Integrated travel planning approach that considers user travel needs and preferences

Abstract

The present invention provides a method and system for integrated travel planning that takes into account user needs and preferences, including the steps of: obtaining user travel needs and constructing a static database for travel; extracting user travel preferences based on user travel information and a travel behavior model; arranging the sequence of tourist points of interest and the modes of transportation between points of interest in combination with user travel needs, the static database for travel, and the user travel preferences, to generate an integrated travel planning scheme. The planning scheme is applied to travel reservations to provide users with integrated travel services. Aiming at the growing demand for personalized travel, the present invention considers the convenience of user travel as a service on the one hand, and the carrying capacity of scenic spots and road networks on the other hand, guides tourists, alleviates the problem of tourist congestion, and promotes the integrated development of the tourism and transportation industries.

Description

Technical Field

[0001] The present invention relates to the field of computer application technology, and in particular to a travel integrated planning method that takes into account user travel needs and preferences. Background Art

[0002] In recent years, with the vigorous development of social economy, the travel demand of Chinese people has increased day by day, and tourism and its related industries have become a new growth point of the national economy.

[0003] Free travel has become a new trend in tourism. However, due to the lack of understanding of the local area, the location of scenic spots, the attractions and the connection between scenic spots require too much extra energy, which causes trouble for travelers. In addition, from the perspective of the local tourism market and transportation system, due to the limited carrying capacity of scenic spots and road networks, the travel phenomenon of "crowding in scenic spots and stuck in traffic" has gradually become known and criticized by people. At the same time, the messy, multi-source information and high itinerary planning costs have also greatly reduced the rare travel experience.

[0004] People's growing demand for travel and their demand for quality and personalized travel have accelerated the industry's innovation and construction process. How to achieve high-quality and high-efficiency development while ensuring high-speed development has become a new challenge facing the tourism and transportation industries.

[0005] Therefore, there is an urgent need to invent an integrated travel planning system that integrates multi-channel data and is based on the personalized needs of tourists, so as to fill the gap in tourists' value needs, improve the service level of enterprises, promote the common development of the industry, and assist in the construction of tourist cities. Summary of the invention

[0006] The embodiments of the present invention provide a method for integrated travel planning that takes into account the travel needs and preferences of users, so as to provide users with an integrated customized travel plan that meets their personalized needs.

[0007] In order to achieve the above object, the present invention adopts the following technical scheme.

[0008] An integrated travel planning method considering user travel needs and preferences, including:

[0009] Obtain user travel needs and build a static database of travel activities;

[0010] Extract user travel preferences based on user travel information and travel behavior models;

[0011] The sequence of tourist points of interest and the modes of transportation between the points of interest are arranged in combination with the user's travel needs, the tourist travel static database and the user's travel preferences, and an integrated tourist travel planning scheme is generated.

[0012] Preferably, the method of obtaining user travel needs and constructing a static database of travel activities includes:

[0013] Acquire user travel needs, which include travel destination, travel duration, travel time and travel budget;

[0014] Collect information about tourist points of interest at the user's travel destination, including the category, grade, ticket price, opening hours and recommended travel time of each attraction; the location, type, rating and per capita consumption of restaurants around the attraction; the location, price and rating of each hotel, and form a comprehensive set of tourist points of interest;

[0015] Obtaining the traffic travel attribute information between the tourist interest points in the comprehensive interest points, including traffic dynamic information, basic travel time of the transportation mode, basic travel cost, number of transfers, walking distance, departure frequency, waiting time, reliability, comfort, public transportation information around the interest points and supporting parking spaces;

[0016] Acquire dynamic information of tourist interest points in the comprehensive interest points, wherein the dynamic information of interest points is the real-time status of the interest points, and can reflect the attractiveness of the interest points at different time periods;

[0017] Get the weather conditions on the travel date;

[0018] The attributes of the tourist interest points, the attributes of the traffic between the tourist interest points, the dynamic information of the interest points and the traffic, and the real-time weather conditions are combined into a tourist travel static database.

[0019] Preferably, the extracting of user travel preferences based on user travel information and travel behavior model includes:

[0020] Acquire user travel information by having the user fill out a travel questionnaire when registering, the user travel information including personal attributes, travel records and travel intentions, construct a travel behavior model for the user, calculate and quantify the user's preference for tourist interest points and transportation methods with different attributes during travel based on the user travel information using the travel behavior model, and use the user's preference for tourist interest points and transportation methods with different attributes as the user's travel preference;

[0021] The user travel preference is updated at set time intervals.

[0022] Preferably, the construction of the user's travel behavior model includes:

[0023] Determine the factors that affect the user's travel, which include points of interest attributes, transportation attributes, weather factors and user personal attributes, and the user personal attributes include age, gender, occupation, monthly income and annual travel times;

[0024] Construct the latent variable of user travel, the latent variable α n It represents the travel preference that is difficult to be directly observed in tourism travel. The calculation formula of the latent variable is:

[0025] α n =γ a z n +ζ n ,ζ n ~N(0,σ ζ )

[0026] In the formula, z n Represents the vector of personal attribute variables of user n; γ a represents the unknown coefficient vector; ζ n represents a random variable, assuming that the random variable follows a normal distribution with a mean of 0 and a standard deviation of σ ζ is 1, which is used to capture the random part of the latent variable;

[0027] Capturing the relationship between latent variables and measurement indicators, the measurement indicators are the answers to the user's travel attitude questions. The relationship between latent variables and measurement indicators is expressed as:

[0028]

[0029]

[0030] In the formula, represents a continuous latent variable for respondent n for the sth question; γ s,c and γ s,m Respectively represent the corresponding intercept and coefficient; ν s,n represents a random variable, which is assumed to be normally distributed with a mean of 0 and a standard deviation of σ s I s,n represents the answer to the sth question of the nth traveler, j s,i represents the i-th answer value in the s-th question, τ s,i Indicates that it corresponds to j s,i The critical value of τ s,i ≥τ s,i-1 ;

[0031] The utility function is constructed using the latent classification method. User n belongs to different user types to different degrees. The utility U of selecting option c is n,c for:

[0032] In the formula, π nq is the membership of user n to the qth group of people, and is calculated as follows:

[0033]

[0034] In the formula, z n Represents the vector composed of personal attribute factors; γ q represents the unknown coefficient vector; δ q is a fixed item for classification; Q is the number of user types;

[0035] V c,q The utility gained by selecting option c for the qth user is calculated as:

[0036] V c,q =β0+β s,q z s +β t,q z t

[0037] In the formula, β0 is the selected fixed term, β s,q is the characteristic parameter vector of the variables related to the qth user and the point of interest, z s is the vector composed of the attribute factors of the point of interest, β t,q is the characteristic parameter vector of the traffic-related variables of the qth type of user, z t is a vector composed of traffic attribute factors. In particular, the influence of weather factors is reflected in the attribute factors of points of interest and traffic attribute factors, and there is a cross-influence of weather attributes on points of interest and traffic attributes;

[0038] Based on the existing users' travel records, willingness surveys and personal attribute information, the maximum likelihood method is used to determine the values ​​of parameters β and γ that can maximize the selection probability of all known users.

[0039] Utility function U n,c That is, it is the travel preference of user n for point of interest c and the mode of transportation to point of interest c, which includes the attribute factors of point of interest, traffic attribute factors and weather factors, and reflects the user's preference information for each attribute factor through the feature parameter vector.

[0040] Preferably, the arrangement of the sequence of tourist points of interest and the modes of transportation between the points of interest in combination with the user's travel needs, the tourist travel static database and the user's travel preferences to generate an integrated tourist travel planning scheme includes:

[0041] Set the objective function to:

[0042]

[0043]

[0044]

[0045] Among them, i represents the starting point of interest, j represents the end point of interest, m represents the mode of transportation, and k represents the influencing factor; N represents the set of points of interest; M represents the set of transportation modes; K represents the set of influencing factors;

[0046] Z is the objective function, which represents the overall utility of tourism travel and is composed of the utility of each single trip; is the decision variable, indicating whether the point of interest and transportation mode are selected or not;

[0047] represents the utility of taking transportation mode m from point of interest i to point of interest j and staying at point of interest j, that is, the utility of a single trip, which is obtained by the user's travel preference; β k is the characteristic parameter of factor k; is the characteristic attribute of interest point j and its arrival mode m;

[0048] Combined with the actual situation of travel and the restrictions in user requests, the path constraints of the dynamic time window are established, including the following types of constraints:

[0049] Point of interest constraints: Based on the VRP model, the path constraints of tourists’ tour routes in dynamic time windows are established to ensure that users do not repeatedly pass through optional points of interest and return to the starting point without special requirements;

[0050] The one-time constraint requires that each optional point of interest, except for the starting and ending points, can be visited at most once. For any point of interest j, all points of interest i can only be reached by one mode of transportation. The calculation method is as follows:

[0051]

[0052] When the starting point and the ending point are the same, the closed loop constraint is calculated as follows:

[0053]

[0054] If the user requests to go to a specified point of interest j, all points of interest i must be reachable by one mode of transportation, and the calculation method of the point of interest constraint is as follows:

[0055]

[0056] When the travel mode required in the user request has transportation restrictions or requires the use of special transportation, the corresponding transportation mode M set is constructed;

[0057] Time window constraint: When When , the point of interest j is determined by the start time and service time of the point of interest i. Under the dynamic time window, the service time and the travel time are real-time times that take into account queuing, congestion, and control. The next point of interest is determined by the start time, stay time, and travel time of the previous point of interest. The calculation method is as follows:

[0058]

[0059]

[0060] In the formula, t i is the arrival time of point of interest i; svt i is the normal stay time of point of interest i, obtained according to the recommended stay time and user travel preference of the point of interest; wt i (t i ) is the additional time caused by special circumstances at point of interest i, is the travel time from point of interest i to point of interest j. The travel time changes with the road conditions, reflecting the dynamic nature of the travel time. B is a positive number to control whether the journey from point of interest i to point of interest j exists.

[0061] Time constraints and cost constraints: The total duration is calculated based on the time window and cannot exceed the preset time limit requested by the user; the total cost is calculated based on points of interest and transportation methods and cannot exceed the preset cost limit requested by the user.

[0062]

[0063]

[0064] In the formula, the total time consumed is the basic stay time svt of each point of interest i , waiting time wt i (t i ) and travel time between points of interest The total cost of the day is paid by the point of interest C i and transportation expenses The two parts together constitute.

[0065] The solution that maximizes the objective function is obtained as the recommended solution. The solution result includes the selection of travel points of interest, the sequence arrangement and the arrangement results of travel modes, and outputs an integrated planning scheme for points of interest and transportation modes. The planning scheme includes an integrated planning scheme for point of interest selection, point of interest sequence and transportation modes between points of interest.

[0066] Preferably, the objective function considers the attributes of points of interest and the attributes of transportation modes as influencing factors, and the weights of the influencing factors are obtained from the user's travel preferences.

[0067] It can be seen from the technical solutions provided by the above-mentioned embodiments of the present invention that the present invention analyzes the user's travel preferences, fully considers the attributes of each point of interest during travel and the traffic attributes between the points of interest, and provides users with an integrated customized travel plan that meets their personalized needs, including point of interest recommendations, tour sequence arrangements, travel modes and route planning.

[0068] Additional aspects and advantages of the present invention will be given in part in the following description, which will become obvious from the following description, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0070] Figure 1 A processing flow chart of a method for integrated travel planning taking into account user travel needs and preferences provided by an embodiment of the present invention;

[0071] Figure 2 A user preference modeling model architecture diagram of a travel integrated planning method that takes into account user travel needs and preferences provided in an embodiment of the present invention.

[0072] Figure 3 A user travel latent variable measurement index system for a tourism travel integrated planning method taking into account user travel needs and preferences is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0073] The embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be interpreted as limiting the present invention.

[0074] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, the "connection" or "coupling" used herein may include wireless connection or coupling. The term "and / or" used herein includes any unit and all combinations of one or more associated listed items.

[0075] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art in the art to which the present invention belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless defined as herein.

[0076] To facilitate understanding of the embodiments of the present invention, several specific embodiments will be further explained below with reference to the accompanying drawings, and each embodiment does not constitute a limitation on the embodiments of the present invention.

[0077] The processing flow of a travel integrated planning method considering user travel needs and preferences disclosed in an embodiment of the present invention is as follows: Figure 1 As shown, the processing steps include the following:

[0078] Step S1: Obtain user travel needs and build a static database of travel activities.

[0079] S11: Obtain user travel needs.

[0080] The user initiates a travel planning request to the system, in which the user provides the travel destination (single city, multiple surrounding areas), travel duration (half-day tour, one-day tour, multi-day tour), travel time and travel budget. Optionally, the user specifies the intended location and travel method, such as specifying the accommodation location and must-see attractions, and specifying that the travel method is self-driving.

[0081] S12: Build a static travel database.

[0082] Acquire the attributes of tourist points of interest, which include the type of point of interest, location, opening hours, consumption price and the attributes of the environment that can reflect the characteristics of the point of interest. Collect information on each tourist point of interest at the destination, collect the categories of each attraction (natural scenery, scenic spots, museums, parks, large business districts, special street fairs, religious temple fairs, architectural humanities), scenic area level (1-5A), attraction evaluation value, popularity (number of searches, popularity of play), ticket price information, opening hours, recommended play time; collect the location, type, evaluation and per capita consumption of restaurants around the scenic spot; collect the location, price and evaluation of each hotel at the destination to form a comprehensive point of interest set as a set of alternative points of interest for the destination. Preferably, the attributes of the point of interest are obtained by integrating network information resources of travel, travel strategies and map navigation.

[0083] Obtain the attributes of transportation, including the basic travel time, basic travel cost, number of transfers, walking distance, departure frequency, waiting time, reliability, comfort, public transportation information around the points of interest, and supporting parking spaces of the optional transportation modes between the points of interest. The basic travel time and basic travel cost are the travel time and travel cost without considering congestion and queuing.

[0084] S13: Obtain travel dynamic information.

[0085] Obtain dynamic information of points of interest. The dynamic information of points of interest is the real-time status of points of interest, which can reflect the attractiveness of points of interest at different time periods. Preferably, the dynamic information of points of interest includes real-time congestion (small flow of people, moderate flow of people, large flow of people), queue waiting time, flow control measures, temporary closure, special activities and discount promotion dynamic information. Preferably, the dynamic information of points of interest is obtained by collecting real-time information publicly released by points of interest, and the dynamic information of points of interest is obtained by cooperating with points of interest.

[0086] Obtain traffic dynamic information. The traffic dynamic information is the traffic conditions between points of interest. Due to the influence of travel time and accidental accidents, congestion may occur, affecting the travel experience. Preferably, the traffic dynamic information includes temporary traffic control, future travel time prediction, waiting time of transportation methods, and travel cost fluctuations. Preferably, the traffic dynamic information between points of interest is obtained through the map navigation API interface, and the real-time traffic travel plan is obtained, so as to avoid the control area, avoid congested routes and congested periods.

[0087] Obtain the weather conditions on the travel date. Preferably, the weather conditions include high temperature, rain, snow and haze conditions at different times.

[0088] The attributes of the tourist interest points, the attributes of the traffic between the tourist interest points, the dynamic information of the interest points and the traffic, and the real-time weather conditions are combined into a tourist travel static database.

[0089] Step S2: Extract user travel preferences based on user information and travel behavior model. Construct a travel behavior model, and calculate and quantify the user's preference for different attributes of tourist attractions and transportation methods during travel through user information as the user's travel preferences.

[0090] S21: Obtain user travel information. When registering, users fill out a travel questionnaire to obtain personal attributes, travel records, and travel intentions. Obtain the user's personal attributes, including age, gender, occupation, monthly income, and number of trips per year. Optionally, the user fills in a travel record for the past year, including the attractions visited, transportation methods, accommodation types, and travel expenses; the user fills in a travel intention survey: the user selects the most desired travel option from the set attractions and transportation methods.

[0091] S22: Figure 2 A user preference modeling model architecture diagram of a travel integrated planning method considering user travel needs and preferences provided by an embodiment of the present invention, such as Figure 2 As shown, in the method for extracting user preferences, the present invention provides a behavior modeling method that can identify and quantify factors that affect user selection behavior, and is a modeling method commonly used in behavioral science.

[0092] S221: Determine influencing factors. Consider the influencing factors that affect the user's travel, further including: the attributes of the points of interest and the attributes of traffic in S12, the dynamic information of the points of interest, traffic and weather in S13, and the user's travel information in S21. The user's personal attributes include age, gender, occupation, monthly income and number of trips per year. The above influencing factors act on the utility function of S222.

[0093] Construct tourism travel latent variables to characterize the influence of users' travel attitudes.

[0094] Construct travel latent variable α n It is used to express the travel preference that is difficult to be directly observed in tourism travel. The calculation formula of the latent variable is:

[0095] α n =γ a z n +ζ n ,ζ n ~N(0,σ ζ )

[0096] In the formula, z n Represents the vector of personal attribute variables of user n; γ a represents the unknown coefficient vector; ζ n represents a random variable, assuming that the random variable follows a normal distribution with a mean of 0 and a standard deviation of σζ is 1 to capture the random part of the latent variable.

[0097] like Figure 3 ,In the implementation case, six latent variables are taken as the tour time, tour economy, attraction specificity, attraction recommendation, travel experience and environmental awareness.

[0098] Capture the relationship between latent variables and measurement indicators, where the measurement indicators are the answers to questions about users' travel attitudes. In the implementation case, 23 attitude-related questions were designed to correspond to the above 6 latent variables, all of which were asked in a 5-level scale. To avoid nonlinearity in the answer results, a sequential logit model was used to describe them.

[0099] The relationship between latent variables and measurement indicators is expressed as:

[0100]

[0101]

[0102] In the formula, represents a continuous latent variable for respondent n for the sth question; γ s,c and γ s,m Respectively represent the corresponding intercept and coefficient; ν s,n represents a random variable, which is assumed to be normally distributed with a mean of 0 and a standard deviation of σ s I s,n represents the answer to the sth question of the nth traveler, j s,i represents the i-th answer value in the s-th question, τ s,i Indicates that it corresponds to j s,i The critical value of τ s,i ≥τ s,i-1 .

[0103] The measurement results of 6 latent variables and personal attribute variables are obtained through 23 measurement indicators. As the user's travel attitude, the latent variables and personal attribute variables are used together in the construction of the utility function.

[0104] S222: Construct utility function. Different types of users have different decision-making patterns in travel. Considering the heterogeneity of users, the utility function is constructed using the latent classification method. User n belongs to different user types to different degrees, so the utility U of selecting option c is n,c for:

[0105]

[0106] In the formula, π nq is the membership of user n to the qth group of people, and is calculated as follows:

[0107]

[0108] In the formula, z n Represents the vector composed of personal attribute factors; γ q represents the unknown coefficient vector; δ q is a fixed item for classification; Q is the number of user types;

[0109] V c,q The utility gained by selecting option c for the qth user is calculated as:

[0110] V c,q =β0+β s,q z s +β t,q z t

[0111] In the formula, β0 is the selected fixed term, β s,q is the characteristic parameter vector of the variables related to the qth user and the point of interest, z s is the vector composed of the attribute factors of the point of interest, β t,q is the characteristic parameter vector of the traffic-related variables of the qth type of user, z t is a vector composed of traffic attribute factors. In particular, the influence of weather factors is reflected in the attribute factors of points of interest and traffic attribute factors, and there is a cross-influence of weather attributes on points of interest and traffic attributes;

[0112] Preferably, some of the points of interest and traffic attribute variables change with changes in the external environment, and the values ​​taken in different time periods are different.

[0113] S223: Based on the existing users' travel records, willingness surveys and personal attribute information, the maximum likelihood method is used to determine the values ​​of the parameters β and γ when the selection probability of all known users is maximized;

[0114] Utility function U n,c That is, the user n's travel preference for the point of interest c and the mode of transportation to the point of interest c, including the attribute factors of the point of interest, the attribute factors of transportation and the weather factors, and the user's preference information for each attribute factor is reflected through the characteristic parameter vector. The utility function is used to calculate the travel objective function in S31.

[0115] S23: Extract and regularly update user preferences based on user travel information.

[0116] S231: For first-time users, the travel behavior model is applied according to the user travel information filled in during registration to obtain quantified travel user preferences.

[0117] S232: On a monthly basis, the calibration results of the travel behavior model for the user are updated through the user's usage records, and the user preferences are updated.

[0118] Step S3: Travel plan planning.

[0119] Considering the static data of tourism travel and user travel preferences, taking into account the selection of points of interest and the transportation arrangements between points of interest, the selection of user points of interest, the order of play and the mode of transportation are integrated to build a tourism and transportation integrated travel plan. The integrated tourism travel planning further includes the following steps:

[0120] S31: Setting an objective function, taking into account factors from multiple aspects including points of interest, traffic, weather and user personal factors in S1 and S2, the objective function is:

[0121]

[0122]

[0123]

[0124] Among them, i represents the starting point of interest, j represents the end point of interest, m represents the mode of transportation, and k represents the influencing factor; N represents the set of points of interest; M represents the set of transportation modes; and K represents the set of influencing factors.

[0125] Z is the objective function, which represents the overall utility of tourism travel and is composed of the utility of each single trip; is a decision variable, indicating whether the point of interest and transportation mode are selected or not.

[0126] β represents the utility of taking transportation mode m from point of interest i to point of interest j and staying at point of interest j, that is, the utility of a single trip, which is obtained from the travel preference of user S2; k is the characteristic parameter of factor k; is the characteristic attribute of interest point j and its arrival mode m.

[0127] S32: Generate constraints, combine the actual situation of travel and the restrictions in the user's request, and establish path constraints for the dynamic time window, which further include:

[0128] S321: Point of interest constraints, based on the VRP (Vehicle Route Problem) model, establish path constraints for tourist tour routes in dynamic time windows to ensure that users do not pass through optional points of interest repeatedly and return to the starting point without special requirements.

[0129] The one-time constraint requires that each optional point of interest (except the starting and ending points) can be visited at most once. For any point of interest j, all points of interest i can only be reached by one mode of transportation. The calculation method is as follows:

[0130]

[0131] Preferably, the closed loop constraint is omitted if the departure location and the end location are not the same location. When the departure location and the end location are the same location, the travel plan is guaranteed to be a closed loop. The constraint calculation method is as follows:

[0132]

[0133] Optionally, specify a point of interest constraint. If the user requests to go to a specific point of interest j, all points of interest i must be reachable by one mode of transportation. The calculation method is as follows:

[0134]

[0135] Optionally, for a specified mode of transportation, if the travel mode requested in the user request has transportation restrictions or requires the use of special transportation, a corresponding set of transportation modes M is constructed.

[0136] S322: Time window constraint. When , the point of interest j is determined by the start time, service time and travel time of the point of interest i. Under the dynamic time window, the service time and travel time are real-time times that take into account queuing, congestion and control, and can cope with delays and emergencies. The next point of interest is determined by the start time, stay time and travel time of the previous point of interest, and is calculated as follows:

[0137]

[0138]

[0139] In the formula, t i is the arrival time of point of interest i; svt i is the normal stay time of point of interest i, obtained according to the recommended stay time and user travel preference of the point of interest; wt i (t i ) is the additional time caused by special circumstances at point of interest i, such as crowded queues and flow restrictions; is the travel time from point of interest i to point of interest j. The travel time changes with the road conditions, reflecting the dynamic nature of the travel time. B is a large positive number to control whether the journey from point of interest i to point of interest j exists.

[0140] S323: Time constraints and cost constraints. The total time is calculated based on the time window, which cannot exceed the preset time limit requested by the user; the total cost is calculated based on the points of interest and transportation methods, which cannot exceed the preset cost limit requested by the user.

[0141]

[0142]

[0143] In the formula, the total time consumed is the basic stay time svt of each point of interest i , waiting time wt i (t i ) and travel time between points of interest The total cost of the day is paid by the point of interest C i and transportation expenses The two parts together constitute.

[0144] S33: Form a plan. Solve to obtain the solution that maximizes the objective function and other larger feasible solutions as recommended solutions. The solution results include the selection of travel points of interest, the sequence arrangement and the arrangement results of travel modes, and output an integrated planning plan for points of interest and transportation modes. The planning plan includes the selection of points of interest, the sequence of points of interest and the integrated planning plan for transportation modes between points of interest. Feedback the recommended plan to the user, who determines the final travel plan and saves the selection result in the user's travel information record.

[0145] Preferably, the planning scheme can be used in travel reservations. According to the sequence and time arrangement of the points of interest in the planning scheme, travel reservations can be made, further reducing users' unnecessary waiting time and improving the quality of travel services.

[0146] In summary, the integrated travel planning scheme generated by the method of the embodiment of the present invention can be applied to travel reservations to provide users with integrated travel services. The present invention targets the growing personalized travel needs, on the one hand, taking into account the convenience of user travel as a service, and on the other hand, taking into account the carrying capacity of scenic spots and road networks, guiding tourists, alleviating tourism congestion problems and promoting the integrated development of the tourism and transportation industries.

[0147] Those skilled in the art can understand that the accompanying drawings are only schematic diagrams of an embodiment, and the modules or processes in the accompanying drawings are not necessarily required to implement the present invention.

[0148] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present invention can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present invention or certain parts of the embodiments.

[0149] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0150] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A travel planning method that takes into account user travel needs and preferences, characterized in that: include: Obtain user travel needs and build a static database of travel activities; Extract user travel preferences based on user travel information and travel behavior models; Arrange the sequence of tourist points of interest and the modes of transportation between the points of interest in combination with the user's travel needs, the tourist travel static database and the user's travel preferences, and generate an integrated travel planning scheme; The extracting of user travel preferences based on user travel information and travel behavior model includes: Acquire user travel information by having the user fill out a travel questionnaire when registering, the user travel information including personal attributes, travel records and travel intentions, construct a travel behavior model for the user, calculate and quantify the user's preference for tourist interest points and transportation methods with different attributes during travel based on the user travel information using the travel behavior model, and use the user's preference for tourist interest points and transportation methods with different attributes as the user's travel preference; Updating the user travel preferences at set time intervals; The construction of the user's travel behavior model includes: Determine the factors that affect the user's travel, which include points of interest attributes, transportation attributes, weather factors and user personal attributes, and the user personal attributes include age, gender, occupation, monthly income and annual travel times; Construct the latent variable of user travel, the latent variable α n It represents the travel preference that is difficult to be directly observed in tourism travel. The calculation formula of the latent variable is: a n =c a z n +g n ,g n ~N(0,σ ζ ) In the formula, z n Represents the vector of personal attribute variables of user n; γ a represents the unknown coefficient vector; ζ n represents a random variable, assuming that the random variable follows a normal distribution with a mean of 0 and a standard deviation of σ ζ is 1, which is used to capture the random part of the latent variable; Capturing the relationship between latent variables and measurement indicators, the measurement indicators are the answers to the user's travel attitude questions. The relationship between latent variables and measurement indicators is expressed as: In the formula, represents a continuous latent variable for respondent n for the sth question; γ s,c and γ s,m Respectively represent the corresponding intercept and coefficient; ν s,n represents a random variable, which is assumed to be normally distributed with a mean of 0 and a standard deviation of σ s , I s,n represents the answer to the sth question of the nth traveler, j s,i represents the i-th answer value in the s-th question, τ s,i Indicates that it corresponds to j s,i The critical value of τ s,i ≥τ s,i-1 ; The utility function is constructed using the latent classification method. User n belongs to different user types to different degrees. The utility U of selecting option c is n,c for: In the formula, π nq is the membership of user n to the qth group of people, and is calculated as follows: In the formula, z n Represents the vector composed of personal attribute factors; γ q represents the unknown coefficient vector; δ q is a fixed item for classification; Q is the number of user types; V c,q The utility gained by selecting option c for the qth user is calculated as: V c,q =β0+β s,q z s +β t,q z t In the formula, β0 is the selected fixed term, β s,q is the characteristic parameter vector of the variables related to the qth user and the point of interest, z s is the vector composed of the attribute factors of the point of interest, β t,q is the characteristic parameter vector of the traffic-related variables of the qth type of user, z t is a vector composed of traffic attribute factors. In particular, the influence of weather factors is reflected in the attribute factors of points of interest and traffic attribute factors. There is a cross-influence of weather attributes, points of interest and traffic attributes. Based on the existing users' travel records, willingness surveys and personal attribute information, the maximum likelihood method is used to determine the values ​​of parameters β and γ that can maximize the selection probability of all known users. Utility function U n,c That is, user n's travel preference for point of interest c and the mode of transportation to point of interest c, which includes the attribute factors of the point of interest, the attribute factors of transportation and the weather factors. The characteristic parameter vector reflects the user's preference information for each attribute factor. The arrangement of the sequence of tourist points of interest and the modes of transportation between the points of interest by combining the user's travel needs, the tourist travel static database and the user's travel preferences to generate an integrated tourist travel planning scheme includes: Set the objective function to: Among them, i represents the starting point of interest, j represents the end point of interest, m represents the mode of transportation, and k represents the influencing factor; N represents the set of points of interest; M represents the set of transportation modes; K represents the set of influencing factors; Z is the objective function, which represents the overall utility of tourism travel and is composed of the utility of each single trip; is the decision variable, indicating whether the point of interest and transportation mode are selected or not; represents the utility of taking transportation mode m from point of interest i to point of interest j and staying at point of interest j, that is, the utility of a single trip, which is obtained by the user's travel preference; β k is the characteristic parameter of factor k; is the characteristic attribute of interest point j and its arrival mode m; Combined with the actual situation of travel and the restrictions in user requests, the path constraints of the dynamic time window are established, including the following types of constraints: Point of interest constraints: Based on the VRP model, the path constraints of tourists’ tour routes in dynamic time windows are established to ensure that users do not repeatedly pass through optional points of interest and return to the starting point without special requirements; The one-time constraint requires that each optional point of interest, except for the starting and ending points, can be visited at most once. For any point of interest j, all points of interest i can only be reached by one mode of transportation. The calculation method is as follows: When the starting point and the ending point are the same, the closed loop constraint is calculated as follows: If the user requests to go to a specified point of interest j, all points of interest i must be reachable by one mode of transportation, and the calculation method of the point of interest constraint is as follows: When the travel mode required in the user request has transportation restrictions or requires the use of special transportation, the corresponding transportation mode M set is constructed; Time window constraint: When When , the point of interest j is determined by the start time and service time of the point of interest i. Under the dynamic time window, the service time and the travel time are real-time times that take into account queuing, congestion, and control. The next point of interest is determined by the start time, stay time, and travel time of the previous point of interest. The calculation method is as follows: Where, t i is the arrival time of point of interest i; svt i is the normal stay time of point of interest i, obtained according to the recommended stay time and user travel preference of the point of interest; wt i (t i ) is the additional time caused by special circumstances at point of interest i, is the travel time from point of interest i to point of interest j. The travel time changes with the road conditions, reflecting the dynamic nature of the travel time. B is a positive number to control whether the journey from point of interest i to point of interest j exists. Time constraints and cost constraints: The total time is calculated based on the time window, which cannot exceed the preset time limit requested by the user; the total cost is calculated based on the points of interest and transportation methods, which cannot exceed the preset cost limit requested by the user; In the formula, the total time consumed is the basic stay time svt of each point of interest i , waiting time wt i (t i ) and travel time between points of interest The total cost of the day is paid by the point of interest C i and transportation expenses The two parts together constitute; The solution that maximizes the objective function is obtained as the recommended solution. The solution result includes the selection of travel points of interest, the sequence arrangement and the arrangement results of travel modes, and outputs an integrated planning scheme for points of interest and transportation modes. The planning scheme includes an integrated planning scheme for point of interest selection, point of interest sequence and transportation modes between points of interest.

2. The method according to claim 1, characterized in that: The method of obtaining user travel needs and building a static database of travel activities includes: Acquire user travel needs, which include travel destination, travel duration, travel time and travel budget; Collect information about tourist points of interest at the user's travel destination, including the category, grade, ticket price, opening hours and recommended travel time of each attraction; the location, type, rating and per capita consumption of restaurants around the attraction; the location, price and rating of each hotel, and form a comprehensive set of tourist points of interest; Obtaining the information on the attributes of transportation between the tourist points of interest in the comprehensive points of interest, including traffic dynamic information, travel time, travel cost, number of transfers, walking distance, departure frequency, waiting time, reliability, comfort, public transportation information around the points of interest, and supporting parking spaces; Acquire dynamic information of tourist interest points in the comprehensive interest points, wherein the dynamic information of interest points is the real-time status of the interest points, and can reflect the attractiveness of the interest points at different time periods; Get the weather conditions on the travel date; The attributes of the tourist interest points, the attributes of the traffic between the tourist interest points, the dynamic information of the interest points and the traffic, and the real-time weather conditions are combined into a tourist travel static database.

3. The method according to claim 1, characterized in that: The objective function considers the attributes of points of interest and the attributes of transportation modes as influencing factors, and the weights of the influencing factors are obtained from the user's travel preferences.

Images