A tourist route customization method based on artificial intelligence

Abstract

The present invention relates to the technical field of travel route customization, and in particular to a travel route customization method based on artificial intelligence, the method comprising: obtaining travel demand information of users; extracting travel locations, travel start time, travel end time and accommodation requirements from the travel demand information; grabbing relevant travel routes from the network, screening out travel routes related to travel locations, and forming a preliminary travel route database; obtaining travel time periods, and predicting the degree of crowding of scenic spots in the travel routes during the travel time periods; reminding users to change travel time periods according to the degree of crowding, and outputting a recommended travel itinerary, and regenerating a recommended route matching the travel itinerary according to user feedback; grabbing hotel information related to accommodation needs from the network, screening out hotels related to accommodation needs, and forming a hotel database; obtaining the distance between each hotel in the hotel database and different scenic spots, optimizing the visiting order of scenic spots in the recommended route, and generating a final travel route.

Description

Technical Field

[0001] The present invention relates to the technical field of travel route customization, and in particular to a travel route customization method based on artificial intelligence. Background Art

[0002] In order to attract tourists, various travel websites will launch travel routes for some popular attractions, and each travel route includes multiple attractions.

[0003] However, current travel route recommendation systems mainly rely on matching users' historical behavior data with scenic spot features. This approach ignores the diversity and complexity of user preferences, as well as the influence of external environmental factors. For example, users' preferences for accommodation, sensitivity to the length of the journey to scenic spots, etc. It is required that the route generation method can filter the recommended routes by user preferences (such as hotel star rating, budget range, travel time length, etc.) to generate customized routes that meet user needs.

[0004] In order to improve the accuracy of recommendations and user satisfaction, it is necessary to develop more refined route planning methods. Summary of the invention

[0005] The present invention utilizes artificial intelligence technology, sets multiple constraints, screens and filters tourist attractions, and generates tourist routes that meet personalized requirements.

[0006] The technical solution provided by the present invention is: a method for customizing tourist routes based on artificial intelligence, the method comprising:

[0007] Acquire the user's travel demand information; extract the travel location, travel start time, travel end time and accommodation demand from the travel demand information; crawl relevant travel routes from the Internet through crawler technology, screen out travel routes related to the travel location, and form a preliminary travel route database; calculate and obtain the travel time period based on the travel start time and travel end time, and predict the congestion level of attractions in the travel route during the travel time period; remind the user to change the travel time period based on the congestion level, and output a recommended travel itinerary, and regenerate a recommended route that matches the travel itinerary based on user feedback; crawl hotel information related to accommodation needs from the Internet through crawler technology, screen out hotels related to accommodation needs, and form a hotel database; obtain the distance between each hotel in the hotel database and different attractions, optimize the order of visiting attractions in the recommended route, and generate the final travel route.

[0008] Preferably, the crawling technology is used to crawl relevant tourist routes from the network, and the tourist routes related to tourist locations are screened out to form a preliminary tourist route database, including:

[0009] Identify tourist location information in tourist demand information; based on the tourist location information, capture tourist routes related to the tourist location information from tourist websites; extract information on each tourist attraction from the related tourist routes, wherein the information on the tourist attractions includes at least the name of the attraction, the location of the attraction, the price information of the attraction ticket, and the ticket reservation status information, and generate a list of tourist attractions; store the tourist route information and the tourist attraction list locally to form a tourist route database.

[0010] Preferably, the method of calculating and obtaining the travel time period according to the travel start time and the travel end time, and predicting the degree of crowding of scenic spots within the travel route during the travel time period, includes:

[0011] Convert the travel start time data and the travel end time data into a numerical date format, remove the digits representing the year, and obtain the travel start date and the travel end date;

[0012] Calculate the total number of travel days; obtain a list of tourist attractions from the travel route database;

[0013] Acquire the historical ticket reservation status information of each scenic spot in the tourist attraction list from the tourist website; the ticket reservation status information includes the total number of tickets, the number of reserved tickets and the crowded state of the scenic spot, and the crowded state of the scenic spot includes crowded and not crowded; encode the crowded state, crowded is 1, and not crowded is 0;

[0014] The historical ticket reservation status information for the same period is the previous ticket reservation status information within the time period from the travel start date to the travel end date. Ticket reservation status information for attractions in the year;

[0015] Extract key feature values ​​from the historical ticket booking status of the same period to form a key feature vector: ,in, For the front Annual attractions Total number of tickets during the travel period, For the front Annual attractions The number of tickets booked during the travel period, For the front Annual attractions The ratio of the number of tickets booked during the travel period to the total number of tickets. ;

[0016] Multiple key feature vectors constitute a key feature set , after normalization, the key feature set and the crowded status of the scenic spot are combined into a sample set, and the sample set is divided into a training set and a validation set;

[0017] Building a predictive model: ,in is the intercept, is the error term, Represents the regression coefficient; the prediction model is trained through the training set, and the prediction model performance is verified through the validation set;

[0018] if , then the scenic spot is judged to be crowded; if , then the scenic spot is judged to be uncrowded.

[0019] Preferably, the step of reminding the user to change the travel time period according to the congestion level and outputting a suggested travel itinerary includes:

[0020] Obtain the user's travel start date and travel end date; obtain a list of tourist attractions from the travel route database; crawl from the travel website the ticket reservation status information for each attraction within one month in the list of tourist attractions that include the travel start date and travel end date;

[0021] The ticket reservation status information within the travel period is obtained, pre-processed and normalized, and then input into the prediction model to output the predicted value of the crowded state of the scenic spot, so as to predict the crowded state of the scenic spot within the travel period;

[0022] If the prediction result is congestion, a sliding window is set, starting from the end date of the tour, and the sliding window is moved to reselect new ticket reservation status information within the same length of the tour period;

[0023] After preprocessing and normalizing, the acquired new ticket reservation status information is input into the prediction model, and the predicted value of the crowded state of the scenic spot is output to predict the crowded state of the scenic spot;

[0024] If the prediction result is congestion, move the sliding window again, select new ticket booking status information within the same length of travel time, and then repeat the previous step;

[0025] If the prediction result is not crowded, the date information corresponding to the starting point of the sliding window is obtained and output to the user end; the user is advised to adjust the start time of the trip.

[0026] Preferably, the regenerating a suggested route matching the travel itinerary according to user feedback includes:

[0027] Obtaining user feedback information; the user feedback information includes agreement or disagreement;

[0028] If the user feedback information is consent, a list of tourist attractions is obtained and pushed to the user end;

[0029] If the user feedback information is disagreement, then obtain a list of tourist attractions and obtain a predicted value of the congestion status of each attraction, arrange the order of the attractions on the tourist attractions list in descending order of the predicted values, generate a new list of tourist attractions; and push the new list of tourist attractions to the user end.

[0030] Preferably, the crawling technology is used to crawl hotel information related to accommodation needs from the network, and hotels related to accommodation needs are screened out to form a hotel database, including:

[0031] Obtain the travel start time and the travel end time; obtain the user's accommodation needs, which at least include room type needs and the area to which the hotel belongs; crawl from the travel website the information of all hotels that meet the accommodation needs between the travel start time and the travel end time; extract the hotel name and hotel address from the hotel information to form a hotel database.

[0032] Preferably, the step of obtaining the distance between each hotel in the hotel database and different scenic spots, optimizing the order of visiting scenic spots in the suggested route, and generating the final tourist route includes:

[0033] Acquire hotel names and hotel addresses of multiple hotels from a hotel database to form a hotel list; push the hotel list to a user terminal, and acquire user feedback data from the user terminal, wherein the user feedback data includes the number of clicks, browsing time, and payment data of each hotel;

[0034] Get a list of tourist attractions; extract some hotel information from the hotel list based on user feedback data to form a new hotel list; calculate the distance between each hotel in the new hotel list and each attraction in the tourist attractions list to form a distance vector of the hotel ,in, Indicates The hotel names are uniquely encoded. Indicates The unique hot encoding of the names of the attractions, Indicates Hotels to The distance to the attractions, , ,in Respectively represent the total number of scenic spots and the total number of hotels; the distance vectors of multiple hotels constitute the distance vector set ; Calculate the average distance between each hotel and all attractions in the new tourist attraction list ; ; Obtain the hotel information corresponding to the smallest average distance, mark the hotel information as a good hotel, and then push it to the user end, and receive user confirmation information; according to the user confirmation information, rearrange the order of attractions in the new tourist attraction list according to the distance principle, generate a tourist route, and push it to the user end; or re-capture tourist attraction information.

[0035] Preferably, the step of rearranging the order of the attractions in the new tourist attraction list according to the distance principle to generate a tourist route includes:

[0036] Obtain a list of tourist attractions; according to the list of tourist attractions, obtain the distance of each attraction in the list of tourist attractions from the preferred hotel from the distance vector, and adjust the order of the attractions in the list of tourist attractions in ascending order of distance, so as to generate a tourist route.

[0037] The present invention also provides an electronic device, which is used to execute the artificial intelligence-based travel route customization method.

[0038] The present invention also provides a computer-readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the artificial intelligence-based travel route customization method.

[0039] Beneficial effects of the present invention:

[0040] 1. The present invention extracts key elements from the information provided by the user, uses crawler technology to collect relevant travel route information from the Internet, and screens out routes related to the tourist destinations specified by the user to form a preliminary database. The prediction model is used to evaluate the congestion level of each scenic spot during this time period, and the user is reminded to change the time or provide travel itinerary suggestions to avoid peak periods. Then, based on the user's feedback, the travel route that matches the user's needs is adjusted and regenerated. And the hotel database is constructed based on the user's accommodation needs. The distance between each hotel and the scenic spot in the hotel database is analyzed to optimize the order of visiting the scenic spots in the tourist route. Combined with user preferences, the congestion level of the scenic spot, the accommodation location and the order of visiting, the final personalized tourist route is generated to improve the comfort and satisfaction of the travel experience.

[0041] 2. The present invention uses crawler technology to crawl ticket reservation status data for each scenic spot in the scenic spot list within one month within the range of the start date and end date of the tour from the travel website, inputs it into the trained prediction model, and outputs the predicted value of the crowded state of the scenic spot during the travel period. If the prediction result shows that the scenic spot will be in a crowded state, set a sliding window, take the end date of the tour as the starting point, move the window backward to select a new travel period of the same length, and re-catch the ticket reservation status information in this new period, input it into the prediction model again, and output a new predicted value of the crowded state of the scenic spot. If the result still shows crowded, continue to adjust the sliding window until the prediction result is not crowded. When the prediction result shows that the scenic spot is no longer crowded, record the date information corresponding to the starting point of the sliding window at this time, and recommend this date to the user as the new travel start time, so that the user can arrange the itinerary.

[0042] 3. The present invention tracks the user's feedback data after displaying the hotel list to the user, and selects several hotels that the user is most interested in based on the user's feedback data to form a new hotel list. For each hotel in the new hotel list, calculate its distance to each scenic spot in the list of tourist attractions, and obtain its average distance to all scenic spots to evaluate the overall convenience of the hotel to the scenic spot. Find the hotel with the smallest average distance, mark it as an "excellent hotel" and recommend it to the user. Send the recommended excellent hotel information to the user and wait for the user's confirmation. Once the user's confirmation is obtained, re-optimize the order of visiting tourist attractions according to the distance principle, generate the final travel route, and push it to the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A flow chart of a method for customizing a tourist route based on artificial intelligence according to the present invention;

[0044] Figure 2 The present invention optimizes the order of visiting scenic spots in the recommended route according to the distance between each hotel and different scenic spots in the hotel database, and generates a flowchart of the final tourist route. DETAILED DESCRIPTION

[0045] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0046] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0047] refer to Figure 1-2 The present invention provides a technical solution: a method for customizing tourist routes based on artificial intelligence, comprising:

[0048] Obtain the user's travel demand information. Extract the travel location, travel start time, travel end time and accommodation demand from the travel demand information.

[0049] Use crawler technology to crawl relevant tourist routes from the Internet, screen out tourist routes related to tourist destinations, and form a preliminary tourist route database. The specific steps are as follows:

[0050] Identify the tourist location information in the tourist demand information; crawl the tourist routes related to the tourist location information from the tourist website according to the tourist location information; extract the information of each tourist attraction from the related tourist routes. The information of tourist attractions at least includes the name of the attraction, the location of the attraction, the price information of the attraction ticket and the ticket reservation status information, and generate a list of tourist attractions; store the tourist route information and the list of tourist attractions locally to form a tourist route database.

[0051] According to the travel start time and travel end time, calculate the travel time period and predict the crowding degree of scenic spots within the travel route during the travel time period. The specific steps are as follows:

[0052] Convert the travel start time data and the travel end time data into a date format in numerical form, remove the digits representing the year, and obtain the travel start date and the travel end date; calculate and obtain the total number of travel days; obtain a list of tourist attractions from a travel route database; obtain the historical ticket reservation status information of each attraction in the tourist attraction list from a travel website; the ticket reservation status information includes the total number of tickets, the number of reserved tickets, and the crowded status of the attraction, and the crowded status of the attraction includes crowded and not crowded; encode the crowded status, crowded is 1, and not crowded is 0.

[0053] Remind users to change travel time periods based on the degree of congestion, and output a recommended travel itinerary. Based on user feedback, regenerate a recommended route that matches the travel itinerary. Specifically, the following steps are included: convert the travel start time data and the travel end time data into a numerical date format, remove the digits representing the year, and obtain the travel start date and travel end date.

[0054] Calculate and obtain the total number of travel days; obtain a list of tourist attractions from a travel route database; obtain the historical ticket reservation status information of each attraction in the list of tourist attractions from a travel website; the ticket reservation status information includes the total number of tickets, the number of reserved tickets and the crowded status of the attraction, and the crowded status of the attraction includes crowded and not crowded; encode the crowded status, crowded is 1, and not crowded is 0.

[0055] The historical ticket reservation status information for the same period is the previous ticket reservation status information within the time period from the travel start date to the travel end date. Ticket reservation status information for attractions in the year.

[0056] Extract key feature values ​​from the historical ticket booking status of the same period to form a key feature vector: ,in, For the front Annual attractions Total number of tickets during the travel period, For the front Annual attractions The number of tickets booked during the travel period, For the front Annual attractions The ratio of the number of tickets booked during the travel period to the total number of tickets. .

[0057] Multiple key feature vectors constitute a key feature set , after normalization, the key feature set and the crowded status of the scenic spot are combined into a sample set, and the sample set is divided into a training set and a validation set;

[0058] Building a predictive model: ,in is the intercept, is the error term, Represents the regression coefficient; the prediction model is trained through the training set, and the prediction model performance is verified through the validation set.

[0059] if , then the scenic spot is judged to be crowded; if , then the scenic spot is judged to be uncrowded.

[0060] Obtain the user's travel start date and travel end date; obtain a list of tourist attractions from the travel route database; crawl from the travel website the ticket reservation status information of each attraction in the list of tourist attractions within the travel start date and travel end date within one month; obtain the ticket reservation status information within the travel time period, preprocess and normalize it, input it into the prediction model, and output the predicted value of the crowded status of the attraction, so as to predict the crowded status of the attraction within the travel time period.

[0061] If the prediction result is congestion, a sliding window is set, starting from the end date of the tour, and the sliding window is moved to reselect new ticket reservation status information within the same length of the tour period.

[0062] The new ticket reservation status information is preprocessed and normalized, and then input into the prediction model to output the predicted value of the crowded state of the scenic spot and predict the crowded state of the scenic spot.

[0063] If the prediction result is congestion, take the end point of the sliding window as the starting point, move the sliding window backward again, select new ticket booking status information within the same length of travel time period, and then repeat the previous step until a travel time period with acceptable congestion is found.

[0064] If the prediction result is not crowded, the date information corresponding to the starting point of the sliding window is obtained and output to the user end; the user is advised to adjust the travel start time, and the user adjusts the travel itinerary according to the suggested time.

[0065] The user can choose to agree or disagree with the recommended travel start time. If the user agrees, a list of tourist attractions will be obtained and pushed to the user for confirmation, and the subsequent travel route optimization will continue. If the user disagrees, the list of tourist attractions will be obtained again, and the predicted value of the congestion status of each attraction will be obtained. If the user disagrees, the system will sort the list of attractions in descending order according to the predicted value of the congestion status of the attractions, so as to give priority to recommending attractions with less congestion, thereby generating a new optimized list of tourist attractions. This new list of tourist attractions will be pushed to the user end for the user to view and make further travel plan decisions.

[0066] Step 6: Use crawler technology to crawl hotel information related to accommodation needs from the Internet, screen out hotels related to accommodation needs, and form a hotel database, which specifically includes the following steps:

[0067] Acquire the travel start time and travel end time. Acquire the user's accommodation needs, which at least include room type needs and the hotel's area.

[0068] The information of all hotels that meet the accommodation needs between the travel start time and the travel end time is captured from the travel website; the hotel name and hotel address are extracted from the hotel information to form a hotel database.

[0069] Step 7: Obtain the distance between each hotel in the hotel database and different scenic spots, optimize the order of visiting scenic spots in the recommended route, and generate the final travel route, which specifically includes the following steps:

[0070] Acquire hotel names and hotel addresses of multiple hotels from a hotel database to form a hotel list; push the hotel list to a user terminal and acquire user feedback data from the user terminal, wherein the user feedback data includes the number of clicks, browsing time and payment data of each hotel; acquire a list of tourist attractions; extract a number of hotel information from the hotel list according to the user feedback data to form a new hotel list.

[0071] Calculate the distance between each hotel in the new hotel list and each attraction in the tourist attraction list to form the distance vector of the hotel ,in, Indicates The hotel names are uniquely encoded. Indicates The unique hot encoding of the names of the attractions, Indicates Hotels to The distance to the attractions, , ,in Respectively represent the total number of scenic spots and the total number of hotels; the distance vectors of multiple hotels constitute the distance vector set ; Calculate the average distance between each hotel and all attractions in the new tourist attraction list ; .

[0072] Get the hotel information corresponding to the smallest average distance, mark the hotel information as a preferred hotel, and then push it to the user end, and receive the user's confirmation information; get the user's confirmation information, including the user's choice of recommended hotels and the final decision on the travel date. Based on the user's choice, re-acquire or update the list of tourist attractions to ensure that all attractions are what the user wants to visit. For the preferred hotel that the user has confirmed, calculate the distance from the hotel to each attraction in the list of tourist attractions. Sort the attractions from small to large according to the calculated distance. In this way, the attractions closest to the hotel will be at the front of the list, and the farthest attractions will be at the end. Generate the final travel route based on the order of attractions after distance sorting. This route will ensure that tourists can visit attractions in the most efficient way and reduce the time on the road. Push the generated travel route to the user end so that the user can view and confirm the final travel plan. If necessary, such as if the user requires to update or change certain attractions, the latest tourist attraction information can be re-captured and the above process can be repeated to meet the user's needs.

[0073] The present invention also provides an electronic device, which is used to execute the fault detection and self-healing method of the polymorphic fusion low-voltage intelligent switch.

[0074] The present invention also provides a computer-readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the artificial intelligence-based travel route customization method.

[0075] It should be noted that the current monitoring model and the voltage monitoring model in this embodiment are both pre-trained.

[0076] The embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. The embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by the central processing unit (CPU), the above-mentioned functions defined in the method of the present application are executed. It should be noted that the above-mentioned computer-readable medium of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of an electrical, magnetic, optical, electromagnetic, infrared segment, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wire segments, a portable computer 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. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, electrical wire, optical cable, RF, etc., or any suitable combination of the foregoing.

[0077] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0078] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be deformed or modified in any way.

Claims

1. A tourist route customization method based on artificial intelligence, characterized in that: The method comprises: Obtain users' travel demand information; Extracting travel location, travel start time, travel end time and accommodation demand from travel demand information; Use crawler technology to crawl relevant tourist routes from the Internet, screen out tourist routes related to tourist destinations, and form a preliminary tourist route database; According to the travel start time and travel end time, calculate and obtain the travel time period, and predict the crowding degree of scenic spots within the travel route during the travel time period; specifically including: Convert the travel start time data and the travel end time data into a date format in numerical form, remove the digits representing the year, and obtain the travel start date and the travel end date; calculate and obtain the total number of travel days; obtain a list of tourist attractions from the travel route database; obtain the historical ticket reservation status information of each attraction in the tourist attraction list from the travel website; the ticket reservation status information includes the total number of tickets, the number of reserved tickets and the crowded status of the attraction, and the crowded status of the attraction includes crowded and not crowded; encode the crowded status, crowded is 1, and not crowded is 0; the historical ticket reservation status information is the previous time period from the travel start date to the travel end date. The ticket booking status information of the scenic spots in 2017; extract the key feature values ​​from the ticket booking status of the same period in history to form the key feature vector: ,in, For the front Annual attractions Total number of tickets during the travel period, For the front Annual attractions The number of tickets booked during the travel period, For the front Annual attractions The ratio of the number of tickets booked during the travel period to the total number of tickets. ; Multiple key feature vectors constitute a key feature set , normalize the key feature set and the crowded state of the scenic spot to form a sample set, and divide the sample set into a training set and a validation set; build a prediction model: ,in is the intercept, is the error term, Represents the regression coefficient; the prediction model is trained through the training set, and the prediction model performance is verified through the validation set; if , then the scenic spot is judged to be crowded; if , then the scenic spot is judged to be uncrowded; Remind users to change travel time periods based on the degree of congestion, output recommended travel itineraries, and regenerate recommended routes that match the travel itinerary based on user feedback; Using crawler technology to crawl hotel information related to accommodation needs from the Internet, filter out hotels related to accommodation needs, and form a hotel database; Get the distance between each hotel in the hotel database and different attractions, optimize the order of visiting attractions in the recommended route, and generate the final travel route.

2. The method for customizing a tourist route based on artificial intelligence according to claim 1, characterized in that: The crawler technology is used to crawl relevant tourist routes from the network, and the tourist routes related to tourist destinations are screened out to form a preliminary tourist route database, including: Identify tourist location information in tourist demand information; According to the tourist location information, the tourist routes related to the tourist location information are captured from the tourist website; Extracting information of each tourist attraction from the relevant tourist routes, wherein the information of the tourist attraction at least includes the name of the attraction, the location of the attraction, the price information of the attraction ticket and the ticket reservation status information, and generating a list of tourist attractions; The tourist route information and tourist attraction list are stored locally to form a tourist route database.

3. The method for customizing a tourist route based on artificial intelligence according to claim 2, characterized in that: The method of reminding the user to change the travel time period according to the congestion level and outputting a recommended travel itinerary includes: Get the user's travel start date and travel end date; Get a list of tourist attractions from the tourist route database; Capture the ticket booking status information of each attraction in the list of tourist attractions within the travel start date and travel end date from the travel website within one month; The ticket reservation status information within the travel period is obtained, pre-processed and normalized, and then input into the prediction model to output the predicted value of the crowded state of the scenic spot, so as to predict the crowded state of the scenic spot within the travel period; If the prediction result is congestion, a sliding window is set, starting from the end date of the tour, and the sliding window is moved to reselect new ticket reservation status information within the same length of the tour period; After preprocessing and normalizing, the acquired new ticket reservation status information is input into the prediction model, and the predicted value of the crowded state of the scenic spot is output to predict the crowded state of the scenic spot; If the prediction result is congestion, move the sliding window again, select new ticket booking status information within the same length of travel time, and then repeat the previous step; If the prediction result is not crowded, the date information corresponding to the starting point of the sliding window is obtained and output to the user end; Users are advised to adjust the travel start time.

4. The method for customizing a tourist route based on artificial intelligence according to claim 3, characterized in that: The regenerating a suggested route matching the travel itinerary according to user feedback includes: Obtaining user feedback information; the user feedback information includes agreement or disagreement; If the user feedback information is consent, a list of tourist attractions is obtained and pushed to the user end; If the user feedback information is disagreement, then obtain a list of tourist attractions, obtain a predicted value of the congestion status of each tourist attraction, arrange the order of the attractions on the list of tourist attractions in descending order of the predicted values, and generate a new list of tourist attractions; Push the new list of tourist attractions to the user end.

5. The method for customizing a tourist route based on artificial intelligence according to claim 4, characterized in that: The crawler technology is used to crawl hotel information related to accommodation needs from the network, and hotels related to accommodation needs are screened out to form a hotel database, including: Get the travel start time and travel end time; Acquiring the user's accommodation requirements, where the accommodation requirements at least include room type requirements and the area to which the hotel belongs; Capture information of all hotels that meet accommodation needs between the travel start time and the travel end time from the travel website; The hotel name and hotel address are extracted from the hotel information to form a hotel database.

6. The method for customizing a tourist route based on artificial intelligence according to claim 5, characterized in that: The method of obtaining the distance between each hotel in the hotel database and different scenic spots, optimizing the order of visiting scenic spots in the recommended route, and generating the final travel route includes: Acquire hotel names and hotel addresses of a plurality of hotels from a hotel database to form a hotel list; Pushing the hotel list to the user end and obtaining user feedback data from the user end, the user feedback data including the number of clicks, browsing time and payment data of each hotel; Get a list of tourist attractions; According to the user feedback data, extract some hotel information from the hotel list to form a new hotel list; Calculate the distance between each hotel in the new hotel list and each attraction in the tourist attraction list to form the distance vector of the hotel ,in, Indicates The hotel names are uniquely encoded. Indicates The unique hot encoding of the names of the attractions, Indicates Hotels to The distance to the attractions, , ,in Respectively represent the total number of scenic spots and the total number of hotels; the distance vectors of multiple hotels constitute the distance vector set Calculate the average distance between each hotel and all attractions in the new tourist attraction list ; ; Obtain the hotel information corresponding to the smallest average distance, mark the hotel information as a good hotel, push it to the user, and receive confirmation information from the user; According to the user confirmation information, the order of the attractions in the new tourist attraction list is rearranged according to the distance principle, a tourist route is generated, and pushed to the user end; or the tourist attraction information is re-captured.

7. The method for customizing a tourist route based on artificial intelligence according to claim 6, characterized in that: The step of rearranging the order of the attractions in the new tourist attraction list according to the distance principle to generate a tourist route includes: Get a list of tourist attractions; According to the list of tourist attractions, the distance between each attraction in the list of tourist attractions and the preferred hotel is obtained from the distance vector, and the order of the attractions in the list of tourist attractions is adjusted in ascending order of distance, so as to generate a tourist route.

8. An electronic device, characterized in that: The electronic device is used to execute the artificial intelligence-based travel route customization method described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the artificial intelligence-based travel route customization method described in any one of claims 1 to 7.

Images