Travel planning method and device, electronic equipment and computer program product

Abstract

The invention provides a travel planning method and device, electronic equipment and a computer program product, and the method can obtain travel portrait data of a user, the travel portrait data at least comprises travel demand data, travel preference data, historical browsing data and current travel state data of the user, and the travel demand data and the travel preference data of the user are acquired according to the travel portrait data. And performing feasibility evaluation on each selectable scenic spot, and selecting a target scenic spot from the scenic spots interested by the user as the scenic spot recommended to the user according to the feasibility evaluation result of each selectable scenic spot. In this way, scenic spots meeting user preferences can be recommended to the user at least according to the travel demand data, the travel preference data, the historical browsing data and the current travel state data of the user, so that the user does not need to perform travel planning personally, time and energy are saved, and personalized travel planning meeting own preferences can be obtained.

Description

Technical Field

[0001] The present application relates to the technical field of travel planning, and in particular to a travel planning method, device, electronic device and computer program product. Background Art

[0002] As the pace of life accelerates, people increasingly hope to directly obtain personalized travel plans that meet their needs in order to save time and energy. Therefore, how to accurately carry out personalized travel planning for users has become a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0003] In view of this, the present application proposes a travel planning method, device, electronic device and computer program product, which can accurately carry out personalized travel planning for users.

[0004] The technical solutions proposed in this application are as follows:

[0005] In a first aspect, an embodiment of the present application provides a travel planning method, comprising:

[0006] Acquire the user's travel portrait data; the travel portrait data at least includes the user's travel demand data, travel preference data, historical browsing data and current travel status data;

[0007] Conduct feasibility evaluation on each optional scenic spot based on the travel portrait data;

[0008] According to the feasibility evaluation results of the optional scenic spots, a target scenic spot is selected from the scenic spots that the user is interested in as a scenic spot recommended to the user.

[0009] In a second aspect, an embodiment of the present application provides a travel planning device, comprising:

[0010] An acquisition module, used to acquire the user's travel portrait data; the travel portrait data at least includes the user's travel demand data, travel preference data, historical browsing data and current travel status data;

[0011] An evaluation module, used to evaluate the feasibility of each optional scenic spot based on the travel portrait data;

[0012] The selection module is used to select a target attraction from the attractions that the user is interested in as an attraction recommended to the user according to the feasibility evaluation results of the optional attractions.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0014] A memory and a processor; wherein the memory is used to store programs; and the processor is used to implement any of the methods described above by running the programs in the memory.

[0015] In a fourth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a computer program or computer instructions, and when the computer program or computer instructions are executed by a processor, any of the methods described above is implemented.

[0016] The travel planning method proposed in the present application can obtain the user's travel portrait data, wherein the travel portrait data at least includes the user's travel demand data, travel preference data, historical browsing data and current travel status data. According to the travel portrait data, the feasibility of each optional scenic spot is evaluated, and then according to the feasibility evaluation results of each optional scenic spot, the target scenic spot is selected from the scenic spots that the user is interested in as the scenic spot recommended to the user. In this way, the scenic spots that meet the user's preferences can be recommended to the user at least based on the user's travel demand data, travel preference data, historical browsing data and current travel status data. In this way, the user does not have to plan the travel personally, which not only saves time and energy, but also can obtain a personalized travel plan that meets their own preferences. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0018] Figure 1 It is a schematic diagram of a feasible application scenario of a travel planning method provided in an embodiment of the present application.

[0019] Figure 2 It is a flowchart of a travel planning method provided in an embodiment of the present application.

[0020] Figure 3 This is a flow chart of scenic spot recommendation provided in an embodiment of the present application.

[0021] Figure 4 It is a schematic diagram of a preset strategy provided in an embodiment of the present application.

[0022] Figure 5 It is a structural schematic diagram of a travel planning device provided in an embodiment of the present application.

[0023] Figure 6 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0025] With the development of tourism, people's demand for personalized travel is growing. At the same time, with the accelerated pace of life, people no longer want to waste their time and energy on travel strategies and selecting suitable attractions. Instead, they hope to directly obtain personalized travel plans that meet their travel needs and get recommended attractions after entering their travel needs. Therefore, in modern tourism planning, how to accurately provide users with personalized travel plans has become a key challenge to improve user experience.

[0026] Based on this, the present application proposes a travel planning method, device, electronic device and computer program product. The technical solution recommends attractions that meet the user's preferences based on at least the user's travel demand data, travel preference data, historical browsing data and current travel status data. In this way, the user does not have to plan the travel personally, which not only saves time and energy, but also allows the user to obtain a personalized travel plan that meets their own preferences.

[0027] Figure 1 The feasible application scenarios of the travel planning method are shown, such as Figure 1 In the scenario shown, a client and a server are set up.

[0028] The client can be an electronic device with network access capability. Specifically, for example, the client can be a desktop computer, a tablet computer, a laptop computer, a smart phone, a digital assistant, a smart wearable device, a shopping guide terminal, a television, etc. Among them, the smart wearable device includes but is not limited to a smart bracelet, a smart watch, a smart glasses, a smart helmet, a smart necklace, etc. Alternatively, the client can also be software that can run in an electronic device.

[0029] The server can be an electronic device with certain computing and processing capabilities. It can have a network communication module, a processor, and a memory, etc. Of course, the server can also refer to software running in an electronic device. The server can also be a distributed server, which can be a system with multiple processors, memories, network communication modules, etc. operating in collaboration. Alternatively, the server can also be a server cluster formed by several servers. Alternatively, with the development of science and technology, the server can also be a new technical means that can realize the corresponding functions of the implementation method of the specification. For example, it can be a new form of "server" based on quantum computing.

[0030] The client and the server can communicate through the target network. The target network can be any type of network. For example, the target network can be a network that can be subdivided into multiple subnetworks. The target network or the multiple subnetworks contained in the target network can be at least one of a cellular mobile network (such as 2G, 3G, 4G or 5G), ZIGBEE, WIFI, Bluetooth, or any combination of at least one of these networks and other networks.

[0031] In the above feasible application scenario, the client obtains the user's travel portrait data and sends the travel portrait data to the server. After the server obtains the travel portrait data, it evaluates the feasibility of each optional scenic spot based on the travel portrait data, and selects the target scenic spot from the scenic spots that the user is interested in as the recommended scenic spot to the user based on the feasibility evaluation results of each optional scenic spot. The server sends the target scenic spot to the client, and the client displays the target scenic spot to the user. With this setting, the user does not need to plan the travel personally, which not only saves time and energy, but also allows the user to obtain a personalized travel plan that meets their own preferences.

[0032] Furthermore, an exemplary embodiment of the present specification provides a travel planning method, which is described by taking the method applied to an electronic device as an example. The electronic device may be a device having communication and computing functions such as the server in the above embodiment. Figure 2 As shown, the method includes:

[0033] S101. Obtain user's travel profile data.

[0034] The above-mentioned travel portrait data refers to data that can reflect the user's travel habits and preferences. In this embodiment, the travel portrait data at least includes the user's travel demand data, travel preference data, historical browsing data and current travel status data.

[0035] More specifically, the user's travel demand data refers to the demand information input by the user. The demand can be a scenery type, such as the seaside, mountainous area, historical ancient city, amusement park, etc., or a travel destination, such as Mount Tai, Dongting Lake, Mogao Grottoes, etc., or a travel purpose, such as relaxing, shopping, learning about history and culture, eating delicious food, watching the aurora, etc., which is not limited in this embodiment.

[0036] Travel preference data refers to data that describes a user's travel tendencies. User travel tendencies may be tendencies regarding any aspect of travel, for example, a user may prefer a time-saving travel route, a user may prefer a less expensive travel route, a user may prefer to appreciate the scenery, a user may prefer to go to places with fewer people, etc. This embodiment does not make any specific limitations. It should be noted that travel preference data may be input by a user, or may be obtained by analyzing a user's historical travel records, travel-related web pages, applications (Application, APP) and other browsing records, and this embodiment does not make any specific limitations.

[0037] Historical browsing data refers to the user's browsing records related to travel, such as browsing records on travel-related websites and apps, browsing records on rating websites and apps, search records on travel ticket purchasing websites and apps, and search records on navigation apps, etc., which are not limited in this embodiment.

[0038] Current travel status data refers to data that can characterize the user's current travel status, such as the current time, current location, current attractions, current fatigue level, historical driving habits, current environmental factors, current emotional state, etc. It should be noted that physiological indicators such as the user's heart rate, blood pressure, and skin galvanic response can be collected through smart watches or health trackers to estimate the user's current fatigue level; the user's current emotional state can be judged using a mobile phone camera or other devices with facial recognition technology.

[0039] Based on the data of current travel status such as current time, current location, current attractions, current fatigue level, historical driving habits, current environmental factors, current emotional state, etc., the user's actual travel status and then the user's current travel preferences and needs can be determined. For example, the current time can assist in reasoning and judging suitable activities for the user, such as recommending lively downtown areas or night-specific activities at night; taking into account the convenience of transportation, attractions near the current location can be recommended based on the geographical location; based on the current attractions, repeated recommendations can be avoided and new attraction options can be provided; the current fatigue level is used to estimate the stress level and fatigue level of tourists; machine learning analysis of driving behavior is performed based on historical driving habits to estimate the user's possible travel preferences, such as preference for time-saving routes or scenic routes; environmental factors include weather and real-time traffic information, which can assist in reasoning and judging the user's appropriate clothing and transportation methods; positive and active current emotional states may indicate that the user enjoys the current activity, and attractions can continue to be recommended to the user, while negative current emotional states may indicate fatigue or dissatisfaction, and labor-saving attractions can be recommended to the user or the user may be advised to rest.

[0040] In this embodiment, the above-mentioned travel portrait data is obtained.

[0041] S102. Conduct feasibility evaluation on each optional scenic spot based on the travel portrait data.

[0042] Each optional scenic spot refers to all scenic spots that the user can currently select. In some embodiments, the optional scenic spots can be determined based on the user's travel profile data. For example, if the user is before the start of the trip, one or more cities that the user wants to go to can be determined based on the user's travel profile data, and all scenic spots in the one or more cities can be determined as optional scenic spots. If the user is in the process of traveling, all scenic spots that the user has not browsed and are within a preset distance range from the user's current location can be determined as optional scenic spots; in addition, if the user is in the process of traveling, all scenic spots that have not been browsed among all scenic spots determined before the start of the trip can also be determined as optional scenic spots.

[0043] Not all optional attractions meet the user's preferences and needs, so it is necessary to conduct a feasibility evaluation on the optional attractions, and recommend attractions to the user based on the feasibility evaluation results of each optional attraction. In some embodiments, a feasibility evaluation model is pre-trained, and the feasibility evaluation model is used to evaluate the feasibility of each optional attraction.

[0044] The training process of the feasibility evaluation model is as follows: obtain the travel portrait data of a large number of sample users, and for any sample user, use the travel portrait data corresponding to the sample user and the optional attractions of the sample user as training samples, wherein the optional attractions of the sample user refer to all attractions in the area where the attractions browsed by the sample user are located, mark the attractions browsed by the sample user as 1, and mark the attractions not browsed by the sample user as 0, and use the training samples to train the feasibility evaluation model so that the feasibility evaluation model has the ability to evaluate the feasibility of the optional attractions. The above-mentioned feasibility evaluation model can be obtained by training based on any neural network model, or based on training based on a pre-trained model, such as a pre-trained large model similar to ChatGPT.

[0045] The travel profile data and all optional attractions in this embodiment are input into the trained feasibility evaluation model to obtain the feasibility evaluation results for each optional attraction output by the feasibility evaluation model. The closer the feasibility evaluation result of any optional attraction is to 1, the higher the feasibility of the optional attraction.

[0046] S103: According to the feasibility evaluation results of each optional scenic spot, a target scenic spot is selected from the scenic spots that the user is interested in as a scenic spot recommended to the user.

[0047] The above-mentioned attractions of interest to the user refer to the attractions that are presumed to be of interest to the user among all the optional attractions. In some embodiments, after the optional attractions are determined, the attractions of interest to the user can be selected from the optional attractions based on the user's travel profile data. For example, if it is determined based on the user's travel profile data that the user likes attractions with few people, then multiple attractions with less traffic can be selected from the optional attractions as the attractions of interest to the user; if it is determined based on the user's travel profile data that the user likes attractions with less consumption, then multiple attractions with low ticket prices can be selected from the optional attractions as the attractions of interest to the user. In some embodiments, an interest extraction model is pre-trained, and the feasibility of each optional attraction is evaluated using the interest extraction model.

[0048] The training process of the interest extraction model is: obtain travel portrait data of a large number of sample users, conduct questionnaire surveys on the sample users, and collect scenic spots that the sample users are interested in. For any sample user, the travel portrait data corresponding to the sample user and the optional scenic spots of the sample user are used as training samples, where the optional scenic spots of the sample user refer to all scenic spots in the area where the scenic spots of interest to the sample user are located. The scenic spots of interest to the sample user are marked as 1, and the scenic spots that the sample user is not interested in are marked as 0. The interest extraction model is trained using the training samples to enable the interest extraction model to have the ability to predict scenic spots of interest to users. The above-mentioned interest extraction model can be trained based on any neural network model, or based on a pre-trained model, such as a pre-trained large model similar to ChatGPT.

[0049] The travel portrait data and all optional attractions in this embodiment are input into the trained interest extraction model to obtain the extraction results output by the interest extraction model. For the extraction results of any optional attractions, the closer its value is to 1, the higher the user's interest level is. The N attractions with the highest interest level can be selected as the attractions of interest to the user. Wherein, N is a positive integer, and the value of N can be set according to the actual situation, for example, N is set to 10 or 20, etc., which is not limited in this embodiment.

[0050] In the embodiment of the present application, one or more scenic spots with the highest feasibility may be selected from the scenic spots that the user is interested in and recommended to the user as target scenic spots.

[0051] For example, during the user's travel process, based on the user's current travel status data, the information obtained by the user in the actual travel scenario and the impact of external factors on the user can be analyzed. Therefore, the feasibility of each optional attraction is evaluated according to the travel portrait data, and the attractions that the user is interested in are selected. According to the feasibility evaluation results of each optional attraction, the target attraction is selected from the attractions that the user is interested in as the next attraction recommended to the user. This can realize the fusion of multi-source information so that the content can be adjusted and optimized according to the user's real-time feedback, so that the next attraction meets the user's current needs. This real-time feedback mechanism makes travel planning no longer a one-time service, but a process of continuous adjustment and optimization, ensuring that the user's experience always meets their latest needs and environmental changes.

[0052] In the above embodiment, the user's travel portrait data can be obtained, wherein the travel portrait data at least includes the user's travel demand data, travel preference data, historical browsing data and current travel status data. Based on the travel portrait data, a feasibility evaluation is performed on each optional scenic spot, and then based on the feasibility evaluation results of each optional scenic spot, a target scenic spot is selected from the scenic spots that the user is interested in as a scenic spot recommended to the user. In this way, scenic spots that meet the user's preferences can be recommended to the user at least based on the user's travel demand data, travel preference data, historical browsing data and current travel status data. In this way, the user does not have to plan the travel personally, which not only saves time and energy, but also can obtain a personalized travel plan that meets their own preferences.

[0053] As an optional implementation, another embodiment of the present application discloses that the steps of the above embodiment are to evaluate the feasibility of each optional scenic spot according to the travel portrait data, which may specifically include the following steps:

[0054] Based on the travel portrait data, the feasibility of each optional attraction is evaluated from the dimensions of attraction overview, transportation cost, degree of fit with user preferences, travel time allocation, and travel expenses.

[0055] Based on the travel demand data, travel preference data, historical browsing data and current travel status data in the travel portrait data, user features, scenic spot features, and context features can be extracted. Among them, user features include user personalized preferences, user history, social media records, real-time input content and other features; scenic spot features include location tags of optional scenic spots (such as close to a hotel, close to the beach, etc.), Dianping ratings, must-see ratings, etc. Context features include current time, current location, current scenic spot, current fatigue level, etc.

[0056] Based on the above-mentioned user characteristics, scenic spot characteristics, and context characteristics, the feasibility of each optional scenic spot can be evaluated from the dimensions of scenic spot overview, transportation cost, degree of fit with user preferences, travel time allocation, and travel cost.

[0057] Specifically, the dimension of scenic spot overview (POIs) mainly evaluates the feasibility of each optional scenic spot based on the overview of the scenic spot, which includes the type of scenic spot, geographical location, ticket price and opening hours, etc. The more diverse the types of scenic spots are, the higher the feasibility of POIs is.

[0058] The traffic cost dimension (TrafficCost) mainly evaluates the feasibility of each optional attraction based on the traffic cost required for different attractions during the browsing process. TrafficCost includes the time cost and the cost of transportation from the current location to each optional attraction. Among them, the main modes of transportation include public transportation, cycling, walking, etc. The lower the traffic time cost and transportation cost of the attraction, the higher the feasibility of TrafficCost.

[0059] The dimension of the degree of fit with user preferences (Profit) mainly evaluates the feasibility of each optional scenic spot based on the degree of fit between the scenic spot and the user's preferences. The objective evaluation can be integrated with personal preferences to obtain the dimension of the degree of fit between the optional scenic spot and the user's preferences. Among them, the objective evaluation can be obtained from a third-party evaluation website, which is not limited in this embodiment. The higher the degree of fit between the scenic spot and the user's preferences, the higher the feasibility of Profit.

[0060] The travel time allocation dimension (TConstraint) mainly evaluates the feasibility of each optional attraction based on the time required to visit different attractions during the browsing process, the total number of days the user spends on the trip, and the specific time of each day. The more the time spent on the attraction matches the total number of days the user spends on the trip and the specific time of each day, the higher the feasibility of TConstraint.

[0061] The travel cost dimension (FConstraint) mainly evaluates the feasibility of the cost of attractions, including accommodation, transportation, tickets, etc. The less the cost of the attraction, the higher the feasibility of FConstraint should be.

[0062] In the embodiments of the present application, the feasibility of the optional attractions can be evaluated from the dimensions of transportation, budget, time, overview of the attractions, whether it matches the user's preferences, etc., so that the attractions with high feasibility are more in line with the user's needs and preferences.

[0063] As an optional implementation, another embodiment of the present application discloses that the steps of the above embodiment evaluate the feasibility of each optional attraction from the dimensions of attraction overview, transportation cost, degree of fit with user preferences, travel time allocation, and travel cost based on travel portrait data, and may specifically include the following steps:

[0064] According to the travel portrait data, the scores of each optional scenic spot in the dimensions of scenic spot overview, transportation cost, degree of fit with user preferences, travel time allocation, and travel cost are calculated respectively; the weighted sum of the scores of each optional scenic spot in the dimensions of scenic spot overview, transportation cost, degree of fit with user preferences, travel time allocation, and travel cost is calculated respectively to obtain a comprehensive score for each optional scenic spot; among which, the weight of each score is determined based on the travel portrait data; the comprehensive score of the optional scenic spot is used as the feasibility evaluation result of the optional scenic spot.

[0065] In an embodiment of the present application, based on the travel portrait data, the scores of each optional attraction in the dimensions of attraction overview, transportation cost, degree of fit with user preferences, travel time allocation, and travel cost can be calculated respectively.

[0066] Based on the overview of each optional attraction, the richer the content of the same attraction, the higher the score of the optional attraction in the attraction overview dimension should be.

[0067] Use the shortest path algorithm such as Dijkstra algorithm to calculate the optimal path from the current location to each optional attraction, and adjust the optimal path in combination with real-time traffic data to obtain the optimal route and transportation method from the current location to each optional attraction. Among them, if the transportation method to a certain optional attraction is more convenient, takes less time and costs less, the score of the optional attraction in the transportation cost dimension should be higher.

[0068] A weighted scoring model is used to integrate objective evaluation and personal preferences to calculate the degree of fit between each optional attraction and the user's preferences. The objective evaluation can be a Dianping score from a third-party software, a must-see list score, etc., which is not limited in this embodiment. The closer the objective evaluation of the optional attraction is to the user's personal preferences, the higher the score of the degree of fit between the optional attraction and the user's preferences should be.

[0069] A time management model, such as a rule-based system, can be used to ensure that the travel plan meets the overall time frame. The browsing time of each scenic spot can be predicted. The shorter the browsing time of each optional scenic spot, the higher the score of the corresponding travel time allocation dimension should be. It should be noted that the browsing time of each scenic spot can also be obtained through third-party software, which is not limited in this embodiment.

[0070] The budget optimization model is used to optimize and adjust the costs of different consumption items, such as accommodation, transportation, tickets, etc. The cost of each optional attraction can be calculated. The lower the cost of each optional attraction, the higher the score of the corresponding travel cost dimension should be. It should be noted that the cost of each attraction can also be obtained through third-party software, which is not limited in this embodiment.

[0071] The weighted sum of the scores of each optional attraction in the dimensions of attraction overview, transportation cost, degree of fit with user preferences, travel time allocation, and travel cost is calculated respectively to obtain a comprehensive score for each optional attraction. The comprehensive score of the optional attractions is used as the feasibility evaluation result of the optional attractions.

[0072] The calculation formula is as follows:

[0073]

[0074] Among them, Score represents the comprehensive score of the optional attractions, p i Indicates the score of each dimension of the optional scenic spot, w i represents the weight of each score, w 1 +w 2 +w 3 +w 4 +w 5 =1, need w i Normalize to [0,1] to ensure they are on the same comparison scale.

[0075] In addition, it should be noted that the weight of each score is determined based on the travel profile data. For example, if the travel profile data determines that the user wants to visit diverse and interesting attractions, the weight of the attraction overview dimension needs to be increased; if the travel profile data determines that the user wants convenient transportation and tries to shorten the time and money spent on transportation, the weight of the transportation cost dimension needs to be increased; if the travel profile data determines that the user wants the journey to be valuable, the weight of the degree of fit with the user's preferences needs to be increased; if the travel profile data determines that the user wants to have a certain time limit, the weight of the travel time allocation dimension needs to be increased; if the travel profile data determines that the user wants to travel within the budget, the weight of the travel cost dimension needs to be increased.

[0076] Assume that users' preferences on the five dimensions are as follows:

[0077] Attractions profile dimension: Very important, users want to visit diverse and interesting attractions.

[0078] Transportation cost dimension: moderately important. Users want convenient transportation but can accept moderate travel time.

[0079] The degree of alignment with user preferences is moderately important. Users want the journey to be valuable but do not rely entirely on this factor.

[0080] Travel time allocation dimension: Slightly important, users have certain time constraints, but it is not the main consideration.

[0081] Travel cost dimension: more important, users want to travel within their budget.

[0082] Based on the above preferences, the following weights can be assigned: 1 to w 5 The values ​​are 0.3, 0.2, 0.2, 0.15, and 0.15 respectively.

[0083] In the above embodiments, target attractions can be recommended according to user needs such as shortest time, lowest cost, maximum satisfaction, etc., so that the recommended attractions meet user needs and preferences, thereby improving the user's travel experience.

[0084] As an optional implementation, another embodiment of the present application discloses that the steps of the above embodiment may specifically include the following steps before selecting a target attraction from the attractions that the user is interested in as an attraction recommended to the user based on the feasibility evaluation results of each optional attraction:

[0085] The user's personalized preference features are extracted from the travel portrait data; based on the personalized preference features, the candidate attractions that the user is interested in are scored, and the N candidate attractions with the highest scores are selected as the attractions that the user is interested in; wherein N is a positive integer.

[0086] The candidate scenic spots that the user is interested in refer to all scenic spots that the user may be interested in. The candidate scenic spots that the user is interested in can be extracted using the interest extraction model of the above embodiment, which will not be described in detail here.

[0087] Based on the travel demand data, travel preference data, historical browsing data and current travel status data in the travel portrait data, user features, attraction features, and context features can be extracted.

[0088] The personalized preference features of the user are extracted from the user features, the scenic spot features, and the context features. Specifically, the personalized preference features of the user can be extracted from the user features, the scenic spot features, and the context features using a feature extraction model, which is not limited in this embodiment.

[0089] Then, the candidate attractions that the user is interested in are scored according to the personalized preference features. Among the candidate attractions that the user is interested in, the attractions that are more in line with the user's personalized preferences should have higher scores. In a specific embodiment, the personalized preference features can be input into a pre-trained deepfm model so that the deepfm model scores the candidate attractions that the user is interested in according to the personalized preference features.

[0090] The deepfm model can be trained in the following way: extract a large number of sample users' personalized preference features and optional attractions as training samples, and use questionnaires to ask sample users to score each optional attraction according to their interest, and use the score as a training label. The deepfm model is trained using the above training samples and training labels, and the model parameters are optimized through the back propagation algorithm to make the predicted user preferences as close as possible to the actual user interaction data, so that the deepfm model has the ability to score the candidate attractions that users are interested in.

[0091] The N candidate attractions with the highest scores are selected as the attractions that the user is interested in. Wherein, N is a positive integer. The specific value of N can be set according to actual conditions, for example, it can be set to 10 or 20, etc., which is not limited in this embodiment.

[0092] In the above embodiment, the deepfm model can be used to process high-dimensional nonlinear personalized preference feature data to predict the user's preference for attractions, thereby obtaining more accurate scoring results.

[0093] As an optional implementation, another embodiment of the present application discloses that the steps of the above embodiment select a target attraction from the attractions that the user is interested in as an attraction recommended to the user according to the feasibility evaluation results of each optional attraction, and specifically may include the following steps:

[0094] The feasibility evaluation results of each optional scenic spot and the scenic spots that the user is interested in are input into the pre-trained DNN model, so that the DNN model selects the target scenic spot from the scenic spots that the user is interested in as the scenic spot recommended to the user based on the feasibility evaluation results of each optional scenic spot.

[0095] The target scenic spot is selected by using a deep neural network (DNN) model. Specifically, the feasibility evaluation results of each optional scenic spot and the scenic spots that the user is interested in are input into a pre-trained DNN model, so that the DNN model processes the feasibility evaluation results of each optional scenic spot and the scenic spots data that the user is interested in, and outputs the target scenic spot as a recommended scenic spot to the user.

[0096] The DNN model can be trained in the following way: extract a large number of sample users' feasibility evaluation results and the scenic spots that the sample users are interested in as training samples, and use the scenic spots that the sample users are interested in as training labels. The DNN model is trained using the above training samples and training labels, and the parameters of the DNN model are optimized through the back propagation algorithm so that the DNN model has the ability to select target scenic spots.

[0097] In the above embodiment, the DNN model is used to obtain the user's favorite and most reasonably planned scenic spots, which represent the best choice based on the user's personalized preferences and actual travel planning.

[0098] As an optional implementation, another embodiment of the present application discloses that, when there are multiple target scenic spots, the method of the above embodiment may specifically include the following steps:

[0099] Based on the travel portrait data, a visiting order of the target attractions is generated; based on the user's departure location and the visiting order of the target attractions, transportation and accommodation recommendation information is generated; based on the travel portrait data and weather data of the area where the target attractions are located, clothing recommendation information is output; based on the visiting order of the target attractions, the transportation and accommodation recommendation information and the clothing recommendation information, a travel plan is generated.

[0100] In an embodiment of the present application, a travel planning table can also be generated for the user before the user starts traveling.

[0101] Specifically, before the user starts traveling, the current travel status data includes the location of the user's travel departure point. Based on the user's travel demand data, travel preference data, historical browsing data and the location of the user's travel departure point, according to the records of the above embodiment, each optional scenic spot is evaluated for feasibility. According to the feasibility evaluation results of each optional scenic spot, a target scenic spot is selected from the scenic spots of interest to the user as the first scenic spot recommended to the user; the current travel status data is updated to the location of the first scenic spot recommended to the user, and then based on the user's travel demand data, travel preference data, historical browsing data and the location of the first scenic spot recommended to the user, according to the records of the above embodiment, each optional scenic spot is evaluated for feasibility. According to the feasibility evaluation results of each optional scenic spot, a target scenic spot is selected from the scenic spots of interest to the user as the second scenic spot recommended to the user, and so on and so forth until the scenic spot recommendation is completed, and multiple target scenic spots and the tour order of multiple target scenic spots are obtained. Alternatively, a classification model is used to determine the scenic spots preferred by the user, and a corresponding location analysis is performed through a geographic information system to optimize the travel route.

[0102] According to the user's starting location and the order of visiting multiple target attractions, combined with the information provided by third-party information sources, transportation and accommodation recommendation information is generated. It can recommend accommodation places that are closer to the attractions and have higher ratings from third-party information sources, and at the same time, the type of accommodation place is selected based on the user's budget and preferences, such as hotels, homestays, or youth hostels. The choice of transportation mode can use the shortest path algorithm such as the Dijkstra algorithm to calculate the optimal path between different target attractions, and adjust the recommended route in combination with real-time traffic data. In addition, it can also recommend places to eat to users. Specifically, it can recommend places to eat that are closer to the attractions and have higher ratings from third-party information sources, and arrange the places to eat at lunch and dinner time.

[0103] According to the travel portrait data and the weather data of the target scenic spots, clothing recommendation information is output. For example, if it is determined according to the travel portrait data that the user likes to wear cotton clothing, and the weather data of the target scenic spots is high temperature, clothing recommendation information can be output to recommend the user to bring cotton T-shirts.

[0104] Finally, a travel planning table is generated according to the visiting sequence of multiple target attractions, transportation and accommodation recommendation information, and clothing recommendation information. Table 1 shows a travel planning table provided by an embodiment.

[0105]

[0106] Table 1

[0107] Furthermore, during the user's travel, the scenic spots can be adjusted according to the user's current travel status data according to the records of the above embodiments. The current travel status data includes the current time, current location, current scenic spot, current fatigue level, historical driving habits, current environmental factors, current emotional state, etc. Specifically, the feasibility of each optional scenic spot can be evaluated according to the user's travel demand data, travel preference data, historical browsing data and current travel status data. According to the feasibility evaluation results of each optional scenic spot, the target scenic spot is reselected from the scenic spots that the user is interested in as the next scenic spot recommended to the user. In this way, the content is adjusted and optimized according to the user's real-time feedback so that the next scenic spot meets the user's current needs. This real-time feedback mechanism makes travel planning no longer a one-time service, but a process of continuous adjustment and optimization, ensuring that the user's experience always meets their latest needs and environmental changes.

[0108] Figure 3 This is a flow chart of scenic spot recommendation provided by the embodiment of the present application. Figure 3As shown, during the user's travel process, the user's current travel status data can be collected in real time, and user features, scenic spot features, and context features can be extracted from travel demand data, travel preference data, historical browsing data, and current travel status data.

[0109] On the one hand, personalized preference features are extracted from user features, scenic spot features, and context features, and then the deepfm model is used to score the candidate scenic spots that the user is interested in, and the N candidate scenic spots with the highest scores are selected as the scenic spots that the user is interested in; on the other hand, based on user features, scenic spot features, and context features, the feasibility of each optional scenic spot is evaluated from the dimensions of scenic spot overview, transportation cost, degree of fit with user preferences, travel time allocation, and travel cost, and the feasibility evaluation results of each optional scenic spot are obtained. Based on the feasibility evaluation results of each optional scenic spot, the DNN model selects the target scenic spot from the scenic spots that the user is interested in as the scenic spot recommended to the user. Continue to collect the user's current travel status data to prepare for the generation of the next scenic spot. And so on, until the last scenic spot is generated.

[0110] This embodiment makes up for the fact that the DeepFM model cannot fully consider the diverse needs of users in actual travel. It uses a combination of the DeepFM model and the DNN model to comprehensively consider multiple factors in travel planning and evaluate the actual suitability of each attraction through a scoring mechanism. This two-layer model structure allows the system to first identify attractions that users may be interested in, and then further screen them based on actual travel conditions, ensuring that the final recommendation is in line with user preferences and suitable for their travel plans.

[0111] As an optional implementation method, another embodiment of the present application discloses that if a sufficient amount of travel portrait data is not collected, the user's preferences can be obtained and modifications can be made based on the preset strategy according to the user's preferences.

[0112] The preset guide refers to the ready-made guide stored in the database. In other words, if a sufficient amount of travel portrait data is not collected, the preset guide can be added, deleted, or modified to obtain recommended attractions for users. Figure 4 The following is a preset guide. If attraction 1 is A and the user's need is B, then A in attraction 1 is changed to B.

[0113] As an optional implementation, another embodiment of the present application discloses that the method of the above embodiment further includes the following steps:

[0114] Based on travel profile data and hotel ratings, hotel recommendation information is output during meal times.

[0115] Specifically, the embodiments of the present application can also recommend restaurants to users during meal time periods. Specifically, the user's dietary preferences, such as the user's favorite flavors, cuisines, etc., and the user's current location can be obtained in combination with the travel portrait data; the public's basic evaluation of the restaurant can be obtained in combination with the restaurant rating, and then a preliminary understanding of the restaurant can be obtained, so that the user can be recommended to the user for the user's favorite flavors and cuisines with higher ratings and closer to the user's current location. In addition, in addition to outputting restaurant recommendation information during meal time periods, the user's restaurant recommendation instruction can also be obtained, and in response to the user's restaurant recommendation instruction, the restaurant recommendation information is output based on the travel portrait data and the restaurant rating.

[0116] In this way, we can recommend hotels that are closer and more in line with the user's preferences, thereby improving the user's travel experience.

[0117] As an optional implementation, another embodiment of the present application discloses that when recommending attractions, restaurants and accommodation, the corresponding virtual reality (VR) images and / or augmented reality (AR) images of attractions, restaurants and accommodation are output. That is to say, all attractions, hotels and restaurants can provide an interactive user interface based on VR, and VR / AR preview mode can be activated. If a VR device is used, the user will be brought into a completely virtual environment and can view panoramic images or videos of the attractions in 360 degrees. If an AR device is used, such as a smartphone or tablet, virtual information is superimposed on the actual landscape captured by the camera of the device, which enables the user to fully understand the places to be visited from different angles. Users can drag, add and delete on the system to make modifications, and the system can optimize the content of the guide and the recommendation service in real time through adaptive adjustment strategies based on these feedbacks, so as to realize the dynamic update and self-optimization of the travel guide.

[0118] As an optional implementation method, another embodiment of the present application discloses that after the user finishes traveling, a digital travel memory preservation service is provided to the user, and the user can upload and save photos, videos, travel notes and other content. This embodiment can automatically generate a digital travel memory book based on the journey. In addition, a sharing function can also be opened to allow users to easily share their travel experiences and strategies, and build a travel community ecology.

[0119] As an optional implementation method, another embodiment of the present application discloses that blockchain technology is used, and all tourism-related information, such as user evaluations, service provider information, etc., is stored using blockchain technology to ensure the immutability and transparency of data and establish a trust mechanism between users and service providers. In addition, the system includes a cross-platform integrated service experience, which integrates the system with multiple platforms such as mobile APP, official website, and social platform to more accurately grasp user preferences, seamlessly connect users' travel planning experience, and provide a full range of information services and real-time travel suggestions. Users can receive strategy push notifications across devices to achieve travel planning and adjustments anytime, anywhere.

[0120] As an optional implementation, algorithms such as random forests and deep learning networks are used to train the models in the above embodiments. These models can handle nonlinear relationships and high-dimensional interactions and are suitable for processing complex contextual information. The model is evaluated and adjusted through cross-validation and other techniques. After the user visits each recommended attraction, feedback information such as satisfaction scores and comments is collected, and model parameters and user preference configurations are adjusted based on these feedbacks to form a self-learning and self-optimizing recommendation system. At the same time, users can see in real time how the changes they make to their plans affect the overall travel experience, including cost, time, and satisfaction.

[0121] Corresponding to the above travel planning method, the present application embodiment also discloses a travel planning device, see Figure 5 As shown, the device comprises:

[0122] The acquisition module 100 is used to acquire the user's travel portrait data; the travel portrait data at least includes the user's travel demand data, travel preference data, historical browsing data and current travel status data;

[0123] Evaluation module 110, for evaluating the feasibility of each optional scenic spot based on the travel portrait data;

[0124] The selection module 120 is used to select a target attraction from the attractions that the user is interested in as an attraction recommended to the user according to the feasibility evaluation results of each optional attraction.

[0125] As an optional implementation, another embodiment of the present application discloses that the evaluation module 110 in the above embodiment is specifically used for:

[0126] Based on the travel portrait data, the feasibility of each optional attraction is evaluated from the dimensions of attraction overview, transportation cost, degree of fit with user preferences, travel time allocation, and travel expenses.

[0127] As an optional implementation, another embodiment of the present application discloses that the evaluation module 110 in the above embodiment is specifically used for:

[0128] According to the travel portrait data, the scores of each optional scenic spot in the dimensions of scenic spot overview, transportation cost, degree of fit with user preferences, travel time allocation, and travel cost are calculated respectively; the weighted sum of the scores of each optional scenic spot in the dimensions of scenic spot overview, transportation cost, degree of fit with user preferences, travel time allocation, and travel cost is calculated respectively to obtain a comprehensive score for each optional scenic spot; among which, the weight of each score is determined based on the travel portrait data; the comprehensive score of the optional scenic spot is used as the feasibility evaluation result of the optional scenic spot.

[0129] As an optional implementation, another embodiment of the present application discloses that the device in the above embodiment further includes:

[0130] An extraction module is used to extract the user's personalized preference features from the travel portrait data;

[0131] The scoring module is used to score the candidate attractions that the user is interested in according to the personalized preference characteristics, and select the N candidate attractions with the highest scores as the attractions that the user is interested in; wherein N is a positive integer.

[0132] As an optional implementation, another embodiment of the present application discloses that the scoring module in the above embodiment is specifically used for:

[0133] The personalized preference features are input into the pre-trained deepfm model so that the deepfm model scores the candidate attractions that the user is interested in according to the personalized preference features, and selects the N candidate attractions with the highest scores as the attractions that the user is interested in.

[0134] As an optional implementation, another embodiment of the present application discloses that the selection module 120 in the above embodiment is specifically used for:

[0135] The feasibility evaluation results of each optional scenic spot and the scenic spots that the user is interested in are input into the pre-trained DNN model, so that the DNN model selects the target scenic spot from the scenic spots that the user is interested in as the scenic spot recommended to the user based on the feasibility evaluation results of each optional scenic spot.

[0136] As an optional implementation, another embodiment of the present application discloses that the device in the above embodiment further includes:

[0137] The generation module is used to generate planned attractions and the order of visiting the planned attractions based on the user's travel profile data; generate transportation and accommodation recommendation information based on the user's departure location and the order of visiting the planned attractions; output clothing recommendation information based on the travel profile data and the weather data of the area where the planned attractions are located; and generate a travel planning table based on the order of visiting the planned attractions, transportation and accommodation recommendation information, and clothing recommendation information.

[0138] As an optional implementation, another embodiment of the present application discloses that the device in the above embodiment further includes:

[0139] The restaurant recommendation module is used to output restaurant recommendation information during meal time periods based on travel profile data and restaurant ratings.

[0140] Specifically, the device provided in this embodiment belongs to the same application concept as the method provided in the above embodiment of this application, can execute the method provided in any of the above embodiments of this application, and has the corresponding functional modules and beneficial effects of the execution method. For the technical details not fully described in this embodiment, please refer to the specific processing content of the method provided in the above embodiment of this application, which will not be repeated here.

[0141] The functions implemented by the above modules can be implemented by the same or different processors respectively, and the embodiments of the present application are not limited thereto.

[0142] It should be understood that the units in the above devices can be implemented in the form of a processor calling software. For example, the device includes a processor, the processor is connected to a memory, and instructions are stored in the memory. The processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of each unit of the device, wherein the processor can be a general-purpose processor, such as a CPU or a microprocessor, etc., and the memory can be a memory in the device or a memory outside the device. Alternatively, the units in the device can be implemented in the form of hardware circuits, and the functions of some or all units can be realized by designing the hardware circuits. The hardware circuit can be understood as one or more processors; for example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units are realized by designing the logical relationship of the components in the circuit; for another example, in another implementation, the hardware circuit can be implemented by PLD, taking FPGA as an example, which can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by the configuration file, so as to realize the functions of some or all of the above units. All units of the above devices can be implemented in the form of a processor calling software, or in the form of hardware circuits, or in part by a processor calling software, and the remaining part is implemented in the form of hardware circuits.

[0143] In an embodiment of the present application, a processor is a circuit with the ability to process signals. In one implementation, the processor may be a circuit with the ability to read and run instructions, such as a CPU, a microprocessor, a GPU, or a DSP; in another implementation, the processor may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit is fixed or reconfigurable, such as a hardware circuit implemented by an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, DPU, etc.

[0144] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0145] In addition, all or part of the units in the above device can be integrated together, or can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a SOC. The SOC may include at least one processor for implementing any of the above methods or implementing the functions of each unit of the device. The type of the at least one processor may be different, for example, including a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0146] An embodiment of the present application further provides a control device, which includes a processor and an interface circuit. The processor in the control device is connected to an input-output component through the interface circuit of the control device.

[0147] The input-output component specifically refers to a hardware component that enables a user to input information and output information to the user, such as a microphone, keyboard, handwriting tablet, touch screen, display, speaker, printer, etc.

[0148] The above-mentioned interface circuit can be any interface circuit that can realize the data communication function, for example, it can be a USB interface circuit, a Type-C interface circuit, a serial port circuit, a PCIE circuit, etc.

[0149] The processor in the control device is a circuit with signal processing capability, which can recommend travel attractions to users by executing any of the travel planning methods described in the above embodiments. The specific implementation of the processor can refer to the above processor implementation, and the embodiments of this application are not strictly limited.

[0150] When the control device is applied to a device with a human-computer interaction function, the input and output components of the control device may be input components and output components on the device, such as a microphone, a keyboard, a handwriting tablet, a touch screen, a display, an audio player, etc. At the same time, the processor of the control device may be a CPU or GPU, etc. provided by the device, and the interface circuit of the control device may be an interface circuit between the information input component of the device and a processor such as a CPU or GPU.

[0151] Corresponding to the above travel planning method, the present application embodiment also discloses an electronic device, see Figure 6 As shown, the electronic device includes:

[0152] Memory 200 and processor 210;

[0153] The memory 200 is connected to the processor 210 and is used to store programs;

[0154] The processor 210 is used to implement the travel planning method disclosed in any of the above embodiments by running the program stored in the memory 200.

[0155] Specifically, the electronic device may further include: a bus, a communication interface 220 , an input device 230 and an output device 240 .

[0156] The processor 210, the memory 200, the communication interface 220, the input device 230 and the output device 240 are connected to each other via a bus.

[0157] A bus may include a pathway that transfers information between components of a computer system.

[0158] The processor 210 may be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0159] The processor 210 may include a main processor, and may also include a baseband chip, a modem, and the like.

[0160] The memory 200 stores a program for executing the technical solution of the present application, and may also store an operating system and other key services. Specifically, the program may include a program code, and the program code includes computer operation instructions. More specifically, the memory 200 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk storage, a flash, and the like.

[0161] The input device 230 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor.

[0162] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0163] The communication interface 220 may include any transceiver or the like to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0164] The processor 210 executes the program stored in the memory 200 and calls other devices, which can be used to implement the various steps of the travel planning method provided in the above embodiments of the present application.

[0165] In addition to the above-mentioned methods and devices, the embodiments of the present application may also be a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor, the processor executes the various steps of the travel planning method provided in the above-mentioned embodiments.

[0166] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0167] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK).

[0168] In addition, the embodiments of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the various steps of the travel planning method provided in the above embodiments.

[0169] The computer readable storage medium may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0170] Specifically, the specific working contents of each part of the above-mentioned electronic device, computer program product and storage medium, as well as the specific processing contents when the computer program product or the computer program on the above-mentioned storage medium is executed by the processor, can all be found in the contents of the various embodiments of the above-mentioned travel planning method, and will not be repeated here.

[0171] For the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0172] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device 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.

[0173] The steps in the methods of each embodiment of the present application can be adjusted in order, combined and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.

[0174] The modules and sub-modules in the devices and terminals in the various embodiments of the present application can be combined, divided and deleted according to actual needs.

[0175] In the several embodiments provided in the present application, it should be understood that the disclosed terminals, devices and methods can be implemented in other ways. For example, the terminal embodiments described above are only schematic, for example, the division of modules or submodules is only a logical function division, and there may be other division methods in actual implementation, such as multiple submodules or modules can be combined or integrated into another module, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0176] The modules or submodules described as separate components may or may not be physically separated, and the components of the modules or submodules may or may not be physical modules or submodules, that is, they may be located in one place, or they may be distributed on multiple network modules or submodules. Some or all of the modules or submodules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0177] In addition, each functional module or submodule in each embodiment of the present application may be integrated into one processing module, or each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into one module. The above-mentioned integrated modules or submodules may be implemented in the form of hardware or in the form of software functional modules or submodules.

[0178] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0179] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly by hardware, software units executed by a processor, or a combination of the two. The software units may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0180] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including a..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0181] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A travel planning method, characterized in that: include: Obtain user travel profile data; The travel portrait data at least includes the user's travel demand data, travel preference data, historical browsing data and current travel status data; Conduct feasibility evaluation on each optional scenic spot based on the travel portrait data; According to the feasibility evaluation results of the optional scenic spots, a target scenic spot is selected from the scenic spots that the user is interested in as a scenic spot recommended to the user.

2. The method according to claim 1, characterized in that The feasibility evaluation of each optional scenic spot based on the travel portrait data includes: Based on the travel portrait data, the feasibility of each optional attraction is evaluated from the dimensions of attraction overview, transportation cost, degree of fit with user preferences, travel time allocation, and travel cost.

3. The method according to claim 2, characterized in that According to the travel portrait data, the feasibility of each optional attraction is evaluated from the dimensions of attraction overview, transportation cost, degree of fit with user preferences, travel time allocation, and travel cost, including: According to the travel portrait data, the scores of each optional scenic spot in terms of scenic spot overview, transportation cost, degree of fit with user preferences, travel time allocation, and travel cost are calculated respectively; The weighted sum of the scores of each optional scenic spot in terms of scenic spot overview, transportation cost, degree of fit with user preferences, travel time allocation, and travel cost is calculated respectively to obtain a comprehensive score for each optional scenic spot; wherein the weight of each score is determined based on the travel portrait data; the comprehensive score of the optional scenic spot serves as a feasibility evaluation result of the optional scenic spot.

4. The method according to claim 1, characterized in that: Before selecting a target attraction from the attractions that the user is interested in as an attraction recommended to the user based on the feasibility evaluation results of the optional attractions, the method further includes: Extracting the personalized preference features of the user from the travel portrait data; According to the personalized preference characteristics, the candidate attractions that the user is interested in are scored, and the N candidate attractions with the highest scores are selected as the attractions that the user is interested in; wherein N is a positive integer.

5. The method according to claim 4, characterized in that Scoring the candidate attractions that the user is interested in according to the personalized preference characteristics, and selecting N candidate attractions with the highest scores as the attractions that the user is interested in, includes: The personalized preference features are input into a pre-trained deepfm model, so that the deepfm model scores the candidate attractions that the user is interested in according to the personalized preference features, and selects the N candidate attractions with the highest scores as the attractions that the user is interested in.

6. The method according to claim 1, characterized in that The step of selecting a target attraction from the attractions that the user is interested in as an attraction recommended to the user according to the feasibility evaluation results of the optional attractions includes: The feasibility evaluation results of the optional attractions and the attractions that the user is interested in are input into a pre-trained DNN model, so that the DNN model selects a target attraction from the attractions that the user is interested in as an attraction recommended to the user based on the feasibility evaluation results of the optional attractions.

7. The method according to claim 1, characterized in that In the case where there are multiple target scenic spots, the method further includes: Generating a visiting sequence of the target attractions according to the travel portrait data; Generate transportation and accommodation recommendation information based on the user's departure location and the order of visiting the target attractions; output clothing recommendation information based on the travel portrait data and the weather data of the area where the target attractions are located; A travel plan is generated according to the visiting sequence of the target attractions, the transportation and accommodation recommendation information, and the clothing recommendation information.

8. The method according to claim 1, characterized in that The method further comprises: Based on the travel profile data and the hotel ratings, hotel recommendation information is output during the dining time period.

9. A travel planning device, characterized in that: include: The acquisition module is used to obtain the user's travel profile data; The travel portrait data at least includes the user's travel demand data, travel preference data, historical browsing data and current travel status data; An evaluation module, used to evaluate the feasibility of each optional scenic spot based on the travel portrait data; The selection module is used to select a target attraction from the attractions that the user is interested in as an attraction recommended to the user according to the feasibility evaluation results of the optional attractions.

10. An electronic device, characterized in that: include: Memory and processor; Wherein, the memory is used to store programs; The processor is used to implement the method according to any one of claims 1 to 8 by running the program in the memory.

11. A computer program product, characterized in that The computer program product comprises a computer program or a computer instruction, and when the computer program or the computer instruction is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images