Tourism strategy integration method and system based on big data

Abstract

The invention relates to the field of tourism strategies, and discloses a tourism strategy integration method and system based on big data, and the method comprises the steps: firstly collecting scenic spot strategy information, and carrying out the classification according to different scenic spots, and obtaining a preliminary tourism strategy classification; inputting into a large language segmentation model, and carrying out semantic segmentation to obtain a travel strategy character string; synonym replacement is carried out on the tourist attraction strategy information, keyword extraction is carried out, and tourist strategy keywords are obtained; carrying out reservation travel strategy binding, and controlling the number of people; recording the number of tourists bound with the reserved travel strategy in real time to obtain a scenic spot visitor flow overall fluctuation curve graph; performing analysis according to the historical scenic spot visitor flow rate fluctuation curve graph to obtain scenic spot visitor flow rate prediction data; the problems that in the prior art, travel strategies are single, targeted strategy integration of small scenic spots does not exist, people need to actively find tourists in the same scenic spot group at the same time offline, and the tourist flow is not monitored and estimated in detail are solved.

Description

Technical Field

[0001] The present invention relates to the field of travel guides, and particularly to a method and system for integrating travel guides based on big data. Background Art

[0002] With the improvement of people's living standards and the pursuit of high-quality life, leisure travel has become one of the main ways for people to relax and enjoy life. However, since the number of people traveling together most of the time is not the same as the number of people for relevant travel projects, it will cause a lot of inconvenience. For example, on transportation, due to the inability to find fellow passengers for carpooling, traffic resources are wasted.

[0003] Currently, since the travel guides for many tourist attractions are a whole and there are no travel guides for individual small scenic spots, tourists need to cut out the guides for small scenic spots by themselves and then combine multiple travel guides to obtain the travel guide they want. Moreover, after obtaining the travel guide, since the number of travel companions is not necessarily the optimal number of tourists, and it is very difficult to find tourists who want to go to the same scenic spot at the same time period, the travel experience is very poor. Therefore, a method that can cut and integrate travel guides, automatically form groups by tourists' reservation time and scenic spots, and can predict the tourist flow of scenic spots based on the automatically formed group data is very necessary. Summary of the Invention

[0004] The present invention aims to provide a method and system for integrating travel guides based on big data to solve the problems in the prior art that travel guides are single, there is no targeted integration of guides for small scenic spots, tourists need to actively find fellow tourists for the same scenic spot at the same time offline, and there is no detailed monitoring and estimation of tourist flow.

[0005] To achieve the above object, the present invention provides the following method: A method for integrating travel guides based on big data provided by the present invention is as follows: S1: Collect the scenic spot guide information of each tourist attraction, classify the scenic spot guide information according to different scenic spots to obtain a preliminary classification of travel guides; S2: Input the scenic spot guide information of the preliminary classification of travel guides into a large language segmentation model for semantic segmentation to obtain travel guide segmentation fields, and integrate the travel guide segmentation fields to obtain a travel guide string; S3: Perform synonym replacement on the scenic spot guide information and extract keywords from the travel guide segmentation fields to obtain travel guide keywords; S4: Associate the travel guide keywords with intelligent terminals for binding reserved travel guides, and control the number of bindings of the reserved travel guides according to the actual situation of tourist attractions; S5: Record the number of tourists bound to the reserved travel guide in real time, and conduct a statistical summary of the number of people at the corresponding tourist attractions to obtain an overall fluctuation curve of the tourist flow at the attractions; S6: Analyze the changes in the tourist flow at the attractions under different weather conditions and different travel times based on the historical fluctuation curve of the tourist flow at the attractions to obtain the predicted data of the tourist flow at the attractions.

[0006] Preferably, the step of collecting the scenic spot guide information of each tourist attraction and classifying the scenic spot guide information according to different scenic spots to obtain the preliminary classification of the travel guide includes: collecting the scenic spot guide information of each tourist attraction, where the scenic spot guide information includes all the scenic spot guide information from leaving for the tourist attraction to leaving the tourist attraction; classifying the scenic spot guide information according to the travel time spent on the journey between the location of the scenic spot and the adjacent scenic spot as the division criterion to obtain the preliminary classification of the travel guide; if the travel time spent on the journey between the location of the scenic spot and the adjacent scenic spot is greater than 1 / 12 day, then divide this scenic spot and the adjacent scenic spot into two tourist attractions; if the travel time spent on the journey between the location of the scenic spot and the adjacent scenic spot is less than 1 / 12 or equal to 1 / 12 day, then divide this scenic spot and the adjacent scenic spot into one tourist attraction.

[0007] Preferably, the training process of the large language segmentation model is as follows: construct the large language segmentation model according to the network tourism-related vocabulary; formulate the segmentation rules of the large language segmentation model according to the travel time, travel duration, and weather forecast conditions during the travel, and segment the string according to different travel times, travel durations, and weather forecast conditions during the travel; split the string input into the large language segmentation model into tourism-related vocabulary and meaningless vocabulary.

[0008] Preferably, the step of inputting the scenic spot guide information of the preliminary classification of the travel guide into the large language segmentation model for semantic segmentation to obtain the travel guide segmentation field and integrating the travel guide segmentation field to obtain the travel guide string includes: inputting the scenic spot guide information of the preliminary classification of the travel guide into the large language segmentation model, classifying the scenic spot guide information according to the secondary scenic spot location of the tourist attraction to obtain the secondary tourist attraction guide; performing a semantic segmentation process on the secondary tourist attraction guide according to the tourism-related vocabulary and the meaningless vocabulary, marking the tourism-related vocabulary in the secondary tourist attraction guide as the travel guide segmentation field, and marking the meaningless vocabulary in the secondary tourist attraction guide as the irrelevant field; integrating the travel guide segmentation field and the irrelevant field into a string to obtain the travel guide string.

[0009] Preferably, the steps of performing synonym replacement on the travel attraction strategy information and extracting keywords from the travel strategy segmentation fields to obtain travel strategy keywords include: extracting keywords from the travel strategy segmentation fields and extracting the vocabulary associated with the corresponding travel attractions; collecting the vocabulary associated with the travel attractions that belong to the same category in multiple preliminary travel strategy classifications, and judging through an intelligent semantic recognition system whether the meanings of the vocabulary associated with the travel attractions in different travel strategies in the same preliminary travel strategy classification are the same / similar, unifying the vocabulary associated with the travel attractions, and performing synonym replacement; if the meanings of the vocabulary associated with the travel attractions are the same / similar, replacing the vocabulary associated with the travel attractions with the vocabulary associated with the travel attractions that appears most frequently in the scenic spot travel strategy; marking the vocabulary associated with the travel attractions that appears most frequently in the scenic spot travel strategy as travel strategy keywords.

[0010] Preferably, the steps of associating the travel strategy keywords with intelligent terminals, performing reservation travel strategy binding, and controlling the number of people for the reservation travel strategy binding according to the actual situation of the travel attraction include: associating the travel strategy keywords with intelligent terminals and performing reservation travel strategy binding; providing free group reservation with a fixed number of people for tourists according to the transportation mode, play mode, and play time period of the travel attraction, and tourists make travel strategy and corresponding travel time period reservations according to the selected strategy for the corresponding travel attraction; when each travel strategy meets the free group reservation with a fixed number of people, a new free group reservation with a fixed number of people is made; and controlling according to the actual situation of the travel attraction, the number of free group reservations with a fixed number of people in the same time period, and controlling the number of people for the reservation travel strategy binding.

[0011] Preferably, the steps of recording the number of tourists bound to the reservation travel strategy in real time include: when each travel strategy meets the free group reservation with a fixed number of people, recording the number of people in one unit; statistically recording the number of people in one unit according to different time periods of each year and different time periods of each day; establishing an annual scenic spot passenger flow fluctuation curve based on the number of people in one unit recorded in different time periods of each year, and establishing a daily scenic spot passenger flow fluctuation curve based on the number of people in one unit recorded in different time periods of each day.

[0012] Preferably, the steps of counting and summarizing the number of people in corresponding tourist attractions to obtain the overall fluctuation curve graph of the tourist flow of the attractions include: after establishing the annual tourist flow fluctuation curve of the attractions and the daily tourist flow fluctuation curve of the attractions, binding each corresponding node of the annual tourist flow fluctuation curve of the attractions to the corresponding daily tourist flow fluctuation curve of the attractions, integrating the data into a secondary curve graph to obtain the overall fluctuation curve graph of the tourist flow of the attractions; marking each inflection point, peak point and valley point of the overall fluctuation curve graph of the tourist flow of the attractions as the passenger flow conversion point, tourist peak point and tourist off-season point respectively; and pushing the best tourist time period for tourists through the passenger flow conversion point, tourist peak point and tourist off-season point.

[0013] Preferably, the steps of analyzing the changes in the tourist flow of the attractions under different weather conditions and different tourist times according to the historical tourist flow fluctuation curve graph of the attractions to obtain the predicted data of the tourist flow of the attractions include: analyzing the changes in the tourist flow according to the historical tourist flow fluctuation curve graph of the attractions; using the control variable method to control the different weather conditions and tourist times to collect the changes in the tourist flow of the attractions in the overall fluctuation curve graph of the tourist flow of the attractions under different conditions to obtain the analysis data of the controlled variable tourist flow; and predicting the predicted data of the tourist flow of the attractions according to the analysis data of the controlled variable tourist flow.

[0014] A tourism strategy integration system based on big data provided by the present invention is: Information collection module: collecting the scenic spot strategy information of each tourist attraction and classifying the scenic spot strategy information according to different scenic spots; Model construction module: formulating the segmentation rules of the large language segmentation model according to the tourist time, tourist duration and weather forecast conditions during the tourist period, and segmenting the character string according to different tourist times, tourist durations and weather forecast conditions during the tourist period; Keyword extraction module: performing synonym replacement on the tourist attraction strategy information and extracting keywords from the segmented fields of the tourism strategy; Strategy reservation module: providing free group reservation for a fixed number of people for tourists according to the transportation mode, play mode and play time period of the tourist attraction, and tourists making reservations for the tourism strategy and the corresponding tourism time period according to the selected strategy of the corresponding tourist attraction; Number monitoring module: when each tourism strategy meets the free group reservation of the fixed number of people, recording a number unit quantity, and counting the number unit quantity record according to different time periods of each year and different time periods of each day; Number prediction module: Using the control variable method, by controlling different weather conditions and travel times, the overall fluctuation curve of the number of visitors at scenic spots under different situations is collected, and the change of the number of visitors at scenic spots is obtained to get the control variable number of visitors analysis data. According to the control variable number of visitors analysis data, the predicted number of visitors at scenic spots is predicted.

[0015] The beneficial effects of the present invention are reflected in: by collecting the scenic spot strategy information of tourist attractions and classifying each scenic spot according to the actual distance, the present invention can make the tourist strategy into modular strategy information, making the tourist strategy more specific and not being mixed together. Then, the tourist strategy is segmented by secondary scenic spots, enabling tourists to search and reserve the corresponding tourist strategy according to their travel plans. Then, the reservation and group formation service is provided, which can save a large amount of tourism resources and personal resources, maximizing the utilization of resources. Through the tourist strategy keywords, the corresponding tourist strategy information can be quickly found for viewing and reservation, saving a large amount of search time. Then, by establishing the overall fluctuation curve of the number of visitors at scenic spots, the prediction of the tourist flow at the scenic area at the macro and micro levels is realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0017] Figure 1 It is a schematic flow chart of a method for integrating tourist strategies based on big data provided by an embodiment of the present invention; Figure 2 It is a schematic flow chart of a system for integrating tourist strategies based on big data provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] In order to enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0019] In the description, claims and the above drawings of the present invention, terms such as "first", "second", etc. are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or terminal that includes a series of steps or units is not limited to the listed steps or units, but may optionally further include steps or units not listed, or may optionally further include other steps or units inherent to these processes, methods, products or terminals.

[0020] Reference to "embodiment" herein means that a particular feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0021] Currently, since the travel guides for many tourist attractions are a whole and there are no travel guides for individual small attractions, tourists need to cut out the guides for small attractions by themselves and then combine multiple travel guides to obtain the travel guide they want. Moreover, after obtaining the travel guide, since the number of travel companions does not necessarily match the optimal number of tourists, and it is very difficult to find tourists who want to go to the same attractions at the same time period, the travel experience is very poor. Therefore, a method that can cut and integrate travel guides, automatically form groups by tourists' reserved time and attractions, and predict the tourist flow in the scenic area based on the automatically grouped data is very necessary.

[0022] The present invention aims to provide a travel guide integration method and system based on big data to solve the problems in the prior art that travel guides are single, there is no targeted integration of travel guides for small attractions, tourists need to actively find group members who go to the same attractions at the same time offline, and there is no detailed monitoring and estimation of tourist flow.

[0023] The specific embodiment of the present invention provides a travel guide integration method based on big data. The method is as Figure 1 shown and includes the following steps: S1: Collect the scenic spot guide information of each tourist attraction, classify the scenic spot guide information according to different scenic spots to obtain a preliminary classification of travel guides.

[0024] In an embodiment of the present invention, scenic spot strategy information of each tourist attraction is collected. The scenic spot strategy information includes all the scenic spot strategy information from departing for the tourist attraction to leaving the tourist attraction. The scenic spot strategy information is classified according to the travel time spent on the journey between the location of the scenic spot and the adjacent scenic spot to obtain a preliminary classification of tourist strategies. If the travel time spent on the journey between the location of the scenic spot and the adjacent scenic spot is greater than 1 / 12 day, the scenic spot and the adjacent scenic spot are divided into two tourist attractions. If the travel time spent on the journey between the location of the scenic spot and the adjacent scenic spot is less than or equal to 1 / 12 day, the scenic spot and the adjacent scenic spot are divided into one tourist attraction.

[0025] S2: Input the scenic spot strategy information of the preliminary classification of tourist strategies into the large language segmentation model for semantic segmentation to obtain tourist strategy segmentation fields, and integrate the tourist strategy segmentation fields to obtain a tourist strategy string.

[0026] In an embodiment of the present invention, the training process of the large language segmentation model is as follows: The large language segmentation model is constructed according to network tourism-related vocabulary. The segmentation rules of the large language segmentation model are formulated according to travel time, travel duration, and weather forecast conditions during the travel, and the string is segmented according to different travel times, travel durations, and weather forecast conditions during the travel. The string input into the large language segmentation model is split into tourism-related vocabulary and meaningless vocabulary. The scenic spot strategy information of the preliminary classification of tourist strategies is input into the large language segmentation model, and the scenic spot strategy information is classified according to the secondary scenic spot location of the tourist attraction to obtain a secondary tourist attraction strategy. The secondary tourist attraction strategy is semantically segmented according to tourism-related vocabulary and meaningless vocabulary. The tourism-related vocabulary in the secondary tourist attraction strategy is marked as a tourist strategy segmentation field, and the meaningless vocabulary in the secondary tourist attraction strategy is marked as an irrelevant field. The tourist strategy segmentation field and the irrelevant field are integrated into a string to obtain a tourist strategy string.

[0027] S3: Perform synonym replacement on the scenic spot strategy information and extract keywords from the tourist strategy segmentation fields to obtain tourist strategy keywords.

[0028] In an embodiment of the present invention, keyword extraction is performed on the travel guide segmentation field to extract the vocabulary associated with the corresponding tourist attractions; the tourist attraction-related vocabulary belonging to the same category in multiple preliminary travel guide classifications is collected, and the intelligent semantic recognition system is used to determine whether the meanings of the tourist attraction-related vocabulary in different travel guides in the same preliminary travel guide classification are the same / similar, and the unified tourist attraction-related vocabulary is obtained for synonym replacement; if the meanings of the tourist attraction-related vocabulary are the same / similar, the tourist attraction-related vocabulary is replaced with the tourist attraction-related vocabulary that appears most frequently in the scenic spot travel guide; the tourist attraction-related vocabulary that appears most frequently in the scenic spot travel guide is marked as the travel guide keyword.

[0029] S4: Associate the travel guide keyword with the intelligent terminal to perform the binding of the reserved travel guide, and control the number of people binding the reserved travel guide according to the actual situation of the tourist attraction.

[0030] In an embodiment of the present invention, the travel guide keyword is associated with the intelligent terminal to perform the binding of the reserved travel guide; according to the transportation mode, play mode and play time period of the tourist attraction, a free group reservation with a fixed number of people is provided for tourists, and the tourists make a reservation for the travel guide and the corresponding travel time period according to the selected travel guide of the corresponding tourist attraction; when each travel guide meets the free group reservation with a fixed number of people, a new free group reservation with a fixed number of people is made; and according to the actual situation of the tourist attraction, the number of free group reservations with a fixed number of people in the same time period is controlled, and the number of people binding the reserved travel guide is controlled.

[0031] S5: Real-time record the number of tourists binding the reserved travel guide, and perform the statistical summary of the number of people in the corresponding tourist attraction to obtain the overall fluctuation curve graph of the scenic spot traffic flow.

[0032] In an embodiment of the present invention, when each travel guide meets the free group reservation with a fixed number of people, a record of the number of people per unit is made; according to different time periods of each year and different time periods of each day, the record of the number of people per unit is statistically counted; the record of the number of people per unit in different time periods of each year is used to establish the annual scenic spot traffic flow fluctuation curve, and the record of the number of people per unit in different time periods of each day is used to establish the daily scenic spot traffic flow fluctuation curve; after establishing the annual scenic spot traffic flow fluctuation curve and the daily scenic spot traffic flow fluctuation curve, each corresponding node of the annual scenic spot traffic flow fluctuation curve is bound to the corresponding daily scenic spot traffic flow fluctuation curve, and the data is integrated into a secondary curve graph to obtain the overall fluctuation curve graph of the scenic spot traffic flow; each inflection point, peak point and valley point of the overall fluctuation curve graph of the scenic spot traffic flow are respectively marked as the traffic flow change point, tourist peak point and tourist off-season point; the best travel time period is pushed to tourists through the traffic flow change point, tourist peak point and tourist off-season point.

[0033] S6: Analyze the changes in the number of visitors to scenic spots under different weather conditions and different travel times based on the historical fluctuation curve of the number of visitors to scenic spots, and obtain the predicted data of the number of visitors to scenic spots.

[0034] In the embodiment of the present invention, analyze the changes in the number of visitors to scenic spots based on the historical fluctuation curve of the number of visitors to scenic spots; use the control variable method to control the different weather conditions and travel times to collect the overall fluctuation curve of the number of visitors to scenic spots under different conditions, and obtain the analysis data of the number of visitors with controlled variables; predict the predicted data of the number of visitors to scenic spots based on the analysis data of the number of visitors with controlled variables.

[0035] A tourism strategy integration system based on big data provided by the present invention is as Figure 2 shown: Information collection module: Collect the scenic spot strategy information of each tourist scenic spot, and classify the scenic spot strategy information according to different scenic spots; Model construction module: Formulate the segmentation rules of the large language segmentation model according to the travel time, travel duration, and weather forecast conditions during the travel period, and segment the character string according to different travel times, travel durations, and weather forecast conditions during the travel period; Keyword extraction module: Replace synonyms in the tourism scenic spot strategy information, and extract keywords from the segmented fields of the tourism strategy; Strategy reservation module: Provide free group reservation for a fixed number of people for tourists according to the transportation mode, play mode, and play time period of the tourist scenic spot. Tourists make reservations for the tourism strategy and the corresponding travel time period according to the selected strategy of the corresponding tourist scenic spot; Number monitoring module: When each tourism strategy meets the free group reservation for a fixed number of people, record a unit quantity of the number of people, and count the unit quantity record of the number of people according to different time periods of each year and different time periods of each day; Number prediction module: Use the control variable method to control the different weather conditions and travel times to collect the overall fluctuation curve of the number of visitors to scenic spots under different conditions, and obtain the analysis data of the number of visitors with controlled variables. Predict the predicted data of the number of visitors to scenic spots based on the analysis data of the number of visitors with controlled variables.

[0036] The beneficial effects of the present invention are reflected in that: by collecting the scenic spot strategy information of tourist attractions and classifying each scenic spot according to the distance in reality, the travel strategy can be made into modular strategy information, making the travel strategy more specific and not being mixed together. Then, the travel strategy is segmented by secondary scenic spots, enabling tourists to search for and reserve the corresponding travel strategy according to their travel plans. Then, the reservation group service is provided, which can save a large amount of tourism resources and personal resources, maximizing the utilization of resources. Through the travel strategy keywords, the corresponding travel strategy information can be quickly found for viewing and reservation, saving a large amount of searching time. Then, by establishing an overall fluctuation curve graph of the scenic spot population flow, the prediction of the tourist flow of the scenic area at the macro and micro levels is realized.

[0037] The above are only the embodiments of the present invention. Specific technical solutions or common knowledge such as characteristics known in the art are not described in detail herein. It should be pointed out that for those skilled in the art, without departing from the solution of the present invention, several deformations and improvements can still be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effects of the present invention and the practicality of the patent. The protection scope required by this application should be based on the content of its claims, and the specific implementation manners and the like recorded in the specification can be used to interpret the content of the claims.

Claims

1. A method for integrating travel guides based on big data, characterized in that, The method includes: S1: Collect the scenic spot strategy information of each tourist scenic spot, classify the scenic spot strategy information according to different scenic spots, and obtain a preliminary classification of tourist strategies; S2: Input the tourist scenic spot strategy information of the preliminary classification of tourist strategies into a large language segmentation model for semantic segmentation to obtain tourist strategy segmentation fields, and integrate the tourist strategy segmentation fields to obtain a tourist strategy string; S3: Replace synonyms in the tourist scenic spot strategy information, and extract keywords from the tourist strategy segmentation fields to obtain tourist strategy keywords; S4: Associate the tourist strategy keywords with intelligent terminals, perform reservation tourist strategy binding, and control the number of people bound to the reservation tourist strategy according to the actual situation of tourist scenic spots; S5: Record the number of tourists bound to the reservation tourist strategy in real time, and conduct statistical summary of the number of people in the corresponding tourist scenic spots to obtain an overall fluctuation curve graph of the scenic spot traffic flow; S6: Analyze the changes in the scenic spot traffic flow under different weather conditions and different tourist times based on the historical scenic spot traffic flow fluctuation curve graph to obtain predicted data on the tourist traffic flow of scenic spots.

2. The method for integrating travel guides based on big data according to claim 1, wherein The step of collecting the scenic spot strategy information of each tourist scenic spot, classifying the scenic spot strategy information according to different scenic spots, and obtaining a preliminary classification of tourist strategies includes: Collect the scenic spot strategy information of each tourist scenic spot, where the scenic spot strategy information includes all the scenic spot strategy information from departing to the tourist scenic spot to leaving the tourist scenic spot; Classify the scenic spot strategy information according to the travel time spent on the journey between the location of the scenic spot and adjacent scenic spots as the classification criterion to obtain a preliminary classification of tourist strategies; If the travel time spent on the journey between the location of the scenic spot and adjacent scenic spots is greater than 1 / 12 day, then divide this scenic spot and the adjacent scenic spot into two tourist scenic spots; If the travel time spent on the journey between the location of the scenic spot and adjacent scenic spots is less than or equal to 1 / 12 day, then divide this scenic spot and the adjacent scenic spot into one tourist scenic spot.

3. The method for integrating travel guides based on big data according to claim 2, wherein, The training process of the large language segmentation model is: Construct a large language segmentation model based on network tourism-related vocabulary; Formulate the segmentation rules of the large language segmentation model according to travel time, travel duration, and weather forecast conditions during the travel period, and segment the string according to different travel times, travel durations, and weather forecast conditions during the travel period; Split the string input into the large language segmentation model into tourism-related vocabulary and meaningless vocabulary.

4. A method for integrating travel guides based on big data according to claim 3, characterized in that, The step of inputting the tourist scenic spot strategy information of the preliminary classification of tourist strategies into a large language segmentation model for semantic segmentation to obtain tourist strategy segmentation fields, and integrating the tourist strategy segmentation fields to obtain a tourist strategy string includes: Input the tourist scenic spot strategy information of the preliminary classification of tourist strategies into the large language segmentation model, and classify the tourist scenic spot strategy information according to the secondary scenic spot location of the tourist scenic spot to obtain secondary tourist scenic spot strategies; Perform a semantic segmentation process on the secondary tourist attraction guide according to the tourism-related vocabulary and the meaningless vocabulary, mark the tourism-related vocabulary in the secondary tourist attraction guide as tourism guide segmentation fields, and mark the meaningless vocabulary in the secondary tourist attraction guide as irrelevant fields; Integrate the strings of the tourism guide segmentation fields and the irrelevant fields to obtain a tourism guide string.

5. The integrated method of travel guides based on big data according to claim 1, wherein The steps of performing synonym replacement on the tourist attraction guide information and extracting keywords from the tourism guide segmentation fields to obtain tourism guide keywords include: Extract keywords from the tourism guide segmentation fields and extract the vocabulary associated with the corresponding tourist attractions; Collect the tourism attraction-related vocabulary belonging to the same category in multiple preliminary tourism guide classifications, and judge through an intelligent semantic recognition system whether the meanings of the tourism attraction-related vocabulary in different tourism guides in the same preliminary tourism guide classification are the same / similar, unify the tourism attraction-related vocabulary, and perform synonym replacement; If the meanings of the tourism attraction-related vocabulary are the same / similar, replace the tourism attraction-related vocabulary with the tourism attraction-related vocabulary that appears most frequently in the scenic spot tourism guide; Mark the tourism attraction-related vocabulary that appears most frequently in the scenic spot tourism guide as tourism guide keywords.

6. The integrated method for travel guides based on big data according to claim 5, wherein The steps of associating the tourism guide keywords with intelligent terminals, performing reservation tourism guide binding, and controlling the number of people for the reservation tourism guide binding according to the actual situation of tourist attractions include: Associate the tourism guide keywords with intelligent terminals and perform reservation tourism guide binding; Provide free group reservation for a fixed number of people for tourists according to the transportation mode, play mode, and play time period of the tourist attraction. Tourists make tourism guide and corresponding tourism time period reservations according to the selected guide for the corresponding tourist attraction; When each tourism guide meets the free group reservation for the fixed number of people, make a new free group reservation for the fixed number of people; And control according to the actual situation of the tourist attraction, the number of free group reservations for the fixed number of people in the same time period, and control the number of people for the reservation tourism guide binding.

7. A method for integrating travel guides based on big data according to claim 6, characterized in that The steps of recording the number of tourists bound to the reservation tourism guide in real time include: When each tourism guide meets the free group reservation for the fixed number of people, record the number of one unit; Statistically record the number of one unit according to different time periods of each year and different time periods of each day; Establish an annual scenic spot passenger flow fluctuation curve based on the number of one unit records for different time periods of each year, and establish a daily scenic spot passenger flow fluctuation curve based on the number of one unit records for different time periods of each day.

8. A method for integrating travel guides based on big data according to claim 7, characterized in that, The steps of performing a statistical summary of the number of people for the corresponding tourist attraction to obtain an overall passenger flow fluctuation curve graph of the scenic spot include: After establishing the annual scenic spot footfall fluctuation curve and the daily scenic spot footfall fluctuation curve, bind each corresponding node of the annual scenic spot footfall fluctuation curve to the corresponding daily scenic spot footfall fluctuation curve, and integrate the data into a secondary curve graph to obtain the overall footfall fluctuation curve graph of the scenic spot; Mark each inflection point, peak point, and valley point of the overall footfall fluctuation curve graph of the scenic spot as the passenger flow conversion point, tourist peak point, and tourist off-season point respectively; Push the best travel time period for tourists through the passenger flow conversion point, tourist peak point, and tourist off-season point.

9. The integrated method of travel guides based on big data according to claim 8, wherein The step of analyzing the changes in the footfall of the scenic spot under different weather conditions and different travel times based on the historical footfall fluctuation curve graph of the scenic spot to obtain the predicted data of the footfall of tourists in the scenic spot includes: Analyze the changes in the footfall of tourists based on the historical footfall fluctuation curve graph of the scenic spot; Use the control variable method to control different weather conditions and travel times to collect the changes in the footfall of tourists in the overall footfall fluctuation curve graph of the scenic spot in different situations, and obtain the control variable footfall analysis data; Predict the predicted data of the footfall of tourists in the scenic spot based on the control variable footfall analysis data.

10. A tourism strategy integration system based on big data, characterized in that, The system includes: Information collection module: Collect the scenic spot strategy information of each tourist scenic spot, and classify the scenic spot strategy information according to different scenic spots; Model construction module: Formulate the segmentation rules of the large language segmentation model according to the travel time, travel duration, and weather forecast conditions during the travel period, and segment the string according to different travel times, travel durations, and weather forecast conditions during the travel period; Keyword extraction module: Replace synonyms in the scenic spot strategy information, and extract keywords from the segmented fields of the travel strategy; Strategy reservation module: Provide free group reservation for a fixed number of people for tourists according to the transportation method, play method, and play time period of the tourist scenic spot. Tourists make reservations for travel strategies and corresponding travel time periods according to the selected strategies of the corresponding tourist scenic spots; Number monitoring module: When each travel strategy meets the free group reservation for the fixed number of people, record a unit quantity of the number of people, and count the unit quantity records of the number of people according to different time periods of each year and different time periods of each day; Number prediction module: Use the control variable method to control different weather conditions and travel times to collect the changes in the footfall of tourists in the overall footfall fluctuation curve graph of the scenic spot in different situations, and obtain the control variable footfall analysis data. Predict the predicted data of the footfall of tourists in the scenic spot based on the control variable footfall analysis data.

Images