the hotel terminal: when the target hotel agrees to manual intervention, a bargaining communication channel is established between the user terminal and the hotel terminal of the target hotel (such as building a special chat room).

[0178] The AI hosting module of the present invention bargains with users based on a dynamic game strategy of incomplete information. On the one hand, the AI hosting module quickly identifies the user's bottom price tendency by analyzing the user's historical bidding behavior (such as quotation range, concession mode), generates a dynamic recommended price, reduces the number of tentative quotations, and directly cuts into the effective negotiation range; at the same time, in multiple rounds of negotiations, the AI hosting module automatically processes standardized responses, avoids delays caused by manual intervention, shortens the time of a single round of negotiations, thereby improving the efficiency of bargaining and negotiation and the user experience. On the other hand, combining the merchant's historical concession range with real-time market supply and demand, the AI hosting module simulates the game results under different bidding scenarios, dynamically adjusts the recommended price, ensures that the price is attractive to users and protects the merchant's costs, and at the same time, for the user's price sensitivity (such as high-frequency price comparison users) and the merchant's cost structure, the AI hosting module generates differentiated recommended prices to achieve effective coordination between "users and merchants" and avoid cost increases or user loss caused by unified pricing.

[0179] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the technical solutions. Those skilled in the art should understand that modifications or equivalent replacements of the technical solutions of the present invention that do not depart from the purpose and scope of the technical solutions of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A hotel booking bargaining matching system based on AI hosting, characterized by: include: User terminal, uniquely associated with the user, used to obtain the user's hotel booking needs and initial bid; The hotel matching module is used to match hotels according to the user's hotel booking needs and obtain the target hotel and the corresponding target room type; The AI hosting module is used to calculate the recommended price of the target room type based on big data and the historical data of the target hotel. If the user's initial bid is lower than the recommended price, the recommended price is sent to the user's user terminal; The user terminal is configured to obtain user feedback information including whether the user agrees with the recommended price after receiving the recommended price sent by the AI hosting module, and send the user feedback information to the AI hosting module; The AI hosting module is used to receive user feedback information sent by the user terminal. When the user agrees to the recommended price, it automatically books the target room type of the target hotel for the user.

2. The AI-hosted hotel booking and bargaining matching system according to claim 1, characterized in that: The AI hosting module is used to generate corresponding room type reservation information before automatically reserving the target room type of the target hotel for the user, and send the room type reservation information to the hotel terminal of the target hotel; The hotel terminal is used to obtain hotel feedback information including whether the target hotel agrees to the transaction after receiving the room reservation information sent by the AI hosting module, and send the hotel feedback information to the AI hosting module; The AI hosting module is used to receive hotel feedback information sent by the hotel terminal. When the target hotel agrees to the transaction, it reserves the target room type of the target hotel for the user and sends the successful booking information to the user's user terminal.

3. The AI-hosted hotel booking and bargaining matching system according to claim 1, characterized in that: The hotel matching module matches hotels based on the user's hotel booking requirements, including user location, booking date, room type requirements, and number of guests, to obtain target hotels and corresponding target room types that meet the user's hotel booking requirements.

4. The AI-hosted hotel booking and bargaining matching system according to claim 3, characterized in that: The hotel matching module processes hotel matching in the following steps: S01: Obtain the user's location, booking date, room type requirements, and number of guests in the user's hotel booking request; S02: Hotels with available rooms on the reservation date are selected as candidate hotels; S03: Calculate the straight-line distance d between the user's location and the candidate hotel, and calculate the distance attenuation factor δ of the candidate hotel based on the set attenuation coefficient k. d =e -k·d ; S04: Match the room type requirements with the existing room types of the candidate hotels to obtain the room type matching degree m of the candidate hotels: if the room type requirements are consistent with the existing room types of the candidate hotels, the room type matching degree m=1; otherwise, m=0; S05: Calculate the candidate hotel's occupancy suitability score based on the number of guests and the maximum capacity of a single room in the candidate hotel. S06: Weighting the distance attenuation factor, room type matching degree, and number of people matching degree of the candidate hotel to obtain the matching score S of the candidate hotel; The calculation formula of the matching score is expressed as: S=ω1·δ n +ω2·m+ω3·s n ; Where: ω1, ω2, ω3 represent the dynamic weights set; S07: The candidate hotels with matching scores higher than the score threshold are selected as target hotels, and the room types in the target hotels that meet the user's needs are selected as target room types.

5. The AI-hosted hotel booking and bargaining matching system according to claim 4, characterized in that: In step S06, when the hotel matching module calculates the matching score S of the candidate hotel, the user preference coefficient is introduced into the calculation; The calculation formula for the matching score is updated as follows: S=(ω1·δ n +ω2·m+ω3·s n )·or; Where: η represents the user preference coefficient, which is calculated based on user preferences and the facilities and services of candidate hotels; User preferences include any one or more of free internet, free breakfast, free gym, free swimming pool, close to the city center, close to the subway station, and good restaurants; When the facilities and services of the candidate hotel meet all user preferences, the user preference coefficient η = 1; when the number of items of the candidate hotel's facilities and services that do not meet user preferences does not exceed one, the user preference coefficient η = 0.9; when the number of items of the candidate hotel's facilities and services that do not meet user preferences is greater than or equal to two, the user preference coefficient η = 0.

8.

6. The AI-hosted hotel booking and bargaining matching system according to claim 1, characterized in that: The AI hosting module calculates the recommended price for the target room type using the following formula: P t =a·P c +b·P j ; Where: P t Indicates the recommended price of the target room type; P c Indicates the historical lowest quote of the target hotel for the target room type; P j It represents the average quoted price of the same type of room type as the target hotel by hotels of the same type as the target hotel; a and b represent the set weights.

7. The AI-hosted hotel booking and bargaining matching system according to claim 6, characterized in that: When the AI hosting module calculates the recommended price, it introduces the holiday premium factor parameter into the calculation; The calculation formula for the recommended price is updated as follows: P.S t (a·P c +b·P j )·θ h 100. Where: θ h It represents the holiday premium factor, which is related to whether the user's booking date is a weekend or a holiday: when the user's booking date is a weekend, the holiday premium factor θ h =1.2, when the user's booking date is a holiday, the holiday premium factor θ h =1.5, when the user's booking date is not a weekend or holiday, the holiday premium factor θ h =1.

8. The AI-hosted hotel booking and bargaining matching system according to claim 7, characterized in that: When the AI hosting module calculates the recommended price, it introduces the supply and demand factor parameters of the time period into the calculation; The calculation formula for the recommended price is updated as follows: P.S t (a·P c +b·P j )·θ h ·δ t 100. Where: δ t represents the supply and demand factors for the time period; Where: λ represents the time period sensitivity coefficient, which is associated with the time period; Divide the day into three time periods: Time period 1: 0:00 to 8:00, time period sensitivity coefficient λ = 0.1; Time period 2: 8:00 to 16:00, time period sensitivity coefficient λ = 0.5; Time period three: 16:00 to 24:00, time period sensitivity coefficient λ = 0.

3.

9. The AI-hosted hotel booking and bargaining matching system according to claim 1, characterized in that: When the user disagrees with the recommended price, the AI hosting module negotiates with the user based on an incomplete information dynamic game strategy. The specific processing steps include: S11: Calculate price sensitivity E, time sensitivity T, and loyalty L based on the user's historical booking records; The formula is: L=a1·R+a2·F+a3·M; Where: T n Indicates the current time; T t Indicates the user's booking date; R, F, and M respectively represent the time, frequency, and amount of the user's recent spending on the system; S12: Calculate the marginal cost MC and inventory pressure Y based on the relevant data of the target hotel; the marginal cost MC refers to the additional cost of each additional room order for the target hotel; The formula is: S13: Build a user patience model based on the user's price sensitivity E, time sensitivity T, and loyalty L; build a hotel concession strategy model based on the target hotel's inventory pressure Y; The user patience value model is expressed as: P u,t =f(E,T,L)·e -μ·t +ε u Where: P u,t represents the user patience value in negotiation round t; f represents a function mapping relationship; μ represents the patience value attenuation coefficient; ε u represents the user random perturbation term; The hotel concession strategy model is expressed as: C t =α·1-Y)+β·ΔP u +g·r t +xC c +e m ; Where: C t represents the concession range in negotiation round t; α represents the inventory pressure coefficient; β represents the weight of the change in user patience value; ΔP u represents the rate of change of user patience value; γ represents the supply-demand ratio weight; ρ t Indicates the real-time supply-demand ratio; C c Indicates the difference between the current quotes of hotels of the same type and the target hotel; ε m represents the random disturbance term of the hotel; S14: Calculate the initial bid price P based on the marginal cost MC of the target hotel o,1 ; The initial offer P o,1 Send to the user's terminal and receive the user's feedback: if the user accepts the quotation, execute step S18; otherwise, execute step S15; P o,1 =MC·(1+θ)+κ·(1-E)·(1-Y); Where: θ represents the minimum profit margin set; κ represents the price sensitivity adjustment coefficient; S15: Execute negotiation round t=t+1, and update the user patience value P of negotiation round t+1 based on the user patience value model u,t+1 ; Determine whether the user's patience value P is satisfied u,t+1 Less than the set patience threshold or the negotiation round t is greater than the set maximum negotiation round t max : If yes, go to step S19; otherwise, go to S16; S16: Get the user's current counter-offer P u,c , combined with the current quote P o,t Calculate the user patience value change rate ΔP u ; According to the user's patience value change rate ΔP u Calculate the concession range C based on the hotel concession strategy model t ; According to the concession C t Combined with the current quotation P o,t Calculate the concession price ΔP m,t ; The formula is: C t =α·(1-Y)+β·ΔP u +g·r t ; ΔP m,t =P o,t ·C t ; S17: Based on the concession price ΔP m,t and the current quote P o,t Calculate the new offer P for negotiation round t+1 o,t+1 ; The new quote P o,t+1 Send to the user's terminal and receive the user's feedback: if the user accepts the quotation, execute step S18; otherwise, return to step S15; The formula is: P o,t+1 =P o,t -ΔP m,t ; S18: The offer accepted by the user is taken as the user's final bid, and the target room type of the target hotel is automatically reserved for the user; S19: Bargaining failed.

10. The AI-hosted hotel booking and bargaining matching system according to claim 9, characterized in that: In step S19, when the bargaining fails, the AI hosting module sends a request for manual intervention to the hotel terminal of the target hotel and receives feedback from the hotel terminal: when the target hotel agrees to manual intervention, a bargaining communication channel is established between the user terminal and the hotel terminal of the target hotel.

Images