Agricultural tourist station site selection method, system and device and medium

Abstract

The invention discloses an agricultural tourism post site selection method, system and device and a medium, and the method comprises the steps: firstly constructing an agricultural tourism attraction-post bearing capacity comprehensive evaluation model, and then carrying out the preprocessing of POI data, mobile phone signaling data, agricultural tourism statistical data and social media data in a to-be-planned region; generating multiple items of index data in the index layer, calculating an agricultural tourism attraction index and a station bearing capacity index based on the multiple items of index data after preprocessing and the model, and according to the agricultural tourism attraction index and the station bearing capacity index, calculating the station bearing capacity index according to the agricultural tourism attraction index and the station bearing capacity index. And calculating an agricultural tourism attraction-post bearing capacity comprehensive evaluation index of each candidate post address in the to-be-planned area, finally identifying the grade of each candidate post address according to the agricultural tourism attraction-post bearing capacity comprehensive evaluation index, and outputting a site selection result. According to the invention, the site selection precision of the agricultural tourist station can be improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, system, equipment and medium for selecting sites for agricultural tourism stations. Background Technology

[0002] As a key service node connecting tourists and agricultural tourism resources, the scientific selection of agricultural tourism stations is crucial for enhancing the tourist experience, optimizing resource allocation, and promoting the sustainable development of regional agricultural tourism.

[0003] However, existing methods for selecting sites for agricultural tourism stations often focus on agricultural production itself or a single tourist attraction, lacking a systematic balance between attractiveness and carrying capacity. For example, Chinese patent CN117709621A discloses a GIS-based method for recommending sites for agricultural projects. Its core is to use historical land survey data and agricultural project data to predict suitable plots for specific agricultural projects (such as planting) through a random forest model. This method primarily focuses on the suitability of land for agricultural production but does not take into account the attractiveness of agricultural tourism resources, actual tourist travel patterns, and seasonal fluctuations in visitor flow. Furthermore, existing site selection methods often rely on single types of data, lacking the fusion and intelligent interpretation of multi-source heterogeneous data, making it difficult to quantify in real time and accurately. This prevents the construction of a comprehensive evaluation system that can respond to dynamic market changes and balance resource potential with service thresholds. For instance, Chinese patent CN116739839A discloses a remote sensing identification and attractiveness analysis method for sightseeing agricultural landscapes. It identifies crop flowering periods through remote sensing images and analyzes tourist attractiveness by combining location data. While this method addresses the issue of attractiveness, its analysis is limited to a single dimension, primarily focusing on the instantaneous attractiveness during the flowering season, and completely neglecting the carrying capacity of necessary service facilities such as parking lots, restrooms, and medical facilities at the inn. In summary, existing methods for selecting sites for agricultural tourism inns suffer from problems such as reliance on single data points, subjectivity in site selection, and low accuracy. Summary of the Invention

[0004] The purpose of this invention is to provide a method, system, equipment, and medium for selecting sites for agricultural tourism stations, thereby improving the accuracy of site selection for agricultural tourism stations.

[0005] To achieve the above objectives, the present invention provides a method for selecting sites for agricultural tourism stations, comprising: A comprehensive evaluation model for agricultural tourism attractiveness and the carrying capacity of rest stops is constructed. The model includes an objective layer, a criterion layer, and an indicator layer. The objective layer is the comprehensive evaluation index for agricultural tourism attractiveness and the carrying capacity of rest stops. Preprocessing is performed on POI data, mobile signaling data, agricultural tourism statistics data, and social media data within the planning area to generate multiple indicator data in the indicator layer; The agricultural tourism attractiveness index and the station carrying capacity index are calculated based on the preprocessed multiple indicator data and the model. Based on the agricultural tourism attractiveness index and the post station carrying capacity index, calculate the comprehensive evaluation index of agricultural tourism attractiveness-post station carrying capacity for each candidate post station address in the area to be planned. The ranking of each candidate rest stop location is identified based on the comprehensive evaluation index of agricultural tourism attractiveness and rest stop carrying capacity, and the site selection results are output.

[0006] Optionally, the dimensions of the criteria layer include agricultural resource base, tourist market vitality, service facility support, research and study tours and exhibitions activity, and seasonal fluctuation resilience.

[0007] Optionally, the POI data, mobile signaling data, agricultural tourism statistics, and social media data within the planning area are preprocessed to generate multiple indicator data in the indicator layer, including: Obtain POI data, mobile signaling data, agricultural tourism statistics, and social media data within the area to be planned; The acquired POI data, mobile signaling data, agricultural tourism statistics data, and social media data are preprocessed. Based on the preprocessed POI data, generate agricultural resource baseline dimension index data and service facility support dimension index data; Data on tourist market vitality dimension indicators were generated based on preprocessed mobile signaling data and agricultural tourism statistics. Data on the activity level of study tours and exhibitions was generated based on preprocessed POI data, agricultural tourism statistics, and social media data. Seasonal fluctuation resilience dimension index data is generated based on preprocessed POI data and agricultural tourism statistics.

[0008] Optionally, the preprocessing of the POI data, the mobile signaling data, the agricultural tourism statistics data, and the social media data includes: The POI data is deduplicated using a spatial clustering algorithm to obtain the deduplicated POI data. The signaling peak value is extracted from the mobile phone signaling data to obtain the extracted mobile phone signaling data; Sentiment analysis tools were used to perform sentiment analysis on the social media data to obtain the analyzed social media data. The denoised POI data, extracted mobile signaling data, agricultural tourism statistics data, and analyzed social media data are subjected to noise reduction, normalization, and spatial registration to obtain preprocessed POI data, mobile signaling data, agricultural tourism statistics data, and social media data.

[0009] Optionally, the calculation of the agricultural tourism attractiveness index and the rest stop carrying capacity index based on the preprocessed indicator data includes: Using a 1 km × 1 km grid as the evaluation unit, the preprocessed multi-indicator data is retrieved grid by grid in the GIS engine; Based on the model, the agricultural tourism attractiveness index is calculated according to the following formula. : ; in, This represents the baseline dimension of agricultural resources. This indicates data representing indicators of tourist market vitality. This represents the data in the dimension of study tour and exhibition activity. , , They are respectively , , Weighting coefficients; Based on the model, the carrying capacity index of the rest stop is calculated according to the following formula. : ; in, This represents the data of service facility support dimension indicators. Data representing the resilience dimension of seasonal fluctuations. , They are respectively , The weighting coefficients.

[0010] Optionally, after identifying the level of each candidate rest stop location based on the comprehensive evaluation index of agricultural tourism attractiveness-rest stop carrying capacity and outputting the site selection results, the method further includes: The agricultural tourism attractiveness index and the post station carrying capacity index are seasonally adjusted according to the seasonal correction coefficient table; The seasonal correction coefficient table is generated based on the passenger flow ratio of candidate rest stop addresses in spring, summer, autumn and winter.

[0011] Optionally, the location selection result includes: The raster layers for the agricultural tourism attractiveness index, the raster layer for the inn carrying capacity index, and the raster layer for the comprehensive evaluation index of agricultural tourism attractiveness and inn carrying capacity, as well as the candidate inn address level attribute table.

[0012] To achieve the above objectives, the present invention also provides an agricultural tourism station site selection system, comprising: The model building module is used to construct a comprehensive evaluation model of agricultural tourism attractiveness and station carrying capacity; wherein, the model includes an objective layer, a criterion layer and an indicator layer, and the objective layer is the comprehensive evaluation index of agricultural tourism attractiveness and station carrying capacity; The data preprocessing module is used to preprocess POI data, mobile signaling data, agricultural tourism statistics data and social media data within the planning area to generate multiple indicator data in the indicator layer; The first index calculation module is used to calculate the agricultural tourism attractiveness index and the station carrying capacity index based on the preprocessed multiple index data and the model. The second indicator index calculation module is used to calculate the comprehensive evaluation index of agricultural tourism attractiveness and station carrying capacity of each candidate station address in the area to be planned, based on the agricultural tourism attractiveness index and the station carrying capacity index. The site selection module is used to identify the level of each candidate rest stop location based on the comprehensive evaluation index of agricultural tourism attractiveness-rest stop carrying capacity, and output the site selection results.

[0013] To achieve the above objectives, the present invention also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the agricultural tourism station site selection method as described above.

[0014] To achieve the above objectives, the present invention also provides a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform the agricultural tourism station site selection method described in any of the above embodiments.

[0015] Compared with existing technologies, this invention provides a method, system, equipment, and medium for selecting sites for agricultural tourism rest stops. By constructing a comprehensive evaluation model of agricultural tourism attractiveness and rest stop carrying capacity, it transforms subjective site selection decisions into objective quantitative scores, systematically assesses service facilities and resilience to fluctuations, and achieves a systematic balance between attractiveness and carrying capacity, thus overcoming the shortcomings of existing methods that neglect facility carrying capacity or seasonal fluctuations. By integrating multi-source heterogeneous data such as POI, mobile signaling, agricultural tourism statistics, and social media, and preprocessing them, and then calculating the agricultural tourism attractiveness index, the rest stop carrying capacity index, and the comprehensive evaluation index of agricultural tourism attractiveness and rest stop carrying capacity for each candidate rest stop address in the area to be planned, it not only outputs site selection conclusions but also directly generates dynamic, seasonally adaptive functional configuration and operation strategy suggestions, thereby improving the accuracy of agricultural tourism rest stop site selection. Attached Figure Description

[0016] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of a method for selecting the location of an agricultural tourism station provided in an embodiment of the present invention; Figure 2 This is a structural block diagram of an agricultural tourism station site selection system provided in an embodiment of the present invention; Figure 3 This is a structural block diagram of a terminal device provided in an embodiment of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] See Figure 1 , Figure 1 This is a flowchart of a method for selecting a site for an agricultural tourism station according to an embodiment of the present invention. The method includes steps S1 to S5: Step S1: Construct a comprehensive evaluation model of agricultural tourism attractiveness and station carrying capacity; wherein, the model includes a target layer, a criterion layer and an indicator layer, and the target layer is the comprehensive evaluation index of agricultural tourism attractiveness and station carrying capacity; For example, a three-tiered architecture—target layer, criterion layer, and indicator layer—is used to construct a comprehensive evaluation model for agricultural tourism attractiveness and rest stop carrying capacity. The target layer is the Agricultural Tourism Attractiveness-Rest Stop Carrying Capacity Comprehensive Evaluation Index (AIA-SCCIndex); the criterion layer includes… Five dimensions, As the agricultural resource base, To revitalize the tourist market, To support service facilities, To boost the activity of study tours and exhibitions, To assess resilience to seasonal fluctuations; the indicator layer comprises specific quantitative indicators under the criterion layer. Therefore, the indicator layer includes multiple specific indicators belonging to the five criterion layer dimensions, and these multiple specific indicators include at least the density of agricultural tourism resource points. High-grade agricultural tourism resources account for a large proportion Average annual tourist density Holiday passenger flow extremes overnight tourists Repeat visit rate Online positive review rate Parking space density Public toilet density Medical emergency point coverage Density of smart tour guide facilities 5G network coverage Frequency and density of study tours Density of agricultural product exhibition and sales points E-commerce live streaming penetration rate per capita consumption of agricultural and sideline products Seasonal extreme value ratio Seasonal variation coefficient Off-season facility utilization rate Flexible expansion capability The correspondence between the criteria layer and the indicator layer in the site selection of agricultural tourism stations, as well as the attributes of various related indicators, are shown in Table 1.

[0020] Table 1. Criterion and Indicator System for Site Selection of Agricultural Tourism Stations It is worth noting that the embodiments of the present invention adopt a three-level architecture design of target layer, criterion layer, and indicator layer. It not only clarifies the core evaluation target with the Agricultural Tourism Attractiveness-Stop Carrying Capacity Comprehensive Evaluation Index (AIA-SCC Index), but also relies on five criteria layers covering agricultural resource background, tourist market vitality, service facility support, research and study-exhibition activity, and seasonal fluctuation resilience, as well as 20 specific quantitative indicators, which can avoid the one-sidedness of single-factor evaluation. At the same time, the quantitative design of the indicator layer is connected with the subsequent AIA, SCC index calculation, and CSI coupled scoring (taking into account attractiveness and carrying capacity), which can transform traditional experience-based site selection judgments into quantifiable and verifiable scientific decisions, effectively avoiding site selection errors caused by one-way extreme values.

[0021] Step S2: Preprocess the POI data, mobile signaling data, agricultural tourism statistics data and social media data within the planning area to generate multiple indicator data in the indicator layer; In one optional embodiment, step S2 includes steps S201 to S206: Step S201: Obtain POI data, mobile signaling data, agricultural tourism statistics data, and social media data within the area to be planned; Step S202: Preprocess the POI data, the mobile signaling data, the agricultural tourism statistics data, and the social media data; Step S203: Generate agricultural resource baseline dimension index data and service facility support dimension index data based on the preprocessed POI data; Step S204: Generate tourist market vitality dimension index data based on preprocessed mobile signaling data, agricultural tourism statistics data, and social media data; Step S205: Generate study tour and exhibition activity dimension index data based on preprocessed POI data, agricultural tourism statistics and social media data; Step S206: Generate seasonal fluctuation resilience dimension index data based on preprocessed POI data and agricultural tourism statistics.

[0022] For example, step S201 includes: By fully extracting POI data for the area to be planned using map software, including eight categories of points of interest such as orchards, sightseeing farms, farmhouses, ecological landscape areas, parking lots, public toilets, medical points, and exhibition and sales points, with fields including name, coordinates, category, and business area, the data is obtained. Apply to the network operator for anonymized "48-hour holiday scenario package", output the peak daily passenger flow of a 100 m × 100 m grid, and obtain the mobile phone signaling data of the area to be planned; Obtain quarterly reports from the Culture and Tourism Bureau and the Agriculture and Rural Affairs Bureau of the area to be planned, and generate agricultural tourism statistics. We crawled check-in posts with geographical tags from multiple social media platforms, used regular expressions and keyword libraries to match "positive / negative reviews," and collected relevant data to obtain social media data.

[0023] In one optional embodiment, step S202 includes steps S2022 to S2023: Step S2021: Use a spatial clustering algorithm to remove duplicates from the POI data to obtain deduplicated POI data; Preferably, the spatial clustering algorithm is the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) spatial clustering algorithm, with parameters set as follows: =50 m.

[0024] Step S2022: Extract the signaling peak value from the mobile phone signaling data to obtain the extracted mobile phone signaling data; Step S2023: Perform sentiment analysis on the social media data using sentiment analysis tools to obtain the analyzed social media data; Preferably, the sentiment analysis tool is the SnowNLP library, a Python library for Chinese natural language processing. For example, using the SnowNLP library to perform sentiment analysis on social media text, identifying comments with a score greater than 0.6 as "positive," can automate the conversion of unstructured text data into structured evaluation metrics.

[0025] Step S2024: Denoise reduction, normalization, and spatial registration are performed on the deduplicated POI data, extracted mobile signaling data, agricultural tourism statistics data, and analyzed social media data to obtain preprocessed POI data, mobile signaling data, agricultural tourism statistics data, and social media data.

[0026] It should be noted that noise reduction requires considering the invalid information characteristics of different data sources, and removing invalid points of interest (POIs) containing keywords such as "closed" or "relocated" from the POI data (to avoid excessive density of agricultural and tourism resource points). Parking space density (Indicators related to facilities / resources are inflated), base station drift points with a moving speed >120km / h are filtered from mobile signaling data (to exclude interference from non-real tourists such as high-speed mobile devices and ensure the accuracy of indicators related to market vitality), and bot account data with a posting interval <30s and >80% text repetition are removed from social media data (to ensure online positive review rate). (Reflects genuine tourist reviews).

[0027] Normalization requires differentiated processing based on the characteristics of the indicator values, and only applies to extreme ratios of passenger flow during holidays. Seasonal extreme value ratio Seasonal variation coefficient For indicators with large spans, Z-score standardization can be used to eliminate differences in magnitude and prevent them from masking the influence of other indicators in the exponential weighting calculation. The remaining indicators can maintain their original dimensions.

[0028] The spatial matching criteria require the unification of multiple data dimensions. By using a unified CGCS2000 coordinate system projection to eliminate coordinate deviations in POI, mobile signaling, and social media data, and by resampling with a 100m raster to match the original resolution of mobile signaling, a foundation is laid for the aggregation of indicators for 1km×1km evaluation units. Time slices are divided according to the four seasons of "spring, summer, autumn, and winter" to align with the statistical data of agricultural tourism. Ultimately, this ensures a high degree of coordination among multiple data sources in terms of quality, dimensions, and statistical scope, providing high-quality data support for the subsequent calculation of the agricultural tourism attractiveness index (AIA), the station carrying capacity index (SCC), and the classification of candidate sites.

[0029] For example, agricultural resource baseline dimension index data and service facility support dimension index data are generated based on preprocessed POI data, including: All clustered POIs are statistically analyzed using a 1km×1km fishing net. Based on the calculation method of each indicator, the density of agricultural tourism resource points is generated. High-grade agricultural tourism resources account for a large proportion Parking space density Public toilet density Medical emergency point coverage Density of smart tour guide facilities 5G network coverage .

[0030] For example, tourist market vitality dimension index data is generated based on preprocessed mobile signaling data, agricultural tourism statistics, and social media data, including: Combining the average annual total number of tourists in agricultural tourism statistics with the area of ​​the evaluation unit (1km×1km grid) can also generate the average annual tourist density. For the extreme ratio of passenger flow during holidays First, sum the passenger flow data of the 100m×100m grid in the "Holiday 48 Scene Package" of mobile phone signaling to obtain the peak daily passenger flow during holidays. Then, combine this with the average annual total number of tourists in agricultural tourism statistics to calculate the average daily passenger flow (average annual total number of tourists ÷ 365). The ratio of the two is the peak passenger flow ratio during holidays. Regarding the percentage of overnight tourists The number of users who remained in the target area between 02:00 and 06:00 during the night was extracted from the preprocessed mobile signaling data. The proportion of this type of user to the total number of visitors in the area during the same period was calculated to estimate the proportion of overnight visitors. In addition, the repeat visit rate was also analyzed. Combining repeated visit records of the same anonymized device in mobile signaling data with the total number of tourists in agricultural tourism statistics, the calculation is based on "number of tourists visiting twice or more / total number of tourists"; online positive review rate. The SnowNLP library was used to perform sentiment analysis on the preprocessed social media check-in posts. Comments with a score >0.6 were identified as positive, and the results were calculated as "number of positive posts / total number of check-in posts".

[0031] For example, based on preprocessed POI data, agricultural tourism statistics, and social media data, data on the activity level of study tours and exhibitions is generated, including: Regarding the density of agricultural product sales outlets Points of interest (POIs) of type "fixed + mobile agricultural product sales points" can be extracted from the preprocessed POI data. The number of sales points within each grid (1km x 1km) can be counted, and then divided by the grid area. This is relevant to the frequency density of learning activities. The calculation is based on the total number of annual study tours in agricultural tourism statistics, divided by the area of ​​the evaluation unit; for e-commerce live streaming penetration rate... By crawling and filtering social media data, the number of agricultural business entities conducting live broadcasts within the target area was counted, and then compared with the total number of regional agricultural business entities in the agricultural tourism statistics; this was used to determine the per capita consumption of agricultural and sideline products. The numerator is the total sales of agricultural and sideline products in the agricultural tourism statistics, and the denominator is the average annual number of tourists in the statistics. The result is obtained by dividing the two.

[0032] For example, seasonal fluctuation resilience dimension index data is generated based on preprocessed POI data and agricultural tourism statistics, including: Seasonal extreme ratio With seasonal variation coefficient This was calculated using the average monthly visitor flow data for each season from agricultural tourism statistics. This is the ratio of average monthly passenger flow during peak season to average monthly passenger flow during off-peak season. This is the ratio of the standard deviation to the mean of monthly average passenger flow in each season, used to reflect the intensity of seasonal fluctuations in passenger flow; off-season facility utilization rate. Based on the facility design capacity extracted from POI data, and combined with the actual daily facility usage during the off-season from agricultural tourism statistics, the flexible expansion capacity is calculated as "off-season daily facility usage / design capacity × 100%". The total facility area within the region is obtained through POI data, and the area of ​​modular facilities that can be erected / dismantled within 48 hours is calculated by combining the data from agricultural tourism statistics with the area of ​​modular facilities that can be erected / dismantled within 48 hours. The result is calculated as "modular facility area / total facility area × 100%".

[0033] After the above preprocessing and indicator data generation, multiple indicator data can be automatically updated hourly in the form of 1 km grid results.

[0034] The grid system includes agricultural resource baseline vectors (category, grade, area), service facility support grids (density of parking spaces, toilets, medical facilities, 5G, and smart guides), and tourist market vitality indicators (average annual density, holiday extreme value ratio, overnight stay ratio, and online positive review rate).

[0035] Step S3: Calculate the agricultural tourism attractiveness index and the rest stop carrying capacity index based on the preprocessed multi-indicator data and the model. In one optional embodiment, step S3 includes: Using a 1 km × 1 km grid as the evaluation unit, the preprocessed multi-indicator data is retrieved grid by grid in the GIS engine; Based on the model, the agricultural tourism attractiveness index is calculated according to the following formula. : ; in, This represents the baseline dimension of agricultural resources. This indicates data representing indicators of tourist market vitality. This represents the data in the dimension of study tour and exhibition activity. , , They are respectively , , Weighting coefficients; preferably , , .

[0036] Based on the model, the carrying capacity index of the rest stop is calculated according to the following formula. : ; in, This represents the data of service facility support dimension indicators. Data representing the resilience dimension of seasonal fluctuations. , They are respectively , Weighting coefficients; preferably , .

[0037] For example, calling a field raster-by-raster within a GIS engine: ; ; in, The weight coefficient for the i-th indicator obtained by the combined weighting method can be obtained by combining expert scoring with entropy value method.

[0038] After calculation, a dual-band raster is output: Band1=AIA, Band2=SCC, value range 0-100 (percentage conversion has been performed for easy hierarchical interpretation).

[0039] Step S4: Calculate the comprehensive evaluation index of agricultural tourism attractiveness and station carrying capacity for each candidate station address in the area to be planned, based on the agricultural tourism attractiveness index and the station carrying capacity index. Specifically, firstly, the list of center coordinates of candidate rest stop addresses is imported. Then, using a GIS engine, the coordinates are spatially matched with AIA and SCC dual-band raster data. After locating the 1km×1km pixel containing the candidate point, the corresponding AIA and SCC values ​​are extracted. Subsequently, a linear coupling method is used, through a formula... Calculate the Comprehensive Evaluation Index (CSI) for each candidate site. It's worth noting that the formula, through the mathematical logic of geometric mean, mandates that candidate sites simultaneously possess a certain level of AIA (Attractiveness to Resources) and SCC (Supporting Capacity for Facilities). If only one index is excessively high (e.g., extremely high AIA but extremely low SCC, meaning excellent resources but insufficient facilities; or extremely high SCC but extremely low AIA, meaning excellent facilities but lack of tourist attraction), the CSI value will significantly decrease due to the weakness of the other index, effectively preventing one-way extreme values ​​from misleading site selection decisions.

[0040] Step S5: Identify the level of each candidate rest stop location based on the comprehensive evaluation index of agricultural tourism attractiveness-rest stop carrying capacity, and output the site selection results.

[0041] In one optional embodiment, the location selection result includes: Agricultural tourism attractiveness index raster layer, post station carrying capacity index raster layer, agricultural tourism attractiveness-post station carrying capacity comprehensive evaluation index raster layer, and candidate post station address level attribute table; Each raster layer has a spatial resolution of 1 km and uses the WGS84 projected coordinate system. The candidate station address level attribute table includes fields such as candidate point number, spatial coordinates, AIA value, SCC value, CSI value, comprehensive level, and recommended function configuration list.

[0042] Specifically, see Table 2, which shows the criteria for classifying each candidate station address and the corresponding operational decision semantics.

[0043] Table 2. Criteria for classifying candidate rest stop locations and corresponding operational decision semantics It is worth noting that by classifying the locations, the selection of agricultural tourism stations can be transformed from a vague judgment to a graded approach. Table 2 provides clear construction priorities, facility configuration strategies and resource investment directions for candidate station locations at different levels.

[0044] In one alternative embodiment, after step S5, the method further includes: The agricultural tourism attractiveness index and the post station carrying capacity index are seasonally adjusted according to the seasonal correction coefficient table; The seasonal correction coefficient table is generated based on the passenger flow ratio of candidate rest stop addresses in spring, summer, autumn and winter.

[0045] In summary, the agricultural tourism station site selection method provided by this invention constructs an agricultural tourism attractiveness-station carrying capacity comprehensive evaluation model, transforming subjective site selection decisions into objective quantitative scores. It systematically evaluates service facilities and resilience to fluctuations, achieving a systematic balance between attractiveness and carrying capacity, thus overcoming the shortcomings of existing methods that neglect facility carrying capacity or seasonal fluctuations. By integrating multi-source heterogeneous data such as POIs, mobile signaling, agricultural tourism statistics, and social media, and through preprocessing, and by calculating the agricultural tourism attractiveness index, the station carrying capacity index, and the agricultural tourism attractiveness-station carrying capacity comprehensive evaluation index for each candidate station address within the planning area, it not only outputs site selection conclusions but also directly generates dynamic, seasonally adaptive functional configuration and operational strategy suggestions. This solves the problems of existing methods relying on single data, low quantitative accuracy, and subjective site selection.

[0046] Based on the above method items, the present invention provides corresponding system items embodiments.

[0047] See Figure 2 , Figure 2 This is a structural block diagram of an agricultural tourism station site selection system provided in an embodiment of the present invention. The agricultural tourism station site selection system includes: Model building module 21 is used to build a comprehensive evaluation model of agricultural tourism attractiveness and station carrying capacity; wherein, the model includes a target layer, a criterion layer and an indicator layer, and the target layer is the comprehensive evaluation index of agricultural tourism attractiveness and station carrying capacity; Data preprocessing module 22 is used to preprocess POI data, mobile phone signaling data, agricultural tourism statistics data and social media data in the area to be planned, and generate multiple indicator data in the indicator layer; The first index calculation module 23 is used to calculate the agricultural tourism attractiveness index and the post station carrying capacity index based on the preprocessed multiple index data and the model. The second index calculation module 24 is used to calculate the comprehensive evaluation index of agricultural tourism attractiveness and station carrying capacity of each candidate station address in the area to be planned, based on the agricultural tourism attractiveness index and the station carrying capacity index. The site selection module 25 is used to identify the level of each candidate rest stop location based on the comprehensive evaluation index of agricultural tourism attractiveness-rest stop carrying capacity, and output the site selection results.

[0048] In one optional embodiment, the data preprocessing module 22 includes: The data acquisition unit is used to acquire POI data, mobile signaling data, agricultural tourism statistics data, and social media data within the area to be planned. The data preprocessing unit is used to preprocess the acquired POI data, mobile signaling data, agricultural tourism statistics data, and social media data. The first indicator data generation unit is used to generate agricultural resource baseline dimension indicator data and service facility support dimension indicator data based on the preprocessed POI data. The second indicator data generation unit is used to generate tourist market vitality dimension indicator data based on preprocessed mobile signaling data and agricultural tourism statistics. The third indicator data generation unit is used to generate indicator data for the study tour-exhibition activity dimension based on preprocessed POI data, agricultural tourism statistics data and social media data. The fourth indicator data generation unit is used to generate seasonal fluctuation resilience dimension indicator data based on preprocessed POI data and agricultural tourism statistics.

[0049] In one alternative embodiment, the data preprocessing unit is configured to: The POI data is deduplicated using a spatial clustering algorithm to obtain the deduplicated POI data. The signaling peak value is extracted from the mobile phone signaling data to obtain the extracted mobile phone signaling data; Sentiment analysis tools were used to perform sentiment analysis on the social media data to obtain the analyzed social media data. The denoised POI data, extracted mobile signaling data, agricultural tourism statistics data, and analyzed social media data are subjected to noise reduction, normalization, and spatial registration to obtain preprocessed POI data, mobile signaling data, agricultural tourism statistics data, and social media data.

[0050] In one optional embodiment, the first index calculation module 23 is configured to: Using a 1 km × 1 km grid as the evaluation unit, the preprocessed multi-indicator data is retrieved grid by grid in the GIS engine; Based on the model, the agricultural tourism attractiveness index is calculated according to the following formula. : ; in, This represents the baseline dimension of agricultural resources. This indicates data representing indicators of tourist market vitality. This represents the data in the dimension of study tour and exhibition activity. , , They are respectively , , Weighting coefficients; Based on the model, the carrying capacity index of the rest stop is calculated according to the following formula. : ; in, This represents the data of service facility support dimension indicators. Data representing the resilience dimension of seasonal fluctuations. , They are respectively , The weighting coefficients.

[0051] In one optional embodiment, the agricultural tourism station site selection system further includes a seasonal adjustment module for: The agricultural tourism attractiveness index and the post station carrying capacity index are seasonally adjusted according to the seasonal correction coefficient table; The seasonal correction coefficient table is generated based on the passenger flow ratio of candidate rest stop addresses in spring, summer, autumn and winter.

[0052] It should be noted that the agricultural tourism station site selection system provided in this embodiment of the invention is used to execute all the process steps of the agricultural tourism station site selection method in the above embodiment. The working principles and beneficial effects of the two are one-to-one, so they will not be described again.

[0053] This invention also provides a terminal device, such as... Figure 3 The diagram shown is a structural block diagram of a preferred embodiment of a terminal device provided by the present invention. The terminal device includes a processor 31, a memory 32, and a computer program stored in the memory 32 and configured to be executed by the processor 31. When the processor 31 executes the computer program, it implements the agricultural tourism station site selection method as described in any of the above embodiments.

[0054] In addition, embodiments of the present invention also provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the agricultural tourism station site selection method as described in any of the above embodiments.

[0055] When the processor 31 executes the computer program, it implements the steps in the above-described embodiments of the agricultural tourism station site selection method, for example... Figure 1 All steps of the agricultural tourism station site selection method shown. Alternatively, when the processor 31 executes the computer program, it implements the functions of each module in the above-described agricultural tourism station site selection system embodiment, for example... Figure 2 The functions of each module in the agricultural tourism station site selection system are shown.

[0056] Preferably, the computer program can be divided into one or more modules / units, which are stored in the memory 32 and executed by the processor 31 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the terminal device.

[0057] The processor 31 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, or the processor 31 can be any conventional processor. The processor 31 is the control center of the terminal device, connecting various parts of the terminal device through various interfaces and lines.

[0058] The memory 32 mainly includes a program storage area and a data storage area. The program storage area can store the operating system, applications required for at least one function, etc., and the data storage area can store related data, etc. In addition, the memory 32 can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, and a flash card, etc., or the memory 32 can also be other volatile solid-state storage devices.

[0059] It should be noted that the aforementioned terminal devices may include, but are not limited to, processors and memory, as will be understood by those skilled in the art. Figure 3 The structural block diagram shown is merely a structural example of the terminal device described above and does not constitute a limitation on the structure of the terminal device. The terminal device may include more or fewer components than shown, or combine certain components, or use different components.

[0060] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for selecting sites for agricultural tourism stations, characterized in that, include: A comprehensive evaluation model for agricultural tourism attractiveness and the carrying capacity of rest stops is constructed. The model includes an objective layer, a criterion layer, and an indicator layer. The objective layer is the comprehensive evaluation index for agricultural tourism attractiveness and the carrying capacity of rest stops. Preprocessing is performed on POI data, mobile signaling data, agricultural tourism statistics data, and social media data within the planning area to generate multiple indicator data in the indicator layer; The agricultural tourism attractiveness index and the station carrying capacity index are calculated based on the preprocessed multiple indicator data and the model. Based on the agricultural tourism attractiveness index and the post station carrying capacity index, calculate the comprehensive evaluation index of agricultural tourism attractiveness-post station carrying capacity for each candidate post station address in the area to be planned. The ranking of each candidate rest stop location is identified based on the comprehensive evaluation index of agricultural tourism attractiveness and rest stop carrying capacity, and the site selection results are output.

2. The method for selecting sites for agricultural tourism stations as described in claim 1, characterized in that, The dimensions of the criteria layer include agricultural resource base, tourist market vitality, service facility support, research and study tours and exhibitions activity, and seasonal fluctuation resilience.

3. The method for selecting sites for agricultural tourism stations as described in claim 2, characterized in that, The process involves preprocessing POI data, mobile signaling data, agricultural tourism statistics, and social media data within the planned area to generate multiple indicator data in the indicator layer, including: Obtain POI data, mobile signaling data, agricultural tourism statistics, and social media data within the area to be planned; The acquired POI data, mobile signaling data, agricultural tourism statistics data, and social media data are preprocessed. Based on the preprocessed POI data, generate agricultural resource baseline dimension index data and service facility support dimension index data; Data on tourist market vitality dimension indicators were generated based on preprocessed mobile signaling data and agricultural tourism statistics. Data on the activity level of study tours and exhibitions was generated based on preprocessed POI data, agricultural tourism statistics, and social media data. Seasonal fluctuation resilience dimension index data is generated based on preprocessed POI data and agricultural tourism statistics.

4. The method for selecting sites for agricultural tourism stations as described in claim 3, characterized in that, The preprocessing of the POI data, the mobile signaling data, the agricultural tourism statistics data, and the social media data includes: The POI data is deduplicated using a spatial clustering algorithm to obtain the deduplicated POI data. The signaling peak value is extracted from the mobile phone signaling data to obtain the extracted mobile phone signaling data; Sentiment analysis tools were used to perform sentiment analysis on the social media data to obtain the analyzed social media data. The denoised POI data, extracted mobile signaling data, agricultural tourism statistics data, and analyzed social media data are subjected to noise reduction, normalization, and spatial registration to obtain preprocessed POI data, mobile signaling data, agricultural tourism statistics data, and social media data.

5. The method for selecting sites for agricultural tourism stations as described in claim 1, characterized in that, The calculation of the agricultural tourism attractiveness index and the rest stop carrying capacity index based on the preprocessed indicator data includes: Using a 1 km × 1 km grid as the evaluation unit, the preprocessed multi-indicator data is retrieved grid by grid in the GIS engine; Based on the model, the agricultural tourism attractiveness index is calculated according to the following formula. : ； in, This represents the baseline dimension of agricultural resources. This indicates data representing indicators of tourist market vitality. This represents the data in the dimension of study tour and exhibition activity. , , They are respectively , , Weighting coefficients; Based on the model, the carrying capacity index of the rest stop is calculated according to the following formula. : ； in, This represents the data of service facility support dimension indicators. Data representing the resilience dimension of seasonal fluctuations. , They are respectively , The weighting coefficients.

6. The method for selecting sites for agricultural tourism stations as described in claim 5, characterized in that, After identifying the level of each candidate rest stop location based on the comprehensive evaluation index of agricultural tourism attractiveness-rest stop carrying capacity and outputting the site selection results, the method further includes: The agricultural tourism attractiveness index and the post station carrying capacity index are seasonally adjusted according to the seasonal correction coefficient table; The seasonal correction coefficient table is generated based on the passenger flow ratio of candidate rest stop addresses in spring, summer, autumn and winter.

7. The method for selecting sites for agricultural tourism stations as described in claim 1, characterized in that, The site selection results include: The raster layers for the agricultural tourism attractiveness index, the raster layer for the inn carrying capacity index, and the raster layer for the comprehensive evaluation index of agricultural tourism attractiveness and inn carrying capacity, as well as the candidate inn address level attribute table.

8. A site selection system for agricultural tourism stations, characterized in that, include: The model building module is used to construct a comprehensive evaluation model of agricultural tourism attractiveness and station carrying capacity; wherein, the model includes an objective layer, a criterion layer and an indicator layer, and the objective layer is the comprehensive evaluation index of agricultural tourism attractiveness and station carrying capacity; The data preprocessing module is used to preprocess POI data, mobile signaling data, agricultural tourism statistics data and social media data within the planning area to generate multiple indicator data in the indicator layer; The first index calculation module is used to calculate the agricultural tourism attractiveness index and the station carrying capacity index based on the preprocessed multiple index data and the model. The second indicator index calculation module is used to calculate the comprehensive evaluation index of agricultural tourism attractiveness and station carrying capacity of each candidate station address in the area to be planned, based on the agricultural tourism attractiveness index and the station carrying capacity index. The site selection module is used to identify the level of each candidate rest stop location based on the comprehensive evaluation index of agricultural tourism attractiveness-rest stop carrying capacity, and output the site selection results.

9. A terminal device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the agricultural tourism station site selection method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform the agricultural tourism station site selection method as described in any one of claims 1 to 7.

Images