Method, equipment, medium and program product for determining the tourism value of tourist roads

Abstract

The present application provides a method, device, medium and program product for determining the tourism value of a tourist highway, and relates to the field of highway information technology. The method includes: by determining a tourism value assessment model, multiple analysis indicators and the target probability distribution of each analysis indicator, generating multiple random samples according to each analysis indicator and the target probability distribution of each analysis indicator, inputting the multiple random samples into the tourism value assessment model, obtaining the initial tourism value of the tourist highway to be processed, inputting the initial tourism value, tourism resource information and corridor landscape information of the tourist highway to be processed into the tourism value determination model, and then obtaining the target tourism value output by the tourism value determination model. In this technical solution, the target tourism value of the tourist highway to be processed is determined by combining the tourism value assessment model and the tourism value determination model, thereby improving the authenticity and processing efficiency of the target tourism value.

Description

Technical Field

[0001] The present application relates to the field of highway information technology, and in particular to a method, device, medium and program product for determining the tourism value of a tourist highway. Background Art

[0002] Tourist highways refer to highways designed and built specifically for tourism purposes. They usually connect scenic spots, historical and cultural cities, nature reserves and other areas rich in tourism resources, making the originally monotonous highways blend into nature. These highways not only have transportation functions, but also focus on beautifying the landscape along the way and improving tourism service facilities to enhance tourists' travel experience.

[0003] The tourism value of tourist roads is the basis for subsequent judgment, classification and project planning of tourist roads. Since tourist roads are transportation products aimed at pleasing people, the tourism value of tourist roads currently needs to be determined manually, which is a complex process with low efficiency and authenticity. Summary of the invention

[0004] The present application provides a method, device, medium and program product for determining the tourism value of a tourist highway, so as to solve the problems existing in the prior art of artificially determining the tourism value of a tourist highway, which leads to a complex process, low efficiency and low authenticity.

[0005] In a first aspect, an embodiment of the present application provides a method for determining the tourism value of a tourist highway, comprising:

[0006] Determine a tourism value assessment model, multiple analysis indicators and a target probability distribution of each analysis indicator, wherein the target probability distribution of each analysis indicator is a probability distribution of the analysis indicator determined based on historical data of the tourist highway to be processed, wherein the analysis indicators include the flow of tourists, the rate of favorable comments and the number of tourists in the city where the tourist highway is located, and the tourism value assessment model is used to characterize the relationship between the analysis indicator and the tourism value of the tourist highway to be processed;

[0007] According to each analysis indicator and the target probability distribution of each analysis indicator, generating a plurality of random samples, wherein the plurality of random samples include an indicator value of each analysis indicator;

[0008] Inputting the plurality of random samples into the tourism value assessment model to obtain the initial tourism value of the tourist highway to be processed;

[0009] The initial tourism value, tourism resource information and corridor landscape information of the tourist highway to be processed are input into a tourism value determination model to obtain a target tourism value output by the tourism value determination model. The tourism value determination model is obtained by pre-training a model through a training set. The training set includes sample tourism resource information, sample corridor landscape information, a first tourism value and a second tourism value of each sample tourist highway in a plurality of sample tourist highways. The first tourism value is the value set for the sample tourist highway by tourists who have traveled on the sample tourist highway, and the second tourism value is a value determined according to a preset scoring standard.

[0010] In a possible design, generating multiple random samples according to each analysis indicator and the target probability distribution of each analysis indicator includes:

[0011] According to each analysis indicator and the target probability distribution of each analysis indicator, correlation analysis is performed on all analysis indicators to determine the correlation information between all analysis indicators;

[0012] Based on the correlation information, the plurality of random samples are generated through a multivariate distribution.

[0013] In a possible design, inputting the plurality of random samples into the tourism value assessment model to obtain the initial tourism value of the tourist highway to be processed includes:

[0014] Input the multiple random samples into the tourism value assessment model to obtain the tourism value corresponding to each random sample output by the tourism value assessment model;

[0015] According to the tourism value corresponding to each random sample, the initial tourism value of the tourist highway to be processed is determined.

[0016] In a possible design, before inputting the initial tourism value, tourism resource information and corridor landscape information of the tourist highway to be processed into a tourism value determination model and obtaining the target tourism value output by the tourism value determination model, the method further includes:

[0017] Obtaining sample tourism resource information, sample corridor landscape information and first tourism value of each sample tourism highway among multiple sample tourism highways;

[0018] For each sample tourist highway, determining the tourist resource score corresponding to the sample tourist highway in the preset scoring standard according to the sample tourist resource information of the sample tourist highway;

[0019] Determining the corridor landscape score corresponding to the sample tourist highway in the preset scoring standard according to the sample corridor landscape information of the sample tourist highway;

[0020] Determining the second tourism value of the sample tourist highway based on the tourism resource score and the corridor landscape score;

[0021] Constructing the training set according to the sample tourism resource information, the sample corridor landscape information, the first tourism value and the second tourism value of each sample tourism highway among the multiple sample tourism highways;

[0022] Training is performed according to the training set to generate the tourism value determination model.

[0023] In a possible design, determining the second tourism value of the sample tourist highway based on the tourism resource score and the corridor landscape score includes:

[0024] Determine the city score corresponding to the sample tourist highway in the preset scoring standard according to the city information of the sample city where the sample tourist highway is located; the city information includes the consumption level, popularity, population, number of news and type of each news of the sample city;

[0025] According to the substitutability information of the sample tourist highway, determine the substitutability score corresponding to the sample tourist highway in the preset scoring standard; wherein the substitutability information includes the number of other tourist highways around the sample tourist highway, the length of the other tourist highways whose distance from the sample tourist highway is less than the preset distance, the number of similar tourist highways similar to the sample tourist highway, and the similarity between the sample tourist highway and each similar tourist highway;

[0026] The tourism resource score, the corridor landscape score, the city score and the substitutability score are weighted and summed, and the processed value is determined as the second tourism value of the sample tourist highway, wherein the weight of the corridor landscape score is greater than the weight of the tourism resource score, the weight of the tourism resource score is greater than the weight of the substitutability score, and the weight of the substitutability score is greater than the weight of the city score.

[0027] In a possible design, the training according to the training set to generate the tourism value determination model includes:

[0028] Constructing an initial model, the initial model comprising a first neural network, a second neural network, and a third neural network, the initial model comprising true intention parameters;

[0029] For each sample tourist highway, extracting features of sample tourist resource information of the sample tourist highway through the first neural network to obtain a first feature of the sample tourist highway;

[0030] Extracting features of the sample corridor landscape information of the sample tourist highway through the second neural network to obtain a second feature of the sample tourist highway;

[0031] Performing feature splicing on the first feature and the second feature to generate a splicing feature;

[0032] Extracting features from the splicing features through the third neural network to generate target features;

[0033] Optimizing the parameter value of the real intention parameter by using the target feature, the first tourism value, and the second tourism value;

[0034] When the training cut-off condition is met, the training of the initial model is stopped to generate the tourism value determination model.

[0035] In a second aspect, an embodiment of the present application provides a device for determining the tourism value of a tourist highway, comprising:

[0036] A determination module is used to determine a tourism value assessment model, multiple analysis indicators and a target probability distribution of each analysis indicator, wherein the target probability distribution of each analysis indicator is a probability distribution of the analysis indicator determined based on historical data of the tourist highway to be processed, wherein the analysis indicators include the flow of tourists, the rate of favorable comments and the number of tourists in the city where the tourist highway is located, and the tourism value assessment model is used to characterize the relationship between the analysis indicator and the tourism value of the tourist highway to be processed;

[0037] A generating module, configured to generate a plurality of random samples according to each analysis indicator and a target probability distribution of each analysis indicator, wherein the plurality of random samples include an indicator value of each analysis indicator;

[0038] A first input module is used to input the plurality of random samples into the tourism value assessment model to obtain the initial tourism value of the tourist highway to be processed;

[0039] The second input module is used to input the initial tourism value, tourism resource information and corridor landscape information of the tourist highway to be processed into a tourism value determination model to obtain a target tourism value output by the tourism value determination model. The tourism value determination model is obtained by pre-training a model through a training set. The training set includes sample tourism resource information, sample corridor landscape information, a first tourism value and a second tourism value of each sample tourist highway in multiple sample tourist highways. The first tourism value is the value set for the sample tourist highway by tourists who have traveled on the sample tourist highway, and the second tourism value is a value determined according to a preset scoring standard.

[0040] In a possible design, the generating module is specifically used for:

[0041] According to each analysis indicator and the target probability distribution of each analysis indicator, correlation analysis is performed on all analysis indicators to determine the correlation information between all analysis indicators;

[0042] Based on the correlation information, the plurality of random samples are generated through a multivariate distribution.

[0043] In a possible design, the first input module is specifically used to:

[0044] Input the multiple random samples into the tourism value assessment model to obtain the tourism value corresponding to each random sample output by the tourism value assessment model;

[0045] According to the tourism value corresponding to each random sample, the initial tourism value of the tourist highway to be processed is determined.

[0046] In a possible design, before inputting the initial tourism value, tourism resource information and corridor landscape information of the tourist highway to be processed into the tourism value determination model and obtaining the target tourism value output by the tourism value determination model, the tourism value determination device of the tourist highway further includes a training module for:

[0047] Obtaining sample tourism resource information, sample corridor landscape information and first tourism value of each sample tourism highway among multiple sample tourism highways;

[0048] For each sample tourist highway, determining the tourist resource score corresponding to the sample tourist highway in the preset scoring standard according to the sample tourist resource information of the sample tourist highway;

[0049] Determining the corridor landscape score corresponding to the sample tourist highway in the preset scoring standard according to the sample corridor landscape information of the sample tourist highway;

[0050] Determining the second tourism value of the sample tourist highway based on the tourism resource score and the corridor landscape score;

[0051] Constructing the training set according to the sample tourism resource information, the sample corridor landscape information, the first tourism value and the second tourism value of each sample tourism highway among the multiple sample tourism highways;

[0052] Training is performed according to the training set to generate the tourism value determination model.

[0053] In a possible design, the training module is specifically used to:

[0054] Determine the city score corresponding to the sample tourist highway in the preset scoring standard according to the city information of the sample city where the sample tourist highway is located; the city information includes the consumption level, popularity, population, number of news and type of each news of the sample city;

[0055] According to the substitutability information of the sample tourist highway, determine the substitutability score corresponding to the sample tourist highway in the preset scoring standard; wherein the substitutability information includes the number of other tourist highways around the sample tourist highway, the length of the other tourist highways whose distance from the sample tourist highway is less than the preset distance, the number of similar tourist highways similar to the sample tourist highway, and the similarity between the sample tourist highway and each similar tourist highway;

[0056] The tourism resource score, the corridor landscape score, the city score and the substitutability score are weighted and summed, and the processed value is determined as the second tourism value of the sample tourist highway, wherein the weight of the corridor landscape score is greater than the weight of the tourism resource score, the weight of the tourism resource score is greater than the weight of the substitutability score, and the weight of the substitutability score is greater than the weight of the city score.

[0057] In a possible design, the training module is specifically used to:

[0058] Constructing an initial model, the initial model comprising a first neural network, a second neural network, and a third neural network, the initial model comprising true intention parameters;

[0059] For each sample tourist highway, extracting features of sample tourist resource information of the sample tourist highway through the first neural network to obtain a first feature of the sample tourist highway;

[0060] Extracting features of the sample corridor landscape information of the sample tourist highway through the second neural network to obtain a second feature of the sample tourist highway;

[0061] Performing feature splicing on the first feature and the second feature to generate a splicing feature;

[0062] Extracting features from the splicing features through the third neural network to generate target features;

[0063] Optimizing the parameter value of the real intention parameter by using the target feature, the first tourism value, and the second tourism value;

[0064] When the training cut-off condition is met, the training of the initial model is stopped to generate the tourism value determination model.

[0065] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a memory, and computer execution instructions stored in the memory and executable on the processor, wherein the processor is used to implement the first aspect and the methods provided by various possible designs when executing the computer execution instructions.

[0066] In a fourth aspect, an embodiment of the present application may provide a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect and the methods provided by various possible designs.

[0067] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, is used to implement the first aspect and the methods provided by various possible designs.

[0068] The method, device, medium and program product for determining the tourism value of a tourist highway provided by the embodiment of the present application, in which a tourism value assessment model, a plurality of analysis indicators and a target probability distribution of each analysis indicator are determined, and a plurality of random samples are generated according to each analysis indicator and the target probability distribution of each analysis indicator, and the plurality of random samples are input into the tourism value assessment model to obtain the initial tourism value of the tourist highway to be processed, and the initial tourism value, tourism resource information and corridor landscape information of the tourist highway to be processed are input into the tourism value determination model, and then the target tourism value output by the tourism value determination model is obtained. Among them, the target probability distribution of each analysis indicator is the probability distribution of the analysis indicator determined according to the historical data of the tourist highway to be processed, and the analysis indicators include the flow of tourists, the praise rate and the number of tourists in the city where the tourist highway is located in the tourist resources around the tourist highway, and the tourism value assessment model is used to characterize the relationship between the analysis indicator and the tourism value of the tourist highway to be processed. The plurality of random samples include the indicator value of each analysis indicator. The tourism value determination model is obtained by pre-training the model through a training set, and the training set includes sample tourism resource information, sample corridor landscape information, first tourism value and second tourism value of each sample tourism highway in multiple sample tourism highways. The first tourism value is the value set for the sample tourism highway by tourists who have traveled on the sample tourism highway, and the second tourism value is the value determined according to the preset scoring criteria. In this technical solution, the target tourism value of the tourism highway to be processed is determined by combining the tourism value assessment model and the tourism value determination model, which effectively improves the authenticity of the determined target tourism value. In addition, the entire processing process does not require human participation, which simplifies the processing flow and improves processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0070] Figure 1 A flow chart of a first embodiment of a method for determining the tourism value of a tourist highway is provided for the embodiment of the present application;

[0071] Figure 2 A flow chart of Embodiment 2 of a method for determining the tourism value of a tourist highway is provided for the embodiment of the present application;

[0072] Figure 3 A flow chart of Embodiment 3 of a method for determining the tourism value of a tourist highway is provided for the embodiment of the present application;

[0073] Figure 4 A schematic diagram of the structure of a device for determining the tourism value of a tourist highway provided in an embodiment of the present application;

[0074] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0075] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0076] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0077] Before introducing the embodiments of the present application, the application background of the embodiments of the present application is first explained:

[0078] The higher the tourism value of a tourist road, the more it attracts tourists. Therefore, the tourist road can be judged, classified and planned according to its tourism value. For example, the publicity intensity of the tourist road can be determined according to its tourism value. That is, the higher the tourism value, the stronger the publicity intensity. The tourist road can be promoted through multiple channels to achieve the purpose of increasing the city's popularity.

[0079] At present, the tourism value of tourist roads is usually determined manually based on relevant standards. For example, if the scenic spots around the tourist road have a long history, the tourist road is considered to have a higher tourism value. The entire process requires human participation and is only implemented according to rigid regulations without considering the real feelings of tourists, resulting in low authenticity and efficiency of the determined tourism value.

[0080] Based on the above technical problems, this application proposes a method, device, medium and program product for determining the tourism value of a tourist highway. First, the initial tourism value of the tourist highway to be processed is determined by a tourism value evaluation model. The tourism value evaluation model is used to characterize the relationship between the analysis index and the tourism value of the tourist highway to be processed. Furthermore, the initial tourism value is further corrected by the tourism value determination model so that the determined target tourism value of the tourist highway to be processed conforms to the real feelings of tourists, thereby improving the authenticity of the processing results. At the same time, the entire processing process of this technical solution does not require user participation, which simplifies the processing process and improves processing efficiency.

[0081] The technical solution of the present application is described in detail below through specific embodiments.

[0082] It should be noted that the following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0083] Figure 1 The present application provides a flowchart of a method for determining the tourism value of a tourist highway in Example 1. Figure 1 As shown, the method for determining the tourism value of the tourist highway may include the following steps:

[0084] S11. Determine the tourism value assessment model, multiple analysis indicators and the target probability distribution of each analysis indicator.

[0085] The analysis indicators include the flow of tourists, favorable comments and the number of tourists in the cities where the tourist roads are located. The tourist resources around the tourist roads are the tourist resources that can be covered, affected or reached by the tourist roads. The tourist resources are composed of tourist resources of scenic spot quality or tourist resources of non-scenic spot quality.

[0086] The target probability distribution of each analysis indicator is the probability distribution of the analysis indicator determined based on the historical data of the tourist highway to be processed.

[0087] For example, the target probability distribution of the flow of people of a tourist resource can be determined by analyzing the public historical number of visitors to the tourist resource. For example, the target probability distribution of the flow of people of tourist resources around a tourist highway can be a distribution that follows seasonal fluctuations.

[0088] For example, the favorable comment rate of a tourism resource can be determined by analyzing the purchase reviews of the tourism resource on the group purchase platform. For example, the target probability distribution of the favorable comment rate may be a normal distribution or a log-normal distribution.

[0089] Among them, the tourism value assessment model is used to characterize the relationship between the analysis indicators and tourism value of the tourist highway to be processed.

[0090] Optionally, the analysis index may also include ticket prices for tourist resources around the tourist highway.

[0091] S12. Generate multiple random samples according to each analysis indicator and the target probability distribution of each analysis indicator.

[0092] The plurality of random samples include an indicator value for each analysis indicator.

[0093] Since each analysis indicator not only affects the tourism value of the tourist highway independently, but also has certain correlation and interaction among them, which jointly affect the tourism value of the tourist highway. For example, there is a correlation between the flow of tourist resources and the number of tourists in the city where the tourist highway is located, and there is also a correlation between the flow of tourist resources and the ticket price. Therefore, when generating random samples, this correlation needs to be considered to improve accuracy.

[0094] In a possible implementation, correlation analysis is performed on all analysis indicators according to each analysis indicator and the target probability distribution of each analysis indicator to determine the correlation information between all analysis indicators, and based on the correlation information, multiple random samples are generated through multivariate distribution.

[0095] Specifically, if the correlation information indicates that there is no correlation between the analysis indicators, then the indicator value of each analysis indicator is generated, and the generated indicator value needs to satisfy the target probability distribution corresponding to the indicator, and then a random sample containing the indicator value of each analysis indicator is generated. If the correlation information indicates that there is a correlation between the analysis indicators, then the indicator value of each analysis indicator is generated according to the correlation, and then a random sample is generated. Among them, the indicator value of each analysis indicator generated must not only meet the target probability distribution corresponding to itself, but also meet the correlation.

[0096] S13. Input multiple random samples into the tourism value assessment model to obtain the initial tourism value of the tourist highway to be processed.

[0097] In a possible implementation, multiple random samples are input into a tourism value assessment model to obtain the tourism value corresponding to each random sample output by the tourism value assessment model, and the initial tourism value of the tourist highway to be processed is determined based on the tourism value corresponding to each random sample.

[0098] Specifically, the average value of the tourism value corresponding to each random sample can be calculated, and the average value can be determined as the initial tourism value of the tourist road to be processed. The median of the tourism value corresponding to each random sample can also be calculated, and the median can be determined as the initial tourism value of the tourist road to be processed. It can also be determined whether the tourism value assessment model has converged based on the tourism value corresponding to each random sample, and any tourism value output after the tourism value assessment model converges can be determined as the initial tourism value of the tourist road to be processed.

[0099] S14, inputting the initial tourism value, tourism resource information and corridor landscape information of the tourist highway to be processed into the tourism value determination model, and obtaining the target tourism value output by the tourism value determination model.

[0100] Among them, the tourism value determination model is obtained by pre-training the model through a training set. The training set includes sample tourism resource information, sample corridor landscape information, first tourism value and second tourism value of each sample tourist highway in multiple sample tourist highways. The first tourism value is the value set for the sample tourist highway by tourists who have traveled on the sample tourist highway, and the second tourism value is the value determined according to a preset scoring standard.

[0101] In this step, since the initial tourism value is the tourism value determined by various analysis indicators, in order to further improve the authenticity of the determined tourism value, the initial tourism value can be used as input, and combined with the tourism resource information and corridor landscape information, the initial tourism value can be corrected through the tourism value determination model, thereby obtaining the target tourism value with higher authenticity output by the tourism value determination model.

[0102] It should be understood that the input of the tourism value determination model includes three parts, namely tourism resource information, corridor landscape information and tourism value determined according to the scoring criteria. Since the initial tourism value is generated according to the preset tourism value assessment model, the tourism value assessment model is established based on the scoring criteria to characterize the relationship between analysis indicators and tourism value. Therefore, the initial tourism value output by the tourism value assessment model can be input into the tourism value determination model as the tourism value determined according to the scoring criteria. Compared with directly determining the tourism value through the scoring criteria, the method of generating the initial tourism value through the tourism value assessment model is faster and more accurate, and does not require human participation.

[0103] Among them, when training the tourism value determination model, the model parameters are trained by taking the first tourism value as a label, and then a trained tourism value determination model is obtained, so that the tourism value determination model can take into account both the scoring criteria and the real feelings of tourists.

[0104] It should be understood that the specific training process of the tourism value determination model will be discussed in the following Figure 2 The detailed description is given in the illustrated embodiment and will not be repeated here.

[0105] The method for determining the tourism value of a tourist highway provided in the embodiment of the present application determines a tourism value assessment model, multiple analysis indicators, and a target probability distribution of each analysis indicator. According to each analysis indicator and the target probability distribution of each analysis indicator, multiple random samples are generated, and the multiple random samples are input into the tourism value assessment model to obtain the initial tourism value of the tourist highway to be processed. The initial tourism value, tourism resource information, and corridor landscape information of the tourist highway to be processed are input into the tourism value determination model, and then the target tourism value output by the tourism value determination model is obtained. Among them, the target probability distribution of each analysis indicator is the probability distribution of the analysis indicator determined based on the historical data of the tourist highway to be processed. The analysis indicators include the flow of tourists, the praise rate of the tourist resources around the tourist highway, and the number of tourists in the city where the tourist highway is located. The tourism value assessment model is used to characterize the relationship between the analysis indicators and the tourism value of the tourist highway to be processed. Multiple random samples include the indicator value of each analysis indicator. The tourism value determination model is obtained by pre-training the model through a training set, and the training set includes sample tourism resource information, sample corridor landscape information, first tourism value and second tourism value of each sample tourism highway in multiple sample tourism highways. The first tourism value is the value set for the sample tourism highway by tourists who have traveled on the sample tourism highway, and the second tourism value is the value determined according to the preset scoring criteria. In this technical solution, the target tourism value of the tourism highway to be processed is determined by combining the tourism value assessment model and the tourism value determination model, which effectively improves the authenticity of the determined target tourism value. In addition, the entire processing process does not require human participation, which simplifies the processing flow and improves processing efficiency.

[0106] Optionally, before inputting the initial tourism value, tourism resource information and corridor landscape information of the tourist highway to be processed into the tourism value determination model and obtaining the target tourism value output by the tourism value determination model, it is also necessary to perform model training based on the training set to obtain a trained tourism value determination model.

[0107] Figure 2 The present application provides a flowchart of a second embodiment of a method for determining the tourism value of a tourist highway. Figure 2 As shown, the method for determining the tourism value of the tourist highway may include the following steps:

[0108] S21. Obtain sample tourism resource information, sample corridor landscape information, and a first tourism value of each sample tourism highway among a plurality of sample tourism highways.

[0109] In the embodiment of the present application, the tourism value of the tourist highway should be evaluated based on the investigation and analysis of at least one of the following data:

[0110] a) Current status and development plan of regional tourism industry.

[0111] b) Current status and development plan of regional road network.

[0112] c) The type, grade, scale, integrity and protection of tourism resources along the route, carrying capacity, suitable travel period and annual passenger flow, as well as connection conditions with highways.

[0113] d) The rarity and uniqueness of the distribution of various types of landscape resources along the route.

[0114] e) Special projects for the reconstruction and expansion of existing highways and the improvement of their tourism service functions also require information on the main highway project, slow lanes and tourism service facilities.

[0115] The sample tourism resource information includes the number of tourism resources and the level of tourism resources. If the tourism resources are the quality of scenic tourism resources, the levels of the tourism resources are 5A, 4A, 3A, 2A, and 1A from high to low. If the tourism resources are the quality of non-scenic tourism resources, the levels of the tourism resources are level 5, level 4, level 3, level 2, and level 1 from high to low.

[0116] It should be understood that if the tourism resources are non-scenic area tourism resources, the classification of tourism resource levels is determined according to the relevant provisions of GB / T 18972. The relevant provisions of GB / T 18972 are that non-scenic area tourism resources are evaluated by scoring and divided into five levels of tourism resources from high to low: level 5, level 4, level 3, level 2, and level 1.

[0117] The corridor landscape refers to the corridor landscape that can be directly experienced or appreciated in the vicinity of the tourist highway, including the visual, natural, cultural, historical, recreational and other landscapes within the field of vision or direct experience. The sample corridor landscape information includes at least one of the following: visual landscape information, natural landscape information, cultural landscape information, historical landscape information or recreational landscape information.

[0118] Next, the visual landscape, natural landscape, cultural landscape, historical landscape or recreational landscape are explained respectively.

[0119] Visual landscape: Visual landscape refers to the overall visual experience composed of the natural landscape, historical and cultural landscape along the route, and the coordinated internal landscape of the highway, including natural and cultural landscape elements with visual sensitivity, unique landforms, etc.

[0120] Natural landscape: refers to natural landscapes such as geographical landscapes, water landscapes, biological landscapes, astronomical and climatic landscapes, or animal and plant fossils that can be seen in a relatively stable and independent space.

[0121] Cultural landscape: refers to the material or intangible manifestations of the traditional customs of the local people that can be observed in the region, including handicrafts, music, dance, rituals, traditional festivals, legends, food, festivals and local architecture.

[0122] Historical landscape: refers to the historical heritage formed by human history or prehistoric human activities preserved in the region, including prehistoric human activity sites and artifacts, historical architectural sites, places where historical events took place, celebrity residences and memorials, relatively intact ancient buildings, ancient engineering sites and revolutionary memorials, etc.

[0123] Recreational landscape: refers to recreational activity opportunities and tourism experiences that rely on corridor landscape elements, such as self-driving, alpine skiing, rafting, boating, fishing and hiking, as well as related leisure and entertainment facilities, such as parks, picking gardens and other leisure facilities.

[0124] That is, the specific interpretations of visual landscape, natural landscape, cultural landscape, historical landscape and recreational landscape are shown in Table 1.

[0125] Table 1

[0126]

[0127] In a possible implementation, a geographic image of a sample tourist highway can be obtained, and the geographic image can be an aerial photo or a topographic map. Then, a plurality of basic survey units are divided in the geographic image according to a preset size, and sub-corridor landscape information is collected within the scope of each basic survey unit. Finally, the sum of the sub-corridor landscape information collected within each basic survey unit is determined as the sample corridor landscape information of the sample tourist highway.

[0128] For example, the preset size may be 1000×1000 meters, 1100×1100 meters, 1200×1200 meters, etc. It should be understood that the preset size may be determined comprehensively based on the feasibility and convenience of the actual investigation and the actual situation on site to facilitate the investigation and data collection, and the embodiments of the present application do not impose specific limitations on this.

[0129] In a specific implementation, the landscape included in the sample corridor landscape information needs to meet the following conditions: it is a landscape that is visible or directly experiential along the route, and the length of the landscape along the highway is not less than 100 meters. In other words, for each basic survey unit, if the landscape in the basic survey unit does not meet the above conditions, the landscape information corresponding to the landscape will not be collected.

[0130] Optionally, after determining the sub-corridor landscape information of each basic survey unit, the sub-corridor landscape information can also be marked on the geographic image of the sample tourist highway to generate a project overall map for subsequent analysis of the corridor landscape of the sample tourist highway. It should be understood that the project overall map can reflect the location, quality, type and section of each landscape.

[0131] Optionally, the first tourism value can be determined based on the review information of the sample tourism highway. Specifically, the first tourism value of the sample tourism highway can be determined based on the total number of reviews, the number of favorable reviews, and the number of unfavorable reviews of the sample tourism highway.

[0132] Among them, the favorable rate of the sample tourist highway can be determined according to the total number of reviews and the number of favorable reviews. At the same time, the unfavorable rate of the sample tourist highway can be determined according to the total number of reviews and the number of unfavorable reviews. Finally, based on the correlation between favorable rate, unfavorable rate, total number of reviews and the score, the score corresponding to the favorable rate, unfavorable rate and total number of reviews of the sample tourist highway in the above correlation is determined as the first tourist value of the sample tourist highway.

[0133] Alternatively, the first tourism value can also be realized by means of a questionnaire survey. A questionnaire survey can be sent to multiple tourists, and their scores on the sample tourist roads can be obtained, and the average value of these scores is determined as the first tourism value of the sample tourist roads.

[0134] S22. For each sample tourist highway, determine the tourism resource score corresponding to the sample tourist highway in the preset scoring criteria according to the sample tourist resource information of the sample tourist highway.

[0135] In a possible implementation, the tourism resource score of the sample tourist highway can be directly determined through Table 2.

[0136] Table 2

[0137]

[0138]

[0139] In Table 2, the sample tourism resource information can be realized as the number of tourism resources and the tourism resource level contained within 20 kilometers of every 100 kilometers of the roadside. According to the sample tourism resource information of the sample tourism highway, the first tourism resource condition satisfied by the tourism resources of the scenic tourism resource quality of the sample tourism highway and the second tourism resource condition satisfied by the tourism resources of the non-scenic tourism resource quality of the sample tourism highway are determined. Afterwards, the scenic tourism resource score of the sample tourism highway is determined within the target score interval corresponding to the first tourism resource condition, and the non-scenic tourism resource score of the sample tourism highway is determined within the target score interval corresponding to the second tourism resource condition, and finally the tourism resource score of the sample tourism highway is determined based on the scenic tourism resource score and the non-scenic tourism resource score.

[0140] It should be understood that the scenic area tourism resource score or non-scenic area tourism resource score corresponding to the sample tourist highway can be determined artificially from the target score interval. Exemplarily, an evaluation team composed of experts in relevant professions can determine the scenic area tourism resource score or non-scenic area tourism resource score corresponding to the sample tourist highway within the target score interval after determining the target score interval corresponding to the first tourist resource condition or the second tourist resource condition through Table 2.

[0141] It should be understood that the scoring range in Table 2 above can also be implemented as specific scoring values, that is, each tourism resource condition corresponds to a specific scoring value, so that the specific scenic spot tourism resource score and non-scenic spot tourism resource score corresponding to the sample tourist highway can be determined from Table 2 based on the tourism resource information of the sample tourist highway.

[0142] Optionally, the average of the scenic area tourism resource score and the non-scenic area tourism resource score can be determined as the tourism resource score of the sample tourism highway. The maximum value of the scenic area tourism resource score and the non-scenic area tourism resource score can also be determined as the tourism resource score of the sample tourism highway. The scenic area tourism resource score and the non-scenic area tourism resource score can also be weighted averaged, and the calculated value can be determined as the tourism resource score of the sample tourism highway.

[0143] It should be understood that the above Table 2 may also include the tourism resource level corresponding to each tourism resource condition, and the tourism resource level is divided into three levels: high, medium and low:

[0144] 1. The tourism resource scores of scenic area tourism resource quality or non-scenic area tourism resource quality are between 27 and 40, that is, the tourism resource level is high, and the tourism resource value is high.

[0145] 2. The tourism resource score of the scenic area tourism resource quality or the tourism resource score of the non-scenic area tourism resource quality is between 14 and 26, that is, the tourism resource level is medium, and the tourism resource value is medium.

[0146] 3. The tourism resource scores of the scenic area tourism resource quality or the non-scenic area tourism resource quality are both in the range of 0 to 13, that is, the tourism resource levels are low, and the tourism resource value is low.

[0147] It should be understood that the above Table 2 is illustrative with a total score of 40 points. In practical applications, the total score may also be other values, such as 100 points, which may be determined according to actual conditions. Table 1 may also include other contents, which are not specifically limited.

[0148] It should be understood that the tourism resource scoring should comply with the relevant provisions of GB / T 18972, GB / T 17775 and LB / T 025. In other words, the tourism resource conditions and corresponding scoring ranges in Table 2 should comply with the relevant provisions of GB / T18972, GB / T 17775 and LB / T025.

[0149] It should be understood that the preset scoring criteria include the tourism resource conditions in Table 2.

[0150] S23. Determine the corridor landscape score corresponding to the sample tourist highway in the preset scoring standard based on the sample corridor landscape information of the sample tourist highway.

[0151] It should be understood that the corridor landscape score is composed of at least one of a visual landscape score, a natural landscape score, a cultural landscape score, a historical landscape score, or a recreational landscape score. Optionally, the corridor landscape score may also include a landscape uniqueness score and a landscape point accessibility score.

[0152] Exemplarily, the corridor landscape score can be determined by the following Table 3.

[0153] Table 3

[0154]

[0155]

[0156] As shown in Table 3, the target corridor landscape conditions of the sample tourist highways in terms of visual landscape, natural landscape, cultural landscape, historical landscape and recreational landscape can be determined based on the sample corridor landscape information of the sample tourist highways, and then the visual landscape score, natural landscape score, cultural landscape score, historical landscape score or recreational landscape score can be determined within the target score range corresponding to the target corridor landscape conditions. Finally, the corridor landscape score of the sample tourist highway is determined based on the visual landscape score, natural landscape score, cultural landscape score, historical landscape score and recreational landscape score.

[0157] Optionally, the visual landscape score, natural landscape score, cultural landscape score, historical landscape score or recreational landscape score corresponding to the sample tourist highway can be determined manually from the target score interval. For example, experts in the fields of ecology, geography, history, tourism, communication, architecture, landscape planning, and transportation planning can be hired to form an evaluation team. After determining the target corridor landscape conditions that the visual landscape meets and then determining the target score interval corresponding to the target corridor landscape conditions, the evaluation team determines the visual landscape score within the target score interval.

[0158] It should be understood that the scoring range in Table 3 above can also be implemented as specific scoring values, that is, each corridor landscape condition corresponds to a specific scoring value, so that the specific visual landscape score, natural landscape score, cultural landscape score, historical landscape score and recreational landscape score corresponding to the sample tourist highway can be determined from Table 3 based on the sample corridor landscape information of the sample tourist highway.

[0159] Optionally, the visual landscape score, natural landscape score, cultural landscape score, historical landscape score and recreational landscape score can be summed up, and the summed value can be determined as the corridor landscape score of the sample tourist highway. The visual landscape score, natural landscape score, cultural landscape score, historical landscape score and recreational landscape score can also be averaged or weighted averaged, and the processed value can be determined as the corridor landscape score of the sample tourist highway. The highest score among the visual landscape score, natural landscape score, cultural landscape score, historical landscape score and recreational landscape score can also be determined as the corridor landscape score of the sample tourist highway.

[0160] It should be understood that each tourism resource condition corresponds to a corridor landscape level. The target corridor landscape level of the sample tourism highway can be determined by the following conditions:

[0161] 1. If there are two or more target landscape scores among the visual landscape score, natural landscape score, cultural landscape score, historical landscape score, and recreational landscape score, and the corresponding corridor landscape grade of the target landscape score reaches "excellent" in an average of more than 5 kilometers per 20 kilometers in the sample tourist highway, or the total score range of the visual landscape score, natural landscape score, cultural landscape score, historical landscape score, and recreational landscape score is between 36 and 60, then the target corridor landscape grade of the sample tourist highway is determined to be high.

[0162] 2. If there are two or more target landscape scores among the visual landscape score, natural landscape score, cultural landscape score, historical landscape score, and recreational landscape score, and the corresponding corridor landscape grade of more than 5 kilometers per 20 kilometers of the sample tourist highway does not reach the "excellent" grade on average, but there are 10 kilometers or more sections that reach the "good" grade, or the total score range of the visual landscape score, natural landscape score, cultural landscape score, historical landscape score, and recreational landscape score is between 36 and 60, then the target corridor landscape grade of the sample tourist highway is determined to be high.

[0163] 3. In other cases, the landscape level of the target corridor is low.

[0164] In other words, the evaluation range of the corridor landscape score is generally 5 kilometers on both sides of the line.

[0165] It should be understood that the total scores of the visual landscape score, natural landscape score, cultural landscape score, visual landscape score, historical landscape score, and recreational landscape score are 10 points, 10 points, 10 points, 5 points, and 5 points, respectively, for illustrative purposes in Table 3. It should be understood that in real life, the total scores corresponding to the above five scores can also be other values, which can be determined according to actual conditions, and will not be repeated here.

[0166] It should be understood that the preset scoring criteria include the corridor landscape conditions in Table 3.

[0167] S23. Determine the second tourism value of the sample tourist highway based on the tourism resource score and corridor landscape score.

[0168] In a possible implementation, the tourism resource score and the corridor landscape score of the sample tourist highway may be added together, and the summed value may be determined as the corridor landscape value of the sample tourist highway.

[0169] In a possible implementation, the maximum value of the tourism resource score and the corridor landscape score of the sample tourist highway can be determined as the corridor landscape value of the sample tourist highway.

[0170] In a possible implementation, the tourism resource score and corridor landscape score of the sample tourist highway are weightedly summed to generate the corridor landscape value of the sample tourist highway.

[0171] It should be understood that the weight of the tourism resource score and the weight of the corridor landscape score can be preset values ​​set manually, for example, the weight of the tourism resource score is 0.4, and the weight of the corridor landscape score is 0.6. It should be understood that the weight of the tourism resource score and the weight of the corridor landscape score in different regions can be different. For example, a region has a large number of tourism resources but a small number of corridor landscapes, so a larger weight value can be set in advance for the tourism resource score and a smaller weight value can be set for the corridor landscape score.

[0172] It should be understood that the sum of the weight of the tourism resource score and the weight of the corridor landscape score is 1.

[0173] Furthermore, the tourism value level of the sample tourism highway can be determined according to the second tourism value. For example, reference can be made to Table 4.

[0174] Table 4

[0175] Tourism value level high medium Meet the Standard Low Rating range [85，100] [70，85) [60，70) [0，60)

[0176] In Table 4, the total score of the tourism resource score is 40 points, the total score of the corridor landscape score is 60 points, and the second tourism value is the sum of the tourism resource score and the corridor landscape score. Assuming that the second tourism value is 80, the score interval of the second tourism value is [70, 85), and the tourism value level corresponding to this score interval is medium, which is the target tourism value level of the sample tourist highway.

[0177] It should be understood that the scoring intervals corresponding to different tourism value levels in Table 4 may also be other values, which can be determined based on the full score of the second tourism value and actual conditions, and there is no specific limitation on this.

[0178] It should be understood that Table 4 is formulated with reference to the relevant requirements of LB / T 025.

[0179] In a possible implementation, S23 may also be implemented by the following steps 1 to 3:

[0180] Step 1: According to the city information of the sample city where the sample tourist highway is located, determine the city score corresponding to the sample tourist highway in the preset scoring standard.

[0181] Among them, city information includes the consumption level, popularity, population size, number of news and the type of each news of the sample cities.

[0182] Optionally, the popularity of a city can be determined by the number of times the city is discussed and searched on the Internet. The more times the city is discussed and searched, the higher the popularity.

[0183] Among them, the news type is positive or negative.

[0184] Optionally, if the sample tourist highway spans across multiple cities, the average of the initial city scores of the multiple cities is determined as the city score of the sample tourist highway.

[0185] Step 2: Based on the substitutability information of the sample tourist highway, determine the substitutability score corresponding to the sample tourist highway in the preset scoring criteria.

[0186] Among them, the substitutability information includes the number of other tourist roads around the sample tourist road, the length of other tourist roads whose distance from the sample tourist road is less than a preset distance, the number of similar tourist roads similar to the sample tourist road, and the similarity between the sample tourist road and each similar tourist road.

[0187] The similarity between tourist roads is composed of the first similarity of tourist resources and the second similarity of corridor landscapes. Exemplarily, the average of the first similarity and the second similarity can be determined as the similarity between tourist roads.

[0188] Step 3: Perform weighted summation on the tourism resource score, corridor landscape score, city score, and substitutability score, and determine the processed value as the second tourism value of the sample tourist highway.

[0189] Among them, the weight of the corridor landscape score is greater than that of the tourism resource score, the weight of the tourism resource score is greater than that of the substitutability score, and the weight of the substitutability score is greater than that of the city score.

[0190] For example, the value of the sample tourist highway can be calculated by the following formula:

[0191] Y=aX1+bX2+cX3+dX4

[0192] Among them, Y is the second tourism value, X1 is the tourism resource score, X2 is the corridor landscape score, X3 is the substitutability score, X4 is the city score, a is the weight of the tourism resource score, b is the weight of the corridor landscape score, c is the weight of the substitutability score, d is the weight of the city score, and a+b+c+d=1.

[0193] Among them, the relationship between a, b, c, d, and e can satisfy the following relationship:

[0194] d<c<a<b

[0195] Considering that in the actual travel process, some tourists want to visit the tourist roads in a city while visiting the city because of their interest in the city, but most tourists are attracted by the unique landscapes or scenic spots of the tourist roads, so the importance of the city score ranks last. Furthermore, the higher the substitutability score, the more similar tourist roads there are, and the more options tourists have, which means that the value of the tourist road is lower, so the importance of the substitutability score ranks third. Since the value of tourist roads mainly lies in the fact that they contain tourist resources and corridor landscapes, the weights of the two are ranked in the top two. Since the corridor landscape contains more landscape types and is more attractive to tourists, the weight of the corridor landscape score is greater than the weight of the tourist resource score.

[0196] S24. Construct a training set according to the sample tourism resource information, sample corridor landscape information, first tourism value and second tourism value of each sample tourism highway in the multiple sample tourism highways.

[0197] S25. Perform training based on the training set to generate a tourism value determination model.

[0198] In a possible implementation, the initial model may be trained based on the training set to generate a tourism value determination model.

[0199] It should be understood that the implementation process of the above method will be Figure 3 The detailed description is given in the illustrated embodiment and will not be repeated here.

[0200] In the above embodiment, the second tourism value of the sample tourist highway is determined by comprehensively referring to multiple factors such as tourist resources, corridor landscape, city and substitutability, which effectively improves the accuracy.

[0201] Optional, Figure 3 The present application provides a flowchart of a third embodiment of a method for determining the tourism value of a tourist highway. Figure 3 As shown, S25 may include the following steps:

[0202] S31. Build an initial model.

[0203] The initial model includes a first neural network, a second neural network, and a third neural network, and the initial model includes true intention parameters.

[0204] S32. For each sample tourist highway, extract the sample tourist resource information of the sample tourist highway through a first neural network to obtain a first feature of the sample tourist highway.

[0205] S33. Extracting features of the sample corridor landscape information of the sample tourist highway through a second neural network to obtain a second feature of the sample tourist highway.

[0206] S34, performing feature splicing on the first feature and the second feature to generate a splicing feature.

[0207] By concatenating the first feature and the second feature, the feature dimension of the concatenated feature can be made larger, thereby improving the generalization ability of the initial model.

[0208] S35. Extract the splicing features through a third neural network to generate target features.

[0209] By extracting the concatenated features again to obtain the target features, the feature interaction can be strengthened and the expressiveness and robustness of the initial model can be further improved.

[0210] S36. Optimize the real intention parameters through the target characteristics, the first tourism value and the second tourism value.

[0211] Specifically, according to the initial parameter value of the real intention parameter, the predicted tourism value of the target feature and the second tourism value under the initial parameter value is calculated. Then, the predicted tourism value is compared with the first tourism value, and the real intention parameter is back-propagated according to the difference between the two.

[0212] S37. When the training cutoff condition is met, the training of the initial model is stopped, and a tourism value determination model is generated.

[0213] In the above embodiment, by setting the real intention parameter in the initial model and training it with the first tourism value determined by the real traveler as a label, the trained tourism value determination model has the ability to generate tourism value with higher authenticity.

[0214] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0215] Figure 4 This is a schematic diagram of the structure of a device for determining the tourism value of a tourist highway provided in an embodiment of the present application. Figure 4 As shown, the tourism value determination device 40 of the tourism highway includes:

[0216] Determination module 41 is used to determine a tourism value assessment model, multiple analysis indicators and the target probability distribution of each analysis indicator. The target probability distribution of each analysis indicator is the probability distribution of the analysis indicator determined based on the historical data of the tourist highway to be processed. The analysis indicators include the flow of tourists in the tourist resources around the tourist highway, the rate of favorable comments and the number of tourists in the city where the tourist highway is located. The tourism value assessment model is used to characterize the relationship between the analysis indicators and the tourism value of the tourist highway to be processed.

[0217] The generating module 42 is used to generate a plurality of random samples according to each analysis indicator and the target probability distribution of each analysis indicator, wherein the plurality of random samples include the indicator value of each analysis indicator.

[0218] The first input module 43 is used to input a plurality of random samples into the tourism value evaluation model to obtain the initial tourism value of the tourist highway to be processed.

[0219] The second input module 44 is used to input the initial tourism value, tourism resource information and corridor landscape information of the tourist highway to be processed into the tourism value determination model to obtain the target tourism value output by the tourism value determination model. The tourism value determination model is obtained by pre-training the model through a training set. The training set includes sample tourism resource information, sample corridor landscape information, a first tourism value and a second tourism value of each sample tourist highway in multiple sample tourist highways. The first tourism value is the value set for the sample tourist highway by tourists who have traveled on the sample tourist highway, and the second tourism value is a value determined according to a preset scoring standard.

[0220] In a possible design, the generating module 42 is specifically configured to:

[0221] According to each analysis indicator and the target probability distribution of each analysis indicator, correlation analysis is performed on all analysis indicators to determine the correlation information between all analysis indicators.

[0222] Based on the correlation information, multiple random samples are generated from a multivariate distribution.

[0223] In a possible design, the first input module 43 is specifically used for:

[0224] Multiple random samples are input into the tourism value assessment model to obtain the tourism value corresponding to each random sample output by the tourism value assessment model.

[0225] According to the tourism value corresponding to each random sample, the initial tourism value of the tourist highway to be processed is determined.

[0226] In a possible design, before the initial tourism value, tourism resource information and corridor landscape information of the tourist highway to be processed are input into the tourism value determination model and the target tourism value output by the tourism value determination model is obtained, the tourism value determination device 40 of the tourist highway further includes a training module for:

[0227] The sample tourism resource information, sample corridor landscape information and the first tourism value of each sample tourism highway among multiple sample tourism highways are obtained.

[0228] For each sample tourist highway, the tourism resource score corresponding to the sample tourist highway in the preset scoring criteria is determined based on the sample tourist resource information of the sample tourist highway.

[0229] Based on the sample corridor landscape information of the sample tourist highway, determine the corridor landscape score corresponding to the sample tourist highway in the preset scoring criteria.

[0230] Based on the tourism resource score and corridor landscape score, the second tourism value of the sample tourist highway is determined.

[0231] A training set is constructed according to the sample tourism resource information, sample corridor landscape information, first tourism value and second tourism value of each sample tourism highway in multiple sample tourism highways.

[0232] The training is performed based on the training set to generate a tourism value determination model.

[0233] In a possible design, the training module is specifically used to:

[0234] According to the city information of the sample city where the sample tourist highway is located, the city score corresponding to the sample tourist highway in the preset scoring standard is determined. The city information includes the consumption level, popularity, population, number of news and type of each news of the sample city.

[0235] According to the substitutability information of the sample tourist highway, the substitutability score corresponding to the sample tourist highway in the preset scoring standard is determined. The substitutability information includes the number of other tourist highways around the sample tourist highway, the length of other tourist highways whose distance from the sample tourist highway is less than the preset distance, the number of similar tourist highways similar to the sample tourist highway, and the similarity between the sample tourist highway and each similar tourist highway.

[0236] The tourism resource score, corridor landscape score, city score and substitutability score are weighted and summed, and the processed value is determined as the second tourism value of the sample tourist highway, among which the weight of the corridor landscape score is greater than the weight of the tourism resource score, the weight of the tourism resource score is greater than the weight of the substitutability score, and the weight of the substitutability score is greater than the weight of the city score.

[0237] In a possible design, the training module is specifically used to:

[0238] An initial model is constructed, wherein the initial model includes a first neural network, a second neural network, and a third neural network, and the initial model includes true intent parameters.

[0239] For each sample tourist highway, feature extraction is performed on the sample tourist resource information of the sample tourist highway through a first neural network to obtain a first feature of the sample tourist highway.

[0240] The second neural network is used to extract the features of the sample corridor landscape information of the sample tourist highway to obtain the second feature of the sample tourist highway.

[0241] The first feature and the second feature are spliced ​​to generate a spliced ​​feature.

[0242] The splicing features are extracted through the third neural network to generate target features.

[0243] The parameter value of the true intention parameter is optimized through the target characteristics, the first tourism value and the second tourism value.

[0244] When the training cutoff condition is met, the training of the initial model is stopped to generate a tourism value determination model.

[0245] The tourism value determination device 40 for a tourism highway provided in the embodiment of the present application can be used to execute the tourism value determination method for a tourism highway in any of the above-mentioned embodiments. The implementation principle and technical effect thereof are similar and will not be described in detail here.

[0246] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, all or part of them can be integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements. They can also be implemented in the form of hardware. Some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. In addition, all or part of these modules can be integrated together or implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0247] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 5 As shown, the electronic device 50 may include: a processor 51, a memory 52, and computer execution instructions stored in the memory 52 and executable on the processor 51. When the processor 51 executes the computer execution instructions, the method for determining the tourism value of a tourist highway provided in any of the aforementioned embodiments is implemented.

[0248] Optionally, the above-mentioned components of the electronic device 50 may be connected via a system bus.

[0249] The memory 52 may be a separate storage unit or a storage unit integrated in the processor. The number of processors is one or more.

[0250] Optionally, the electronic device 50 may also include a communication interface for interacting with other devices.

[0251] It should be understood that the processor 51 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor.

[0252] The system bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage.

[0253] All or part of the steps of the above-mentioned method embodiments can be completed by hardware related to program instructions. The above-mentioned program can be stored in a readable memory. When the program is executed, the steps of the above-mentioned method embodiments are executed. The above-mentioned memory (storage medium) includes: read-only memory (ROM), RAM, flash memory, hard disk, solid state drive, magnetic tape, floppy disk, optical disc and any combination thereof.

[0254] The electronic device provided in the embodiment of the present application can be used to execute the method for determining the tourism value of a tourist highway provided in any of the above-mentioned method embodiments. The implementation principle and technical effects are similar and will not be repeated here.

[0255] An embodiment of the present application provides a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed on a computer, the computer executes the above-mentioned method for determining the tourism value of a tourist highway.

[0256] The computer-readable storage medium mentioned above can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0257] Optionally, a readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0258] An embodiment of the present application also provides a computer program product, which includes a computer program. The computer program is stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When at least one processor executes the computer program, the above-mentioned method for determining the tourism value of the tourist highway can be implemented.

[0259] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for determining the tourism value of a tourist highway, characterized in that: include: Determine a tourism value assessment model, multiple analysis indicators and a target probability distribution of each analysis indicator, wherein the target probability distribution of each analysis indicator is a probability distribution of the analysis indicator determined based on historical data of the tourist highway to be processed, wherein the analysis indicators include the flow of tourists, the rate of favorable comments and the number of tourists in the city where the tourist highway is located, and the tourism value assessment model is used to characterize the relationship between the analysis indicator and the tourism value of the tourist highway to be processed; According to each analysis indicator and the target probability distribution of each analysis indicator, generating a plurality of random samples, wherein the plurality of random samples include an indicator value of each analysis indicator; Inputting the plurality of random samples into the tourism value assessment model to obtain the initial tourism value of the tourist highway to be processed; Input the initial tourism value, tourism resource information and corridor landscape information of the tourist highway to be processed into a tourism value determination model, and obtain the target tourism value output by the tourism value determination model, wherein the tourism value determination model is obtained by pre-training a model through a training set, and the training set includes sample tourism resource information, sample corridor landscape information, a first tourism value and a second tourism value of each sample tourist highway in a plurality of sample tourist highways, wherein the first tourism value is the value set for the sample tourist highway by tourists who have traveled on the sample tourist highway, and the second tourism value is the value determined according to a preset scoring standard; Wherein, before inputting the initial tourism value, tourism resource information and corridor landscape information of the tourist highway to be processed into a tourism value determination model and obtaining the target tourism value output by the tourism value determination model, the method further includes: Obtaining sample tourism resource information, sample corridor landscape information and first tourism value of each sample tourism highway among multiple sample tourism highways; For each sample tourist highway, determining the tourist resource score corresponding to the sample tourist highway in the preset scoring standard according to the sample tourist resource information of the sample tourist highway; Determining the corridor landscape score corresponding to the sample tourist highway in the preset scoring standard according to the sample corridor landscape information of the sample tourist highway; Determining the second tourism value of the sample tourist highway based on the tourism resource score and the corridor landscape score; Constructing the training set according to the sample tourism resource information, the sample corridor landscape information, the first tourism value and the second tourism value of each sample tourism highway among the multiple sample tourism highways; Perform training according to the training set to generate the tourism value determination model; Wherein, determining the second tourism value of the sample tourist highway based on the tourism resource score and the corridor landscape score includes: Determine the city score corresponding to the sample tourist highway in the preset scoring standard according to the city information of the sample city where the sample tourist highway is located; the city information includes the consumption level, popularity, population, number of news and type of each news of the sample city; According to the substitutability information of the sample tourist highway, determine the substitutability score corresponding to the sample tourist highway in the preset scoring standard; wherein the substitutability information includes the number of other tourist highways around the sample tourist highway, the length of the other tourist highways whose distance from the sample tourist highway is less than the preset distance, the number of similar tourist highways similar to the sample tourist highway, and the similarity between the sample tourist highway and each similar tourist highway; Performing a weighted summation on the tourism resource score, the corridor landscape score, the city score and the substitutability score, and determining the processed value as the second tourism value of the sample tourist highway, wherein the weight of the corridor landscape score is greater than the weight of the tourism resource score, the weight of the tourism resource score is greater than the weight of the substitutability score, and the weight of the substitutability score is greater than the weight of the city score; The corridor landscape score is composed of at least one of a visual landscape score, a natural landscape score, a cultural landscape score, a historical landscape score or a recreational landscape score; The corridor landscape score also includes a landscape uniqueness score and a landscape point accessibility score; Among them, the second tourism value of the sample tourist highway can be calculated by the formula: Y=aX1+bX2+cX3+dX4, Y is the second tourism value, X1 is the tourism resource score, X2 is the corridor landscape score, X3 is the substitutability score, X4 is the city score, a is the weight of the tourism resource score, b is the weight of the corridor landscape score, c is the weight of the substitutability score, d is the weight of the city score, a+b+c+d=1, the relationship between a, b, c, d, e can satisfy d<c<a<b; Among them, the similarity between tourist roads is composed of the first similarity of tourist resources and the second similarity of corridor landscape; The step of generating multiple random samples according to each analysis indicator and the target probability distribution of each analysis indicator includes: According to each analysis indicator and the target probability distribution of each analysis indicator, correlation analysis is performed on all analysis indicators to determine the correlation information between all analysis indicators; Based on the correlation information, the plurality of random samples are generated through a multivariate distribution.

2. The method according to claim 1, characterized in that The step of inputting the plurality of random samples into the tourism value assessment model to obtain the initial tourism value of the tourist highway to be processed includes: Input the multiple random samples into the tourism value assessment model to obtain the tourism value corresponding to each random sample output by the tourism value assessment model; According to the tourism value corresponding to each random sample, the initial tourism value of the tourist highway to be processed is determined.

3. The method according to claim 1, characterized in that The training according to the training set to generate the tourism value determination model includes: Constructing an initial model, the initial model comprising a first neural network, a second neural network, and a third neural network, the initial model comprising true intention parameters; For each sample tourist highway, extracting features of sample tourist resource information of the sample tourist highway through the first neural network to obtain a first feature of the sample tourist highway; Extracting features of the sample corridor landscape information of the sample tourist highway through the second neural network to obtain a second feature of the sample tourist highway; Performing feature splicing on the first feature and the second feature to generate a splicing feature; Extracting features from the splicing features through the third neural network to generate target features; Optimizing the parameter value of the real intention parameter by using the target feature, the first tourism value, and the second tourism value; When the training cut-off condition is met, the training of the initial model is stopped to generate the tourism value determination model.

4. A device for determining the tourism value of a tourist highway, characterized in that: include: A determination module is used to determine a tourism value assessment model, multiple analysis indicators and a target probability distribution of each analysis indicator, wherein the target probability distribution of each analysis indicator is a probability distribution of the analysis indicator determined based on historical data of the tourist highway to be processed, wherein the analysis indicators include the flow of tourists, the rate of favorable comments and the number of tourists in the city where the tourist highway is located, and the tourism value assessment model is used to characterize the relationship between the analysis indicator and the tourism value of the tourist highway to be processed; A generating module, configured to generate a plurality of random samples according to each analysis indicator and a target probability distribution of each analysis indicator, wherein the plurality of random samples include an indicator value of each analysis indicator; A first input module is used to input the plurality of random samples into the tourism value assessment model to obtain the initial tourism value of the tourist highway to be processed; A second input module is used to input the initial tourism value, tourism resource information and corridor landscape information of the tourist highway to be processed into a tourism value determination model to obtain a target tourism value output by the tourism value determination model, wherein the tourism value determination model is obtained by pre-training a model through a training set, and the training set includes sample tourism resource information, sample corridor landscape information, a first tourism value and a second tourism value of each sample tourist highway in a plurality of sample tourist highways, wherein the first tourism value is the value set for the sample tourist highway by tourists who have traveled on the sample tourist highway, and the second tourism value is a value determined according to a preset scoring standard; Wherein, before inputting the initial tourism value, tourism resource information and corridor landscape information of the tourist highway to be processed into the tourism value determination model and obtaining the target tourism value output by the tourism value determination model, the tourism value determination device of the tourist highway further includes a training module for: Obtaining sample tourism resource information, sample corridor landscape information and first tourism value of each sample tourism highway among multiple sample tourism highways; For each sample tourist highway, determining the tourist resource score corresponding to the sample tourist highway in the preset scoring standard according to the sample tourist resource information of the sample tourist highway; Determining the corridor landscape score corresponding to the sample tourist highway in the preset scoring standard according to the sample corridor landscape information of the sample tourist highway; Determining the second tourism value of the sample tourist highway based on the tourism resource score and the corridor landscape score; Constructing the training set according to the sample tourism resource information, the sample corridor landscape information, the first tourism value and the second tourism value of each sample tourism highway among the multiple sample tourism highways; Perform training according to the training set to generate the tourism value determination model; Wherein, the training module is specifically used for: Determine the city score corresponding to the sample tourist highway in the preset scoring standard according to the city information of the sample city where the sample tourist highway is located; the city information includes the consumption level, popularity, population, number of news and type of each news of the sample city; According to the substitutability information of the sample tourist highway, determine the substitutability score corresponding to the sample tourist highway in the preset scoring standard; wherein the substitutability information includes the number of other tourist highways around the sample tourist highway, the length of the other tourist highways whose distance from the sample tourist highway is less than the preset distance, the number of similar tourist highways similar to the sample tourist highway, and the similarity between the sample tourist highway and each similar tourist highway; Performing a weighted summation on the tourism resource score, the corridor landscape score, the city score and the substitutability score, and determining the processed value as the second tourism value of the sample tourist highway, wherein the weight of the corridor landscape score is greater than the weight of the tourism resource score, the weight of the tourism resource score is greater than the weight of the substitutability score, and the weight of the substitutability score is greater than the weight of the city score; The corridor landscape score is composed of at least one of a visual landscape score, a natural landscape score, a cultural landscape score, a historical landscape score or a recreational landscape score; The corridor landscape score also includes a landscape uniqueness score and a landscape point accessibility score; Among them, the second tourism value of the sample tourist highway can be calculated by the formula: Y=aX1+bX2+cX3+dX4, Y is the second tourism value, X1 is the tourism resource score, X2 is the corridor landscape score, X3 is the substitutability score, X4 is the city score, a is the weight of the tourism resource score, b is the weight of the corridor landscape score, c is the weight of the substitutability score, d is the weight of the city score, a+b+c+d=1, the relationship between a, b, c, d, e can satisfy d<c<a<b; Among them, the similarity between tourist roads is composed of the first similarity of tourist resources and the second similarity of corridor landscape; Wherein, the generation module is specifically used for: According to each analysis indicator and the target probability distribution of each analysis indicator, correlation analysis is performed on all analysis indicators to determine the correlation information between all analysis indicators; Based on the correlation information, the plurality of random samples are generated through a multivariate distribution.

5. An electronic device comprising: A processor, a memory, and a computer-executable instruction stored in the memory and executable on the processor, wherein the processor is used to implement the method according to any one of claims 1 to 3 when executing the computer-executable instruction.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 4 when executed by a processor.

7. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it is used to implement the method according to any one of claims 1 to 3.

Images