A method for recommending tourist routes

Abstract

The present invention relates to the technical field of travel recommendation, and specifically to a travel route recommendation method, comprising the following steps: step 1. establishing a scenic spot type library; step 2. establishing an inter-city route library; step 3. obtaining words with a tendency as keywords of travel routes; step 4. combining the scenic spot type library and the inter-city route library with the keywords of the travel route to obtain the travel route that best matches the user's preference as the final travel route recommended to the user. The method of the present invention can recommend scenic spots that better meet the personalized preferences of users, and is convenient for planning the best travel route for users.

Description

Technical Field

[0001] The invention belongs to the technical field of tourist routes, in particular to a tourist route recommendation method. Background Art

[0002] The current travel route recommendation method is mainly for a single person or a group, and the commonly used recommendation scheme generally adopts the traditional static search and matching method. This method first obtains the user's access records, and then searches and matches the access records in the existing travel route database based on similarity or uses optimization algorithms such as greedy algorithms to obtain the optimal route. That is, in route recommendation, the route recommendation for individuals is still based on access records, and it is impossible to make targeted recommendations based on the individual's complex preferences, so the user experience is poor. Summary of the invention

[0003] Purpose of the invention: To provide a method for recommending tourist routes to solve the above problems existing in the prior art.

[0004] In a first aspect, the present invention provides a method for recommending a travel route, comprising the following steps:

[0005] Step 1. Establish a scenic spot type library;

[0006] Step 2. Establish an inter-city route database;

[0007] Step 3. Obtain words with tendency as keywords of travel routes;

[0008] Step 4. According to the keywords of the travel route, the scenic spot type library and the inter-city route library are combined to obtain the travel route that best matches the user's preference as the final travel route recommended to the user.

[0009] In one embodiment, step 1 includes the following sub-steps:

[0010] Step 1.1. Obtain scenic spot data, and classify scenic spots according to the acquired scenic spot data;

[0011] Step 1.2. Obtain the coordinates of the corresponding scenic spot, and obtain the city to which the corresponding scenic spot belongs according to the obtained coordinates;

[0012] Step 1.3. Classify and sort the cities that belong to each type of scenic spot according to the MBI value ranking of the cultural and tourism website.

[0013] In one embodiment, step 2 includes the following sub-steps:

[0014] Step 2.1. Obtain public transportation website data;

[0015] Step 2.2. Combine the acquired data with the coordinates of the cities to which different scenic spots belong, and obtain the time and cost required for travel between the cities to which different scenic spots belong.

[0016] In one embodiment, step 4 includes the following sub-steps:

[0017] Step 4.1. Combine the user's travel mode and travel time from the departure place or the departure place to the destination with the inter-city route library and the scenic spot type library to obtain N scenic spot types;

[0018] Step 4.2. Select the highest ranked scenic spot in the corresponding type from the N scenic spot types as the starting city, and combine each starting city with the city coordinates to select the next node layer city, the expression is:

[0019] W m (k i ,l j

[0020] Among them, W m (k i ,l j ) means that in the mth path, the kth node in the i-th level node layer i From the city to the lth node in the jth level node layer j The path segment weight score of each city, where j is the next level node layer of i, that is, j = i + 1, i is an integer, and the value range of i is 0 <i<N;

[0021] Step 4.3. Normalize the weight scores of the path segments in the same node layer to obtain N! travel routes;

[0022] Step 4.4. Sum the weighted scores of each path segment of each travel route. The travel route with the highest score is the travel route that best matches the user's preference, and this travel route is used as the final travel route recommended to the user.

[0023] In one embodiment, the path segment weight score calculation function is:

[0024]

[0025] in, Indicates that in the mth path, the kth node in the i-th level node layer i The comprehensive impact score of each city, Indicates that in the mth path, the lth node in the jth level node layer j The ranking ratio of the city's scenic spots in the type of scenic spots they belong to, Indicates that in the mth path, from the i-th level node layer, the k-th i From the city to the lth node in the jth level node layer jThe ratio of travel time preference to the actual travel time between cities.

[0026] In one embodiment, the weight scores of each path segment of each travel route are summed, and the calculation function is:

[0027]

[0028] In one embodiment, the expression for the travel route with the highest score is:

[0029]

[0030] In one embodiment, the next node layer city is the N-1 cities of the scenic spot type that are closest to the N starting cities in a straight line distance.

[0031] In summary, the beneficial effects of the present invention are as follows: the method of the present invention can recommend scenic spots that better meet the personalized preferences of users, and the recommendation results are accurate, which facilitates planning the best travel route for users. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 is a flow chart of an embodiment of the present invention;

[0033] Figure 2 This is a demonstration diagram of path segment calculation according to an embodiment of the present invention.

[0034] Specific embodiment

[0035] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is apparent to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features well known in the art are not described.

[0036] Example 1

[0037] like Figure 1 and Figure 2 As shown, the travel route recommendation method disclosed in this embodiment includes:

[0038] Step 1. Establish a scenic spot type library;

[0039] Step 1.1. Obtain scenic spot data, and classify scenic spots according to the acquired scenic spot data;

[0040] Obtain the classification and ranking data of 5A / 4A scenic spots across the country, and divide the obtained data into 5 categories according to the classification standards, with a total of 28 different scenic spot types;

[0041] Furthermore, the scenic spot data obtained also includes data on a small number of popular national 3A-level scenic spots.

[0042] Step 1.2. Obtain the coordinates of the corresponding scenic spot based on the map API, and obtain the city to which the corresponding scenic spot belongs according to the obtained coordinates;

[0043] Step 1.3. Classify and sort the cities that belong to each type of scenic spot according to the MBI value ranking of the cultural and tourism website.

[0044] Step 2. Establish an inter-city route database;

[0045] Step 2.1. Obtain public transportation website data;

[0046] Step 2.2. Combine the obtained data with the coordinates of the cities to which different scenic spots belong, and obtain the time and cost required for travel between the cities to which different scenic spots belong;

[0047] Furthermore, the modes of transportation between cities belonging to different scenic spots include buses, subways, railways, long-distance passenger transport and civil aviation.

[0048] Step 3. Obtain words with tendency as keywords of travel routes;

[0049] Allow users to select words with tendencies from the prompt words as keywords for travel routes;

[0050] Optionally, performing text segmentation on the voice description or text description input by the user to form a word sequence, and extracting words with a tendency from the word sequence as keywords of the travel route;

[0051] Furthermore, the prompt words include N scenic spot types, departure places, destinations, travel days, travel methods, travel time and local food, where N is not greater than the travel days.

[0052] Step 4. According to the keywords of the travel route, the travel route that best matches the user's preference is obtained in combination with the scenic spot type library and the inter-city route library as the final travel route recommended to the user;

[0053] Step 4.1. Combine the user's travel mode and travel time from the departure place or the departure place to the destination with the inter-city route library and the scenic spot type library to obtain N scenic spot types;

[0054] Step 4.2. Select the highest ranked scenic spot in the corresponding type from the N scenic spot types as the starting city, and combine each starting city with the city coordinates to select the next node layer city, the expression is:

[0055] W m (k i ,l j )

[0056] Among them, W m (k i ,l j ) means that in the mth path, the kth node in the i-th level node layer i From the city to the lth node in the jth level node layer j The path segment weight score of each city, where j is the next level node layer of i, that is, j = i + 1, i is an integer, and the value range of i is 0 <i<N;

[0057] Among them, the next node layer city is the N-1 scenic spot type cities that are closest to the N starting cities in a straight line;

[0058] Furthermore, the path segment weight score calculation function is:

[0059]

[0060] in, Indicates that in the mth path, the kth node in the i-th level node layer i The comprehensive impact score of a city is the city influence index, which includes city size, city environment, city climate, local cuisine, Indicates that in the mth path, the lth node in the jth level node layer j The ranking ratio of the scenic spots in each city in the type of scenic spots they belong to is 1, and the ranking ratio of the first-ranked scenic spot is 1, and the ranking ratio of the subsequent scenic spots is the reciprocal value of the number of their types of scenic spots. Indicates that in the mth path, from the i-th level node layer, the k-th i From the city to the lth node in the jth level node layer j The ratio of travel time preference to the actual travel time between cities;

[0061] Step 4.3. Normalize the weight scores of the path segments in the same node layer to obtain N! travel routes;

[0062] Step 4.4. Sum the weighted scores of each path segment of each travel route. The travel route with the highest score is the travel route that best matches the user's preference. This travel route is used as the final travel route recommended to the user. The calculation function is:

[0063]

[0064] Its expression is:

[0065]

[0066] The preferred embodiment of the present invention is described in detail above in conjunction with the accompanying drawings. However, the present invention is not limited to the specific details in the above embodiment. Within the technical concept of the present invention, various equivalent transformations can be made to the technical scheme of the present invention, and these equivalent transformations all belong to the protection scope of the present invention.

Claims

1. A method for recommending a tourist route, characterized in that: The following steps are involved: Step 1. Establish a scenic spot type library; Step 2. Establish an inter-city route database; Step 3. Obtain words with tendency as keywords of travel routes; Step 4. According to the keywords of the travel route, the scenic spot type library and the inter-city route library are combined to obtain the travel route that best matches the user's preference as the final travel route recommended to the user.

2. The method according to claim 1, characterized in that The step 1 includes the following sub-steps: Step 1.

1. Obtain scenic spot data, and classify scenic spots according to the acquired scenic spot data; Step 1.

2. Obtain the coordinates of the corresponding scenic spot, and obtain the city to which the corresponding scenic spot belongs according to the obtained coordinates; Step 1.

3. Classify and sort the cities that belong to each type of scenic spot according to the MBI value ranking of the cultural and tourism website.

3. The method according to claim 2, characterized in that The step 2 includes the following sub-steps: Step 2.

1. Obtain public transportation website data; Step 2.

2. Combine the acquired data with the coordinates of the cities to which different scenic spots belong, and obtain the time and cost required for travel between the cities to which different scenic spots belong.

4. The method according to claim 1, characterized in that: The step 4 includes the following sub-steps: Step 4.

1. Combine the user's travel mode and travel time from the departure place or the departure place to the destination with the inter-city route library and the scenic spot type library to obtain N scenic spot types; Step 4.

2. Select the highest ranked scenic spot in the corresponding type from the N scenic spot types as the starting city, and combine each starting city with the city coordinates to select the next node layer city, the expression is: W m (k i ,l j ) Among them, W m (k i ,l j ) means that in the mth path, the kth node in the i-th level node layer i From the city to the lth node in the jth level node layer j The path segment weight score of each city, where j is the next level node layer of i, that is, j = i + 1, i is an integer, and the value range of i is 0 <i<N; Step 4.

3. Normalize the weight scores of the path segments in the same node layer to obtain N! travel routes; Step 4.

4. Sum the weighted scores of each path segment of each travel route. The travel route with the highest score is the travel route that best matches the user's preference, and this travel route is used as the final travel route recommended to the user.

5. The method according to claim 4, characterized in that The path segment weight score calculation function is: in, Indicates that in the mth path, the kth node in the i-th level node layer i The comprehensive impact score of each city, Indicates that in the mth path, the lth node in the jth level node layer j The ranking ratio of the city's scenic spots in the type of scenic spots they belong to, Indicates that in the mth path, from the i-th level node layer, the k-th i From the city to the lth node in the jth level node layer j The ratio of travel time preference to the actual travel time between cities.

6. The method according to claim 4, characterized in that Sum the weighted scores of each path segment of each travel route, and the calculation function is:

7. The method according to claim 6, characterized in that The expression for the travel route with the highest score is:

8. The method according to claim 4, characterized in that The next node layer city is the city of the N-1 scenic spot types that are closest to the N starting cities in a straight line.

Images