A method and system for value analysis of ecological products based on deep learning

Abstract

The present invention relates to the technical field of ecological product value analysis. A method and system for ecological product value analysis based on deep learning includes: determining a cultural scenic area, obtaining a group of popular scenic spot areas, sequentially extracting a popular scenic spot area from the group of popular scenic spot areas, and performing the following operations on each of the extracted popular scenic spot areas: obtaining the biodiversity value, calculating the air purification value of the popular scenic spot area, obtaining the air purification value threshold, performing a green vegetation optimization operation on the popular scenic spot area to obtain an optimized area scenic spot, obtaining the optimization cost value of the optimized area scenic spot, summarizing the optimal value scenic spots, obtaining the optimal value scenic spot group corresponding to the group of popular scenic spot areas, and completing the ecological product value analysis based on deep learning based on the optimization cost value and the optimal value scenic spot group. The present invention can improve the accurate evaluation of ecological product value and the scientific management of ecological resources.

Description

Technical Field

[0001] The present invention relates to the technical field of ecological product value analysis, and in particular, to a method and system for realizing the value analysis of ecological products based on deep learning. Background Art

[0002] Deep learning is a method of enabling a computer to automatically learn complex patterns and features from a large amount of data through constructing a neural network model with multiple layers, so as to realize tasks such as classification, prediction, and generation of data. An ecological product refers to a product of natural elements and ecosystem services that maintains ecological security, provides ecological regulation functions, ensures good ecology, and meets human well-being.

[0003] An ecosystem is constantly changing, and its value will also change with time and the environment. Most traditional methods are static evaluations, which cannot timely reflect the dynamic changes of the value of ecological products and are difficult to meet the real-time needs of ecological management and decision-making. Secondly, traditional systems lack the ability to comprehensively analyze the values of multiple ecological products. Therefore, how to improve the accurate evaluation of the value of ecological products and the scientific management of ecological resources. Summary of the Invention

[0004] The present invention provides a method for realizing the value analysis of ecological products based on deep learning and a computer-readable storage medium, and its main purpose is to improve the accurate evaluation of the value of ecological products and the scientific management of ecological resources.

[0005] To achieve the above object, a method for realizing the value analysis of ecological products based on deep learning provided by the present invention includes:

[0006] Determine a cultural scenic area, where the cultural scenic area includes multiple scenic spots, and each scenic spot in the area includes a camera;

[0007] Obtain a group of popular scenic spots based on multiple scenic spots, where the group of popular scenic spots includes multiple popular scenic spots;

[0008] Successively extract a popular scenic spot from the group of popular scenic spots, and perform the following operations on each of the extracted popular scenic spots:

[0009] Receive an ecological value analysis instruction, and obtain the biodiversity value according to the popular scenic spot and the ecological value analysis instruction;

[0010] Calculate the air purification value of the popular scenic spot according to the biodiversity value, obtain the air purification value threshold, and compare the air purification value with the air purification value threshold;

[0011] If the air purification value is greater than or equal to the air purification value threshold, then use the popular scenic spot as the scenic spot with the optimal value;

[0012] If the value of purifying air is less than the purifying air value threshold, perform a green vegetation optimization operation on the popular scenic area to obtain an optimized scenic area, obtain the optimization cost value of the optimized scenic area, use the optimized scenic area as the popular scenic area, and return to the step of obtaining the biodiversity value according to the popular scenic area and the ecological value analysis instruction;

[0013] Summarize the optimal value scenic spots and the optimization cost value respectively to obtain the optimal value scenic spot group and the optimization cost value group corresponding to the popular scenic area group, and complete the value analysis of ecological products based on deep learning based on the optimization cost value group and the optimal value scenic spot group.

[0014] Optionally, the obtaining of the popular scenic area group based on multiple scenic areas includes:

[0015] Obtain a tourist flow group, a tourist evaluation group, and a scenic spot income group based on multiple scenic areas, where the tourist flow group includes multiple tourist flow values, the tourist evaluation group includes multiple tourist evaluation values, the scenic spot income group includes multiple scenic spot income values, and the tourist flow values, tourist evaluation values, and scenic spot income values correspond to the scenic areas one by one;

[0016] Obtain a comprehensive evaluation index group based on multiple scenic areas, the tourist flow group, the tourist evaluation group, and the scenic spot income group, where the comprehensive evaluation index group includes multiple comprehensive evaluation index values;

[0017] After performing a descending sorting operation on each comprehensive evaluation index value in the comprehensive evaluation index group, obtain a sequence comprehensive index group;

[0018] Extract a high-order evaluation index group from the sequence comprehensive index group, and use all the scenic areas corresponding to the high-order evaluation index group as the popular scenic area group.

[0019] Optionally, the obtaining of the tourist flow group, the tourist evaluation group, and the scenic spot income group based on multiple scenic areas includes:

[0020] Extract one scenic area from multiple scenic areas in sequence, and perform the following operations on the extracted scenic areas:

[0021] Use the camera and the preset shooting frequency to shoot the scenic area to obtain a video of the scenic area for sightseeing, where the video of the scenic area for sightseeing includes multiple images of the scenic area for sightseeing;

[0022] Perform a blurred image screening operation on each image of the scenic area for sightseeing to obtain a set of clear scenic images, where the set of clear scenic images is a set of images of multiple tourists, and one tourist corresponds to multiple clear scenic images in the set of clear scenic images;

[0023] Extract tourists in sequence from multiple tourists, and obtain the first appearance time and the second appearance time of the tourists based on the clear scenic spot image set;

[0024] Obtain the residence time based on the first appearance time and the second appearance time, where the residence time is the difference obtained by subtracting the first appearance time from the second appearance time;

[0025] Judge the residence time and the preset residence time threshold;

[0026] If it is confirmed that the residence time is greater than or equal to the preset residence time threshold, obtain the initial tourist image based on the first appearance time;

[0027] Summarize the initial tourist images to obtain an initial tourist image set, and obtain the tourist flow value based on the initial tourist image set;

[0028] Summarize the tourist flow values to obtain a tourist flow group corresponding to multiple scenic spot areas, and obtain a tourist evaluation group and a scenic spot income group based on the multiple scenic spot areas.

[0029] Optionally, obtaining a comprehensive evaluation index group based on multiple scenic spot areas, a tourist flow group, a tourist evaluation group and a scenic spot income group includes:

[0030] Extract a scenic spot area from multiple scenic spot areas in sequence, and perform the following operations on the extracted scenic spot areas:

[0031] Extract the tourist flow values from the tourist flow group in sequence, and perform the following operations on the extracted tourist flow values:

[0032] Perform a standardization operation on the tourist flow value to obtain an initial tourist flow value, and judge whether the initial tourist flow value is a preset extreme value;

[0033] If the initial tourist flow value is a preset extreme value, perform a translation process on the initial tourist flow value to obtain a standard tourist flow value;

[0034] If the initial tourist flow value is not a preset extreme value, use the initial tourist flow value as the standard tourist flow value;

[0035] Calculate the tourist flow proportion of the standard tourist flow value, calculate the tourist flow entropy value according to the tourist flow proportion, and calculate the tourist flow weight according to the tourist flow entropy value;

[0036] According to the tourist flow value, determine the corresponding tourist evaluation value and scenic spot income value from the tourist evaluation group and the scenic spot income group respectively, and obtain the tourist evaluation weight and the scenic spot income weight based on the tourist evaluation value and the scenic spot income value;

[0037] Calculate the comprehensive evaluation index value according to the tourist flow weight, tourist evaluation weight and scenic spot income weight;

[0038] Summarize the comprehensive evaluation index values to obtain a comprehensive evaluation index group corresponding to multiple scenic spot areas.

[0039] Optionally, the obtaining of the tourist flow value based on the initial tourist image set includes:

[0040] Sort the initial tourist image set to obtain an arranged tourist image set, sequentially extract one arranged tourist image from the arranged tourist image set, and perform the following operations on each of the extracted arranged tourist images:

[0041] Take the arranged tourist image as the target tourist image, remove the target tourist image from the arranged tourist image set to obtain a removed tourist image set;

[0042] Sequentially extract removed tourist images from the removed tourist image set, and perform the following operations on each of the extracted removed tourist images:

[0043] Perform a similarity detection operation on the target tourist image and the removed tourist images to obtain an image similarity;

[0044] If the image similarity is greater than or equal to a preset image similarity threshold, take the removed tourist image as a candidate tourist image, summarize the candidate tourist images to obtain a candidate tourist image set, identify the marked tourist image from the candidate tourist image set, and combine the marked tourist image and the target tourist image to obtain a target tourist image group;

[0045] Remove the candidate tourist image set from the removed tourist image set to obtain an updated tourist image set, take the updated tourist image set as the arranged tourist image set, and return to the step of sequentially extracting one arranged tourist image from the arranged tourist image set until the updated tourist image set is an empty set;

[0046] Summarize the target tourist image groups to obtain a target tourist image group set, obtain the number of target tourist image groups in the target tourist image group set, and take the number of target tourist image groups as the tourist flow value.

[0047] Optionally, the performing of a blurred image screening operation on each of the multiple scenic spot area images to obtain a clear scenic spot image set includes:

[0048] Sequentially extract scenic spot area images from the multiple scenic spot area images, perform a grayscale operation on the scenic spot area images to obtain grayscale scenic spot area images, and perform an image segmentation operation on the grayscale scenic spot area images to obtain a segmented image set;

[0049] Successively extract the segmented images from the segmented image set, perform denoising operations on the segmented images using a pre-constructed filtering algorithm to obtain filtered segmented images, and calculate the variance of the filtered segmented images;

[0050] Accumulate the variances to obtain a comprehensive variance, and determine whether the comprehensive variance is within a preset comprehensive variance interval;

[0051] If the comprehensive variance is within the preset comprehensive variance interval, then use the scenic spot image of the scenic area corresponding to the comprehensive variance as the clear scenic spot image;

[0052] If the comprehensive variance is not within the preset comprehensive variance interval, then eliminate the image of the scenic area of the scenic spot corresponding to the comprehensive variance, summarize the remaining images of the scenic areas of the scenic spots to obtain multiple updated images of the scenic areas, use the multiple updated images of the scenic areas as multiple images of the scenic areas of the scenic spots, and return to the step of successively extracting the images of the scenic areas of the scenic spots from the multiple images of the scenic areas of the scenic spots;

[0053] Summarize the clear scenic spot images to obtain a set of clear scenic spot images corresponding to multiple images of the scenic areas of the scenic spots.

[0054] Optionally, the obtaining of the biodiversity value according to the popular scenic area and the ecological value analysis instruction includes:

[0055] Obtain a set of scenic area images according to the popular scenic area and a pre-constructed drone, and obtain the area of the scenic area and a set of species images according to the set of scenic area images;

[0056] Perform the following operations on each species image in the set of species images:

[0057] Match the species image with a pre-constructed species database to obtain the species type, and summarize the species types to obtain a set of species types;

[0058] Perform species type classification operations on the set of species types to obtain a set of rare and endangered species, a set of endemic species, and a set of ancient tree species, and obtain the species resource conservation value of the scenic area area according to the ecological value analysis instruction;

[0059] Calculate the biodiversity value of the popular scenic area according to the area of the scenic area, the species resource conservation value, the set of rare and endangered species, the set of endemic species, and the set of ancient tree species. The calculation formula of the biodiversity value is as follows:

[0060]

[0061] Among them, Wb represents the biodiversity value, Rn represents the rare and endangered index corresponding to each rare and endangered species, nA variable representing a preset rare and endangered species, Po The index of endemic species for each endemic species, o A variable representing a preset endemic species, Ap The ancient tree age index for each ancient tree species, p A variable representing a preset ancient tree species, C Represents the area of the scenic spot area, a Represents the number of rare and endangered species concentrated in the rare and endangered species, b Represents the number of endemic species concentrated in the endemic species, c Represents the number of ancient tree species concentrated in the ancient tree species, Zb Represents the conservation value of species resources within the area of the scenic spot area.

[0062] Optionally, performing a green vegetation optimization operation on the popular scenic spot area to obtain an optimized area scenic spot includes:

[0063] Obtaining the previous ecosystem state of the popular scenic spot area, where the previous ecosystem state includes: biodiversity value, air purification value, and tourist flow;

[0064] According to the previous ecosystem state, performing an initial green vegetation optimization operation on the popular scenic spot area using a preset vegetation increase area ratio and a preset introduced species type ratio to obtain an initial optimized area;

[0065] Using a preset detection time to detect the initial optimized area to obtain detection data, where the detection data includes: detected biodiversity value, detected air purification value, and detected tourist flow;

[0066] Calculating the initial optimization reward of the initial optimized area based on the detection data, and comparing the initial optimization reward with a preset optimization reward threshold;

[0067] If the initial optimization reward is less than the preset optimization reward threshold, then taking the initial optimized area corresponding to the initial optimization reward less than the preset optimization reward threshold as the popular scenic spot area, and returning to the step of performing the initial green vegetation optimization operation on the popular scenic spot area using a preset vegetation increase area ratio and a preset introduced species type ratio according to the previous ecosystem state;

[0068] If the initial optimization reward is greater than or equal to the preset optimization reward threshold, then taking the initial optimized area as the optimized area scenic spot.

[0069] Optionally, obtaining the optimization cost value of the optimized area scenic spot includes:

[0070] Obtaining the required planting types and planting quantities of the optimized area scenic spot, and obtaining the purchase cost and planting days according to the required planting types and planting quantities;

[0071] Obtain the transportation starting point and the transportation ending point, obtain the transportation route according to the transportation starting point and the transportation ending point, and calculate the transportation cost according to the transportation route;

[0072] Obtain the labor cost, scenic spot impact cost and rental cost according to the planting days and the preset daily per capita wage;

[0073] Obtain the optimized cost value based on the purchase cost, transportation cost, labor cost, scenic spot impact cost and rental cost.

[0074] To achieve the above object, the present invention also provides a value analysis system for ecological products based on deep learning, including:

[0075] A scenic spot area determination module for determining a cultural scenic area, wherein the cultural scenic area includes a plurality of scenic spot areas, and each area scenic spot includes a camera, and obtaining a group of popular scenic spot areas based on the plurality of scenic spot areas, wherein the group of popular scenic spot areas includes a plurality of popular scenic spot areas;

[0076] An air value analysis module for sequentially extracting a popular scenic spot area from the group of popular scenic spot areas, and performing the following operations on each of the extracted popular scenic spot areas: receiving an ecological value analysis instruction, obtaining the biodiversity value according to the popular scenic spot area and the ecological value analysis instruction, calculating the air purification value of the popular scenic spot area according to the biodiversity value, obtaining the air purification value threshold, and comparing the air purification value with the air purification value threshold;

[0077] A green vegetation optimization module for, if the air purification value is greater than or equal to the air purification value threshold, taking the popular scenic spot area as the optimal value scenic spot, and if the air purification value is less than the air purification value threshold, performing a green vegetation optimization operation on the popular scenic spot area to obtain an optimized area scenic spot, obtaining the optimized cost value of the optimized area scenic spot, taking the optimized area scenic spot as the popular scenic spot area, and returning to the step of obtaining the biodiversity value according to the popular scenic spot area and the ecological value analysis instruction;

[0078] A deep learning value analysis module for respectively summarizing the optimal value scenic spots and the optimized cost values to obtain a group of optimal value scenic spots and a group of optimized cost values corresponding to the group of popular scenic spot areas, and completing the value analysis of ecological products based on deep learning based on the group of optimized cost values and the group of optimal value scenic spots.

[0079] To solve the above problems, the present invention also provides an electronic device, and the electronic device includes:

[0080] A memory storing at least one instruction;

[0081] A processor that executes instructions stored in the memory to implement the method for value analysis of ecological products based on deep learning as described above.

[0082] To solve the above problems, the present invention also provides a computer-readable storage medium storing at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the method for value analysis of ecological products based on deep learning as described above.

[0083] To solve the problems described in the background art, the present invention determines a cultural scenic area, wherein the cultural scenic area includes multiple scenic spots areas, and each area scenic spot includes a camera. The present invention divides the cultural scenic area into multiple scenic spots areas, which helps to carry out refined management and analysis of the scenic area. Different scenic spots areas may have different ecological characteristics and functions. By analyzing them separately, the ecological value of each area can be evaluated more accurately. Based on multiple scenic spots areas, a group of popular scenic spots areas is obtained, wherein the group of popular scenic spots areas includes multiple popular scenic spots areas. The present invention screens out the group of popular scenic spots areas from numerous scenic spots areas, which can focus the analysis on those areas that are popular among tourists and have relatively frequent ecological activities. This can improve the efficiency and pertinence of the analysis and avoid waste of resources caused by undifferentiated analysis of all scenic spots areas. One popular scenic spots area is sequentially extracted from the group of popular scenic spots areas, and the following operations are performed on each of the extracted popular scenic spots areas: receiving an ecological value analysis instruction, and obtaining the biodiversity value according to the popular scenic spots area and the ecological value analysis instruction. The present invention receives the ecological value analysis instruction to clarify the goals and requirements of the analysis, and obtains the biodiversity value in combination with the actual situation of the popular scenic spots area. Biodiversity is an important indicator of the health and stability of the ecosystem. Accurately evaluating the biodiversity value can provide a scientific basis for the value analysis of ecological products and help understand the richness of the scenic area ecosystem and the integrity of the ecological functions. Calculate the air purification value of the popular scenic spots area according to the biodiversity value, obtain the air purification value threshold, and compare the air purification value with the air purification value threshold. The present invention converts the biodiversity value into the air purification value, realizing the quantitative evaluation of the ecosystem services. Air purification is one of the important functions of the ecosystem. By calculating the air purification value, the contribution of the popular scenic spots area to improving air quality can be intuitively understood, providing specific data support for the economic value evaluation of ecological products. If the air purification value is greater than or equal to the air purification value threshold, then the popular scenic spots area is used as the scenic spot with the optimal value. The present invention determines the popular scenic spots area with the air purification value greater than or equal to the threshold as the scenic spot with the optimal value, which helps to highlight the areas with good ecological functions and high ecological values in the scenic area. These areas can be used as the highlights of the scenic area for publicity and promotion to attract more tourists. If the air purification value is less than the air purification value threshold, then the green vegetation optimization operation is performed on the popular scenic spots area to obtain the optimized area scenic spot, obtain the optimization cost value of the optimized area scenic spot, use the optimized area scenic spot as the popular scenic spots area, and return to the step of obtaining the biodiversity value according to the popular scenic spots area and the ecological value analysis instruction. When the air purification value is less than the threshold, the present invention performs the green vegetation optimization operation on the popular scenic spots area, which can improve the ecological environment of the area and enhance its air purification ability.By increasing vegetation cover, optimizing vegetation structure, etc., the stability and service functions of the ecosystem can be enhanced, the value of biodiversity and the overall value of ecological products can be improved. The optimal value scenic spots and optimization cost values are respectively summarized to obtain the optimal value scenic spot group and optimization cost value group corresponding to the popular scenic spot area group. Based on the optimization cost value group and the optimal value scenic spot group, the value analysis of ecological products is realized based on deep learning. The present invention completes the value analysis of ecological products based on the optimization cost value and the optimal value scenic spot group, realizes the comprehensive evaluation of ecological products, not only considers the functions and service values of the ecosystem, but also considers the costs paid to improve these values, making the evaluation results more comprehensive, objective and accurate, and helping scenic spot managers formulate scientific and reasonable development strategies. Therefore, the present invention can improve the accurate evaluation of the value of ecological products and the scientific management of ecological resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] Figure 1 FIG. is a schematic flowchart of a method for realizing value analysis of ecological products based on deep learning provided by an embodiment of the present invention.

[0085] Figure 2 FIG. is a functional module diagram of a system for realizing value analysis of ecological products based on deep learning provided by an embodiment of the present invention.

[0086] Figure 3 FIG. is a schematic structural diagram of an electronic device for realizing the method for realizing value analysis of ecological products based on deep learning provided by an embodiment of the present invention.

[0087] Description of reference numerals: 1, electronic device; 10, processor; 11, memory; 12, bus. The realization, functional characteristics and advantages of the purpose of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0088] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0089] An embodiment of the present application provides a method for realizing value analysis of ecological products based on deep learning. The execution subject of the method for realizing value analysis of ecological products based on deep learning includes but is not limited to at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for realizing value analysis of ecological products based on deep learning can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0090] Refer to Figure 1As shown in the figure, it is a schematic flowchart of a method for value analysis of ecological products based on deep learning provided by an embodiment of the present invention. In this embodiment, the method for value analysis of ecological products based on deep learning includes:

[0091] S1. Determine a cultural scenic area, where the cultural scenic area includes multiple scenic spots, and each scenic spot includes a camera.

[0092] It should be explained that a cultural scenic area refers to a geographical area with specific cultural connotations and tourism functions. A scenic spot refers to a relatively independent sub-area within a cultural scenic area with unique landscapes or functions.

[0093] Exemplarily, there is a cultural scenic area, namely Humble Administrator's Garden in Suzhou. Humble Administrator's Garden in Suzhou includes the East Garden area, the West Garden area, and the Middle Garden area, that is, the East Garden area, the West Garden area, and the Middle Garden area are all scenic spots.

[0094] S2. Obtain a group of popular scenic spots based on multiple scenic spots, where the group of popular scenic spots includes multiple popular scenic spots.

[0095] Specifically, the obtaining of the group of popular scenic spots based on multiple scenic spots includes:

[0096] Obtain a group of tourist flows, a group of tourist evaluations, and a group of scenic spot revenues based on multiple scenic spots. The group of tourist flows includes multiple tourist flow values, the group of tourist evaluations includes multiple tourist evaluation values, the group of scenic spot revenues includes multiple scenic spot revenue values, and the tourist flow values, tourist evaluation values, and scenic spot revenue values correspond to the scenic spots one by one;

[0097] Obtain a group of comprehensive evaluation indicators based on multiple scenic spots, the group of tourist flows, the group of tourist evaluations, and the group of scenic spot revenues. The group of comprehensive evaluation indicators includes multiple comprehensive evaluation indicator values;

[0098] After performing a descending order sorting operation on each comprehensive evaluation indicator value in the group of comprehensive evaluation indicators, obtain a sequence of comprehensive indicator groups;

[0099] Extract a group of high-order evaluation indicators from the sequence of comprehensive indicator groups, and use all the scenic spots corresponding to the group of high-order evaluation indicators as the group of popular scenic spots.

[0100] It should be noted that the tourist flow value is an indicator that measures the number of tourists visiting a scenic area within a certain period of time. For example, if the number of tourists visiting a scenic area within a month is 2,000, then 2,000 is the tourist flow value. The tourist evaluation value refers to the comprehensive evaluation score given by tourists to the scenic area. The scenic area income value refers to the economic benefits obtained by the scenic area within a certain period of time. For example, the economic benefits include catering, souvenir sales, etc. The sequence comprehensive index group refers to the set obtained after sorting the comprehensive evaluation index group in descending order. By sorting in descending order, the scenic areas with higher comprehensive evaluations can be quickly found. In this method, the scenic areas corresponding to the first three comprehensive evaluation index values are extracted from the sequence comprehensive index group as the popular scenic area group. In this way, the most attractive, best-operating, and highest tourist-satisfaction scenic areas in the scenic area can be accurately screened out, which helps the scenic area to highlight the key points, concentrate resources for development and promotion, and enhance the overall competitiveness and popularity of the scenic area. The high-order evaluation index group refers to the set composed of the first three comprehensive evaluation index values in the sequence comprehensive index group.

[0101] Specifically, obtaining the tourist flow group, tourist evaluation group, and scenic area income group based on multiple scenic areas includes:

[0102] Extract one scenic area in sequence from multiple scenic areas, and perform the following operations on the extracted scenic area:

[0103] Use the camera and the preset shooting frequency to shoot the scenic area to obtain a video of the scenic area being visited. Among them, the video of the scenic area being visited includes multiple images of the scenic area being visited;

[0104] Perform a blurred image screening operation on each image of the scenic area being visited in the multiple images of the scenic area being visited to obtain a set of clear scenic area images. Among them, the set of clear scenic area images is a set of images of multiple tourists, and one tourist corresponds to multiple clear scenic area images in the set of clear scenic area images;

[0105] Extract tourists in sequence from multiple tourists, and obtain the first appearance time and the second appearance time of the tourists based on the set of clear scenic area images;

[0106] Obtain the residence time based on the first appearance time and the second appearance time. Among them, the residence time is the difference obtained by subtracting the first appearance time from the second appearance time;

[0107] Judge the residence time and the preset residence time threshold;

[0108] If it is confirmed that the residence time is greater than or equal to the preset residence time threshold, obtain the initial tourist image based on the first appearance time;

[0109] Summarize the initial tourist images to obtain a set of initial tourist images, and obtain the tourist flow value based on the set of initial tourist images;

[0110] Summarize the tourist flow values to obtain a tourist flow group corresponding to multiple scenic areas, and obtain a tourist evaluation group and a scenic area income group based on the multiple scenic areas.

[0111] It should be explained that the shooting frequency refers to the number of times the camera shoots the scenic area at a preset time interval. For example, the shooting frequency is 1 second. The scenic area tour image refers to an image obtained by the camera during the process of shooting the scenic area. The clear scenic area image set refers to the set of clear images obtained after performing a blurred image screening operation on multiple scenic area tour images. Since various factors may affect the shooting process, such as light, etc., resulting in some images being blurred, it is necessary to perform a blurred image screening operation on multiple scenic area tour images. The tourist tour image is an image formed by separately extracting the tourist part in the clear scenic area image through image recognition technology. For example, the image recognition technology is FasterR-CNN, YOLO, etc.

[0112] It can be understood that the first appearance time refers to the time when the tourist tour image is first detected in the clear scenic area image set. The second appearance time refers to the time when the tourist tour image is last detected in the clear scenic area image set. The residence time threshold is a preset time standard used to determine whether a tourist is visiting the scenic area. By setting the residence time threshold, those tourists who just pass by briefly can be filtered out, improving the accuracy of tourist flow statistics and more accurately reflecting the actual attractiveness of the scenic area. The initial tourist image refers to the image corresponding to the first appearance time. The initial tourist image set is a set obtained by summarizing the initial tourist images corresponding to multiple scenic area tour images. The tourist flow group is a set composed of tourist flow values corresponding to multiple scenic areas. The obtaining of the tourist evaluation group and the scenic area income group based on multiple scenic areas means collecting the tourist evaluation values of each scenic area in multiple scenic areas from multiple online travel platforms (such as Ctrip, Qunar, Mafengwo, etc.) to obtain the tourist evaluation group, and collecting the daily income values of each scenic area in multiple scenic areas to obtain the scenic area income group.

[0113] Specifically, obtaining the comprehensive evaluation index group based on multiple scenic areas, the tourist flow group, the tourist evaluation group, and the scenic area income group includes:

[0114] Successively extract a scenic area from multiple scenic areas, and perform the following operations on the extracted scenic area:

[0115] Successively extract the tourist flow values from the tourist flow group, and perform the following operations on the extracted tourist flow values:

[0116] Perform a standardization operation on the tourist flow value to obtain an initial tourist flow value, and determine whether the initial tourist flow value is a preset extreme value;

[0117] If the initial tourist flow value is a preset extreme value, perform a translation process on the initial tourist flow value to obtain a standard tourist flow value;

[0118] If the initial tourist flow value is not a preset extreme value, use the initial tourist flow value as the standard tourist flow value;

[0119] Calculate the tourist flow proportion of the standard tourist flow value, calculate the tourist flow entropy value based on the tourist flow proportion, and calculate the tourist flow weight based on the tourist flow entropy value;

[0120] According to the tourist flow value, respectively determine the corresponding tourist evaluation value and scenic spot income value from the tourist evaluation group and the scenic spot income group, and obtain the tourist evaluation weight and the scenic spot income weight based on the tourist evaluation value and the scenic spot income value;

[0121] Calculate the comprehensive evaluation index value according to the tourist flow weight, the tourist evaluation weight and the scenic spot income weight;

[0122] Summarize the comprehensive evaluation index values to obtain a comprehensive evaluation index group corresponding to multiple scenic spot areas.

[0123] It should be explained that the operation of performing standardization on the tourist flow value refers to the operation of converting the tourist flow value into data of a unified scale by using a standardization method, so that the tourist flow values of different scenic spot areas are comparable. For example, the standardization methods include Z-score standardization, Min-Max standardization, etc. The initial tourist flow value refers to the value obtained after performing the standardization operation on the tourist flow value. The extreme value refers to a value that deviates significantly. For example, the extreme value is -1. The steps of performing a translation process on the initial tourist flow value to obtain a standard tourist flow value are as follows: Use the following formula to perform a translation process on the initial tourist flow value, where the formula is as follows:

[0124] u = u 1 + ku

[0125] Wherein, u represents the standard tourist flow value, u 1 represents the initial tourist flow value, kRepresents a preset translation amplitude. The translation amplitude is a numerical value used to adjust the initial tourist flow value. The purpose of the translation amplitude is that when the initial tourist flow value is determined to be an extreme value, by adding this translation amplitude to the initial tourist flow value, it can be transformed into a standard tourist flow value. The standard tourist flow value refers to the tourist flow value when the initial tourist flow value is not a preset extreme value. The calculation formula in the step of calculating the tourist flow proportion of the standard tourist flow value is as follows:

[0126]

[0127] Among them, pi Represents the tourist flow proportion of the i th scenic area, ui Represents the standard tourist flow value of the i th scenic area, n Represents the number of scenic areas. The calculation formula in the step of calculating the tourist flow entropy value based on the tourist flow proportion is as follows:

[0128]

[0129] Among them, E Represents the tourist flow entropy value, and ln(*) represents the natural logarithm function. The step of calculating the tourist flow weight based on the tourist flow entropy value is a prior art and will not be elaborated here.

[0130] It can be understood that the method of obtaining the tourist evaluation weight and the scenic area income weight based on the tourist evaluation value and the scenic area income value is the same as the method of obtaining the tourist flow weight based on the tourist flow value, and will not be elaborated here.

[0131] Specifically, the obtaining of the tourist flow value based on the initial tourist image set includes:

[0132] Sort the initial tourist image set to obtain an arranged tourist image set, and sequentially extract an arranged tourist image from the arranged tourist image set, and perform the following operations on each extracted arranged tourist image:

[0133] Take the arranged tourist image as the target tourist image, and remove the target tourist image from the arranged tourist image set to obtain a removed tourist image set;

[0134] Sequentially extract removed tourist images from the removed tourist image set, and perform the following operations on each extracted removed tourist image:

[0135] Perform a similarity detection operation on the target tourist image and the removed tourist images to obtain an image similarity;

[0136] If the image similarity is greater than or equal to a preset image similarity threshold, then use the image after removing tourists as a candidate tourist image, aggregate the candidate tourist images to obtain a set of candidate tourist images, identify the marked tourist images from the set of candidate tourist images, and combine the marked tourist images and the target tourist images to obtain a set of target tourist images;

[0137] Remove the set of candidate tourist images from the set of images after removing tourists to obtain an updated set of tourist images, use the updated set of tourist images as a set of arranged tourist images, and return to the step of sequentially extracting one arranged tourist image from the set of arranged tourist images until the updated set of tourist images is an empty set;

[0138] Aggregate the set of target tourist images to obtain a set of target tourist image groups, obtain the number of target tourist image groups in the set of target tourist image groups, and use the number of target tourist image groups as the tourist flow value.

[0139] It should be explained that sorting the initial set of tourist images means sorting the initial set of tourist images according to the time sequence of camera shooting. The set of arranged tourist images refers to the set of arranged tourist images obtained after sorting the initial set of tourist images. The target tourist image refers to an image extracted from the set of arranged tourist images. The set of images after removing tourists refers to the set of remaining images after removing the target tourist image from the set of arranged tourist images when the target tourist image is extracted from the set of arranged tourist images. The image after removing tourists refers to each image sequentially extracted from the set of images after removing tourists. The image similarity is an index measuring the similarity degree between the target tourist image and the image after removing tourists. Performing the similarity detection operation on the target tourist image and the image after removing tourists means performing the similarity detection operation on the target tourist image and the image after removing tourists using an image similarity detection method. For example, the image similarity detection method is a feature extraction method, a deep learning method, etc.

[0140] Importantly, the image similarity threshold is a preset standard value used to determine whether the tourists in two images are the same tourist. The candidate tourist image refers to the image after removing tourists when the image similarity between the target tourist image and the image after removing tourists is greater than or equal to the preset image similarity threshold. The set of candidate tourist images refers to the set obtained by aggregating all candidate tourist images whose image similarity with the target tourist image is greater than or equal to the threshold. The marked tourist image refers to the first candidate tourist image whose image similarity with the target tourist image is greater than or equal to the preset image similarity threshold. Exemplarily, the set of candidate tourist images is: (Candidate tourist image 1, Candidate tourist image 2, Candidate tourist image 3), that is, Candidate tourist image 1 is the marked tourist image.

[0141] It is understandable that the target tourist image group refers to the combination of the identified tourist image and the target tourist image. The target tourist image group represents the records of the same tourist in different images. Updating the tourist image set means the remaining image set after removing the candidate tourist image set from the removed tourist image set. The target tourist image group set refers to the set composed of all target tourist image groups. The target tourist image group quantity refers to the quantity of target tourist image groups in the target tourist image group set.

[0142] Specifically, performing a blurred image screening operation on each of the multiple scenic spot area images to obtain a clear scenic spot image set includes:

[0143] Sequentially extracting scenic spot area images from the multiple scenic spot area images, performing a grayscale operation on the scenic spot area images to obtain grayscale scenic spot area images, and performing an image segmentation operation on the grayscale scenic spot area images to obtain a segmentation image set;

[0144] Sequentially extracting segmentation images from the segmentation image set, performing a denoising operation on the segmentation images using a pre - constructed filtering algorithm to obtain filtered segmentation images, and calculating the variance of the filtered segmentation images;

[0145] Accumulating the variances to obtain a comprehensive variance, and determining whether the comprehensive variance is within a preset comprehensive variance interval;

[0146] If the comprehensive variance is within the preset comprehensive variance interval, then taking the scenic spot area image corresponding to the comprehensive variance as a clear scenic spot image;

[0147] If the comprehensive variance is not within the preset comprehensive variance interval, then removing the scenic spot area image corresponding to the comprehensive variance, summarizing the remaining scenic spot area images to obtain multiple updated scenic spot area images, taking the multiple updated scenic spot area images as the multiple scenic spot area images, and returning to the step of sequentially extracting scenic spot area images from the multiple scenic spot area images;

[0148] Summarizing the clear scenic spot images to obtain the clear scenic spot image set corresponding to the multiple scenic spot area images.

[0149] It should be noted that the grayscale operation refers to the operation of converting the color image of the scenic spots in the tour area into a grayscale image. The purpose of the grayscale operation is that the grayscale image is simpler to process, has less computational complexity, and can retain the main structural information of the image. The step of performing the grayscale operation on the image area of the scenic spots is a prior art and will not be elaborated here. The grayscale scenic area image refers to the image obtained after the grayscale operation. The step of performing the image segmentation operation on the grayscale scenic area image refers to performing the image segmentation operation on the grayscale scenic area image by using the clustering segmentation method. For example, the clustering segmentation method is the K-means clustering algorithm. The segmented image set refers to the set of multiple sub-images obtained by segmenting the grayscale scenic area image. The filtering algorithm is an algorithm used to remove noise in the image. For example, mean filtering, median filtering, Gaussian filtering, etc. The filtered segmented image refers to the image obtained by applying the filtering algorithm to the segmented image for denoising. After the filtering process, the noise in the segmented image is suppressed, and the filtered segmented image is clearer, which is beneficial for subsequent analysis and calculation. The step of calculating the variance of the filtered segmented image is as follows: obtain the total pixel value of the filtered segmented image, calculate the mean of the total pixel value, calculate the square of the difference between each pixel value in the total pixel value and the mean to obtain a set of squares, calculate the mean of the set of squares, and take the mean of the set of squares as the variance. The comprehensive variance refers to the sum of all variances. The comprehensive variance interval refers to a preset range used to determine whether the image of the scenic spots in the tour area is clear. The clear scenic image refers to the image whose comprehensive variance of the image of the scenic spots in the tour area is within the preset comprehensive variance interval. The clear scenic image set refers to the set composed of all clear scenic images.

[0150] S3. Sequentially extract a popular scenic area from the group of popular scenic areas, and perform the following operations on each of the extracted popular scenic areas: receive an ecological value analysis instruction, and obtain the biodiversity value according to the popular scenic area and the ecological value analysis instruction.

[0151] It should be noted that the ecological value analysis instruction refers to an instruction issued by a human for evaluating the biodiversity value of a popular scenic area.

[0152] Specifically, the step of obtaining the biodiversity value according to the popular scenic area and the ecological value analysis instruction includes:

[0153] Obtain the scenic area image set according to the popular scenic area and the pre-constructed unmanned aerial vehicle, and obtain the scenic area area and the species image set according to the scenic area image set;

[0154] Perform the following operations on each species image in the species image set:

[0155] Match the species image with the pre-constructed species database to obtain the species type, and summarize the species types to obtain the species type set;

[0156] Perform species type classification operations on the set of species types to obtain a set of rare and endangered species, a set of endemic species, and a set of ancient tree species, and obtain the conservation value of species resources for the scenic area area according to the ecological value analysis instruction;

[0157] Calculate the biodiversity value of popular scenic areas based on the scenic area area, the conservation value of species resources, the set of rare and endangered species, the set of endemic species, and the set of ancient tree species. The calculation formula for the biodiversity value is as follows:

[0158]

[0159] Among them, Wb represents the biodiversity value, Rn represents the rare and endangered index corresponding to each rare and endangered species, n represents the variable of the preset rare and endangered species, Po represents the endemic species index of each endemic species, o represents the variable of the preset endemic species, Ap represents the ancient tree age index of each ancient tree species, p represents the variable of the preset ancient tree species, C represents the scenic area area, a represents the number of rare and endangered species in the set of rare and endangered species, b represents the number of endemic species in the set of endemic species, c represents the number of ancient tree species in the set of ancient tree species, Zb represents the conservation value of species resources within the scenic area area.

[0160] It should be explained that the scenic area image set refers to the set of images obtained by a drone taking pictures over a popular scenic area. Obtaining the scenic area area and species image set from the scenic area image set means using image processing techniques (such as Canny edge detection) to obtain the scenic area area and using object detection algorithms (such as YOLO, Faster R-CNN, etc.) to obtain the species image set. The species database refers to a pre-constructed database that stores a large amount of data such as images, feature descriptions, and classification information of known species. The species type set refers to the set obtained by summarizing the species types matched from each species image in the species image set. The operation of performing species type classification on the species type set refers to performing species type classification on the species type set according to rare and endangered species, endemic species, and ancient tree species. The rare and endangered species set refers to the set of rare and endangered species in the species type set. For example, the rare and endangered species is Davidia involucrata. The endemic species set refers to the set of species endemic to a specific area in the species type set. The ancient tree species set refers to the set of ancient tree species in the species type set. The conservation value of species resources refers to the economic value corresponding to the rare and endangered species set, endemic species set, and ancient tree species set in the scenic area area. The economic value is through the value of rare and endangered species, endemic species, and ancient tree species in the market.

[0161] The steps of matching the species image with the pre-constructed species database are as follows: sequentially extract a species matching image from the species database, and use a deep learning matching model to match the species matching image with the species image. For example, the deep learning matching model is a siamese network, a triplet network, etc.

[0162] Importantly, the biodiversity value is a quantitative indicator to measure the comprehensive situation of biodiversity in a popular scenic area. The higher the biodiversity value, the richer the biodiversity in the popular scenic area. The variable of rare and endangered species means that in the rare and endangered species set, each rare and endangered species has a corresponding identifier. For example, if there are 5 rare and endangered species in the rare and endangered species set, then the variables of the rare and endangered species are taken as 1, 2, 3, 4, 5 in sequence, representing these 5 different rare and endangered species respectively. The endemic species index is a value used to measure the uniqueness and importance of each endemic species. The higher the endemic species index, the higher the importance of the endemic species in the scenic area. The ancient tree age index is a value determined according to the age of the ancient tree, which reflects the historical value and ecological value of the ancient tree. The older the age of the ancient tree, the higher its ancient tree age index. The variables of ancient tree species and endemic species respectively refer to that in the endemic species set and ancient tree species set, each ancient tree species and endemic species has a corresponding identifier. The rare and endangered index is a value used to measure the uniqueness and importance of each rare and endangered species. The higher the rare and endangered index, the higher the importance of the rare and endangered species in the scenic area.

[0163] S4. Calculate the air purification value of the popular scenic area according to the biodiversity value, obtain the air purification value threshold, and compare the air purification value with the air purification value threshold.

[0164] It should be explained that in the step of calculating the air purification value of the popular scenic area according to the biodiversity value, the formula for calculating the air purification value is as follows:

[0165]

[0166] Wherein, Vap represents the air purification value, K represents the preset biodiversity value coefficient, Qv represents the amount of the v th pollutant absorbed by the forest ecosystem, Av represents the area of the forest ecosystem, Nv represents the v th pollutant equivalent value, Cv represents the v th pollutant tax amount. The equivalent value is used to measure the value of different pollutants in terms of environmental impact.

[0167] Importantly, the obtaining of the air purification value threshold refers to obtaining the total air purification value of the cultural scenic area, calculating the mean value of the total air purification value, and taking the mean value of the total air purification value as the air purification value threshold.

[0168] S5. If the air purification value is greater than or equal to the air purification value threshold, then take the popular scenic area as the optimal value scenic area; if the air purification value is less than the air purification value threshold, then perform a green vegetation optimization operation on the popular scenic area to obtain an optimized area scenic area.

[0169] Specifically, the performing of the green vegetation optimization operation on the popular scenic area to obtain an optimized area scenic area includes:

[0170] Obtain the previous ecosystem state of the popular scenic area, where the previous ecosystem state includes: biodiversity value, air purification value, and tourist flow;

[0171] According to the previous ecosystem state, perform an initial green vegetation optimization operation on the popular scenic area by using the preset vegetation increase area ratio and the preset introduced species type ratio to obtain an initial optimized area;

[0172] Use the preset detection time to detect the initial optimized area to obtain detection data, where the detection data includes: detected biodiversity value, detected air purification value, and detected tourist flow;

[0173] Calculate the initial optimization reward for the initial optimization area based on the detection data, and compare the initial optimization reward with a preset optimization reward threshold;

[0174] If the initial optimization reward is less than the preset optimization reward threshold, then use the initial optimization area corresponding to the initial optimization reward that is less than the preset optimization reward threshold as the popular scenic area, and return to the step of performing the initial green vegetation optimization operation on the popular scenic area according to the previous ecosystem state, using the preset vegetation increase area ratio and the preset introduced species type ratio;

[0175] If the initial optimization reward is greater than or equal to the preset optimization reward threshold, then use the initial optimization area as the optimized area scenic spot.

[0176] It should be explained that the previous ecosystem state refers to the state presented by the ecosystem in this area before performing the green vegetation optimization operation on the popular scenic area. For example, the previous ecosystem state is the state presented by the ecosystem in the popular scenic area in the previous month. The vegetation increase area ratio is a preset parameter used to guide the proportion of the vegetation coverage area that needs to be increased in the popular scenic area during the initial green vegetation optimization operation. The introduced species type ratio is a preset parameter that stipulates the proportional relationship between the number of types of newly introduced species and the number of types of original species in the scenic area during the initial green vegetation optimization operation. For example, the preset introduced species type ratio is 10%. Assuming there are originally 100 plant species in the scenic area, then 10 new plant species need to be introduced during the optimization operation, and 10 is the introduced species type ratio. The initial optimization area is the area obtained after performing the initial green vegetation optimization operation on the popular scenic area according to the previous ecosystem state, using the preset vegetation increase area ratio and the preset introduced species type ratio. The optimization reward threshold is a preset standard value.

[0177] It can be understood that the detection time is a preset time period for detecting the initial optimization area. The calculation formula in the step of calculating the initial optimization reward for the initial optimization area based on the detection data is as follows:

[0178]

[0179] Among them, G represents the initial optimization reward, w 1 represents the weight of the preset biodiversity value, B 2 represents the detected biodiversity value, B 1 represents the biodiversity value, w 2 represents the weight of the preset air purification value, O 2 represents the detected air purification value, O 1 represents the air purification value, w3 represents the weight of tourist flow, Z 2 represents detecting tourist flow, Z 1 represents tourist flow.

[0180] S6. Obtain the optimization cost value of the scenic spots in the optimized area, take the scenic spots in the optimized area as the popular scenic spot area, and return the step of obtaining the biodiversity value according to the popular scenic spot area and the ecological value analysis instruction.

[0181] Specifically, the obtaining of the optimization cost value of the scenic spots in the optimized area includes:

[0182] Obtain the required planting types and planting quantities of the scenic spots in the optimized area, and obtain the purchase cost and planting days according to the required planting types and planting quantities;

[0183] Obtain the transportation starting point and the transportation end point, obtain the transportation route according to the transportation starting point and the transportation end point, and calculate the transportation cost according to the transportation route;

[0184] Obtain the labor cost, scenic spot impact cost and leasing cost according to the planting days and the preset daily per capita wage;

[0185] Obtain the optimization cost value based on the purchase cost, transportation cost, labor cost, scenic spot impact cost and leasing cost.

[0186] It should be explained that the required planting type refers to the types of plants that need to be planted when performing green vegetation optimization operations on the scenic spots in the optimized area. The planting quantity refers to the number of individuals of each required planting type of plants that need to be planted. The transportation starting point is the starting position of the plants used for planting in the scenic spots in the optimized area. The transportation end point refers to the destination where the plants need to be transported. Clarifying the transportation end point helps to accurately plan the transportation route and ensure that the plants can be safely and timely delivered to the scenic spots for planting. The transportation route refers to the route passed from the transportation starting point to the transportation end point. The transportation cost refers to the expenses generated for transporting the required plants from the transportation starting point to the transportation end point (such as fuel costs, tolls, vehicle depreciation costs, driver wages, etc.). The planting days refer to the number of days required to complete all the plant planting work in the scenic spots in the optimized area. The daily per capita wage refers to the average daily wage income of the personnel participating in the planting work. The labor cost refers to the total wage expenses paid to the personnel participating in the planting during the process of plant planting in the scenic spots in the optimized area. The scenic spot impact cost refers to the cost generated due to the impact of the planting activities on the normal operation of the scenic spot and the tourist experience during the green vegetation optimization operation. The leasing cost refers to the expenses generated for leasing the equipment, tools, etc. required for planting during the optimization operation. For example, leasing excavators, loaders, etc. The optimization cost value refers to the cost value obtained by adding up all the costs of the purchase cost, transportation cost, labor cost, scenic spot impact cost and leasing cost.

[0187] S7. Aggregate the optimal value scenic spots and the optimized cost value respectively to obtain the optimal value scenic spot group and the optimized cost value group corresponding to the popular scenic spot area group, and complete the value analysis of ecological products based on deep learning based on the optimized cost value group and the optimal value scenic spot group.

[0188] It should be explained that the optimal value scenic spot refers to a scenic spot whose air purification value is greater than or equal to the pre-set air purification value threshold. The optimal value scenic spot group refers to the set composed of all optimal value scenic spots. The optimized cost value group is the set composed of all optimized cost values.

[0189] To solve the problems described in the background art, the present invention determines a cultural scenic area, wherein the cultural scenic area includes multiple scenic spots areas, and each area scenic spot includes a camera. The present invention divides the cultural scenic area into multiple scenic spots areas, which helps to conduct refined management and analysis of the scenic area. Different scenic spots areas may have different ecological characteristics and functions. By analyzing them separately, the ecological value of each area can be evaluated more accurately. Based on multiple scenic spots areas, a group of popular scenic spots areas is obtained, wherein the group of popular scenic spots areas includes multiple popular scenic spots areas. The present invention screens out the group of popular scenic spots areas from numerous scenic spots areas, which can focus the analysis on those areas that are popular among tourists and have relatively frequent ecological activities. This can improve the efficiency and pertinence of the analysis and avoid waste of resources caused by indiscriminate analysis of all scenic spots areas. One popular scenic spots area is sequentially extracted from the group of popular scenic spots areas, and the following operations are performed on each of the extracted popular scenic spots areas: receiving an ecological value analysis instruction, and obtaining the biodiversity value according to the popular scenic spots area and the ecological value analysis instruction. The present invention receives the ecological value analysis instruction to clarify the goals and requirements of the analysis, and obtains the biodiversity value in combination with the actual situation of the popular scenic spots area. Biodiversity is an important indicator of the health and stability of the ecosystem. Accurately evaluating the biodiversity value can provide a scientific basis for the value analysis of ecological products and help understand the richness of the scenic area ecosystem and the integrity of the ecological functions. Calculate the air purification value of the popular scenic spots area according to the biodiversity value, obtain the air purification value threshold, and compare the air purification value with the air purification value threshold. The present invention converts the biodiversity value into the air purification value, realizing the quantitative evaluation of ecosystem services. Air purification is one of the important functions of the ecosystem. By calculating the air purification value, the contribution of the popular scenic spots area to improving air quality can be intuitively understood, providing specific data support for the economic value evaluation of ecological products. If the air purification value is greater than or equal to the air purification value threshold, then the popular scenic spots area is taken as the scenic spot with the optimal value. The present invention determines the popular scenic spots area with the air purification value greater than or equal to the threshold as the scenic spot with the optimal value, which helps to highlight the areas with good ecological functions and high ecological values in the scenic area. These areas can be used as the highlights of the scenic area for publicity and promotion to attract more tourists. If the air purification value is less than the air purification value threshold, then the green vegetation optimization operation is performed on the popular scenic spots area to obtain the optimized area scenic spot, the optimization cost value of the optimized area scenic spot is obtained, the optimized area scenic spot is taken as the popular scenic spots area, and the step of obtaining the biodiversity value according to the popular scenic spots area and the ecological value analysis instruction is returned. When the air purification value is less than the threshold, the present invention performs the green vegetation optimization operation on the popular scenic spots area, which can improve the ecological environment of the area and enhance its air purification ability.By increasing vegetation cover, optimizing vegetation structure, etc., the stability and service functions of the ecosystem can be enhanced, the value of biodiversity and the overall value of ecological products can be increased. The optimal value scenic spots and the optimized cost value are respectively summarized to obtain the optimal value scenic spot group and the optimized cost value group corresponding to the popular scenic spot area group. Based on the optimized cost value group and the optimal value scenic spot group, the value analysis of ecological products is realized based on deep learning. The present invention completes the value analysis of ecological products based on the optimized cost value and the optimal value scenic spot group, realizes the comprehensive evaluation of ecological products, not only considers the functions and service values of the ecosystem, but also considers the costs paid to enhance these values, making the evaluation results more comprehensive, objective and accurate, and helping scenic spot managers formulate scientific and reasonable development strategies. Therefore, the present invention can improve the accurate evaluation of the value of ecological products and the scientific management of ecological resources.

[0190] As Figure 2 shown, it is a functional module diagram of a system for realizing the value analysis of ecological products based on deep learning provided by an embodiment of the present invention.

[0191] The system 100 for realizing the value analysis of ecological products based on deep learning according to the present invention can be installed in an electronic device. According to the functions to be realized, the system 100 for realizing the value analysis of ecological products based on deep learning can include a scenic spot area determination module 101, an air value analysis module 102, a green vegetation optimization module 103 and a deep learning value analysis module 104. The modules of the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by a processor of an electronic device and can complete fixed functions, and are stored in the memory of the electronic device;

[0192] The scenic spot area determination module 101 is used to determine a cultural scenic spot, wherein the cultural scenic spot includes a plurality of scenic spot areas, and each area scenic spot includes a camera. Based on the plurality of scenic spot areas, a popular scenic spot area group is obtained, wherein the popular scenic spot area group includes a plurality of popular scenic spot areas;

[0193] The air value analysis module 102 is used to sequentially extract a popular scenic spot area from the popular scenic spot area group, and perform the following operations on each of the extracted popular scenic spot areas: receive an ecological value analysis instruction, obtain the biodiversity value according to the popular scenic spot area and the ecological value analysis instruction, calculate the air purification value of the popular scenic spot area according to the biodiversity value, obtain the air purification value threshold, and compare the air purification value with the air purification value threshold;

[0194] The green vegetation optimization module 103 is configured to, if the air purification value is greater than or equal to the air purification value threshold, use the popular scenic area as the scenic area with the optimal value; if the air purification value is less than the air purification value threshold, perform green vegetation optimization operations on the popular scenic area to obtain an optimized area scenic spot, obtain the optimization cost value of the optimized area scenic spot, use the optimized area scenic spot as the popular scenic area, and return to the step of obtaining the biodiversity value according to the popular scenic area and the ecological value analysis instruction;

[0195] The deep learning value analysis module 104 is configured to separately summarize the scenic spots with the optimal value and the optimization cost value to obtain the group of scenic spots with the optimal value and the group of optimization cost values corresponding to the popular scenic area group, and complete the value analysis of ecological products based on deep learning based on the group of optimization cost values and the group of scenic spots with the optimal value.

[0196] Specifically, each module in the value analysis system 100 for realizing the value analysis of ecological products based on deep learning in the embodiment of the present invention adopts the same technical means as those in the Figure 1 value analysis method for realizing the value analysis of ecological products based on deep learning described above, and can produce the same technical effects, which will not be elaborated here.

[0197] As Figure 3 shown, it is a schematic structural diagram of an electronic device for realizing the value analysis method of ecological products based on deep learning provided by an embodiment of the present invention.

[0198] The electronic device 1 may include a processor 10, a memory 11, and a bus 12, and may further include a computer program stored in the memory 11 and executable on the processor 10, such as a value analysis method program for realizing the value analysis of ecological products based on deep learning.

[0199] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disc, etc. The memory 11 can be an internal storage unit of the electronic device 1 in some embodiments, such as the mobile hard disk of the electronic device 1. The memory 11 can also be an external storage device of the electronic device 1 in some other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 1. Further, the memory 11 also includes the internal storage unit of the electronic device 1 and also includes an external storage device. The memory 11 can be used not only to store application software installed in the electronic device 1 and various types of data, such as the code of the method program for realizing the value analysis of ecological products based on deep learning, etc., but also to temporarily store the data that has been output or will be output.

[0200] The processor 10 can be composed of integrated circuits in some embodiments. For example, it can be composed of a single packaged integrated circuit, or can be composed of multiple integrated circuits with the same or different functions packaged, including the combination of one or more Central Processing Units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, connecting all components of the entire electronic device through various interfaces and lines, and by running or executing programs or modules stored in the memory 11 (such as the method program for realizing the value analysis of ecological products based on deep learning, etc.), and calling the data stored in the memory 11, to execute various functions of the electronic device 1 and process data.

[0201] The bus 12 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is set to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0202] Figure 3 Only the electronic device with components is shown. Those skilled in the art can understand that, Figure 3The structure shown does not constitute a limitation on the electronic device 1, and it may include fewer or more components than shown, or combine certain components, or have a different component arrangement.

[0203] For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for powering each component. Preferably, the power source can be logically connected to the at least one processor 10 through a power management device, so as to implement functions such as charging management, discharging management, and power consumption management through the power management device. The power source may also include any components such as one or more DC or AC power sources, a recharge device, a power failure detection circuit, a power converter or inverter, and a power status indicator. The electronic device 1 may also include various sensors, a Bluetooth module, a Wi-Fi module, etc., which will not be elaborated here.

[0204] Furthermore, the electronic device 1 may further include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0205] Optionally, the electronic device 1 may further include a user interface. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)). Optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display the information processed in the electronic device 1 and to display a visual user interface.

[0206] The program for the value analysis method of ecological products implemented based on deep learning stored in the memory 11 in the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can implement:

[0207] Determine a cultural scenic area, where the cultural scenic area includes multiple scenic spots, and each regional scenic spot includes a camera;

[0208] Obtain a group of popular scenic spots based on multiple scenic spots, where the group of popular scenic spots includes multiple popular scenic spots;

[0209] Successively extract a popular scenic spot from the group of popular scenic spots, and perform the following operations on each of the extracted popular scenic spots:

[0210] Receive an ecological value analysis instruction, and obtain the biodiversity value according to the popular scenic area and the ecological value analysis instruction;

[0211] Calculate the air purification value of the popular scenic area according to the biodiversity value, obtain the air purification value threshold, and compare the air purification value with the air purification value threshold;

[0212] If the air purification value is greater than or equal to the air purification value threshold, then regard the said popular scenic area as the scenic area with the optimal value;

[0213] If the air purification value is less than the air purification value threshold, then perform a green vegetation optimization operation on the said popular scenic area to obtain an optimized area scenic spot, obtain the optimization cost value of the optimized area scenic spot, regard the optimized area scenic spot as the popular scenic area, and return to the step of obtaining the biodiversity value according to the popular scenic area and the ecological value analysis instruction;

[0214] Summarize the scenic spots with the optimal value and the optimization cost value respectively to obtain the group of scenic spots with the optimal value and the group of optimization cost values corresponding to the popular scenic area group, and complete the value analysis of ecological products based on deep learning based on the group of optimization cost values and the group of scenic spots with the optimal value.

[0215] Specifically, the specific implementation method of the above instructions by the processor 10 can refer to Figures 1 to 3 the description of the relevant steps in the corresponding embodiment, which will not be elaborated here.

[0216] Further, if the modules / units integrated in the electronic device 1 are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory).

[0217] The present invention also provides a computer-readable storage medium, and the readable storage medium stores a computer program, and when the computer program is executed by the processor of the electronic device, it can implement:

[0218] Determine a cultural scenic area, where the cultural scenic area includes multiple scenic areas, and each area scenic spot includes a camera;

[0219] Obtain a group of popular scenic areas based on multiple scenic areas, where the group of popular scenic areas includes multiple popular scenic areas;

[0220] Extract a popular scenic area from the group of popular scenic areas in sequence, and perform the following operations on each of the extracted popular scenic areas:

[0221] Receive an ecological value analysis instruction, and obtain the biodiversity value according to the popular scenic area and the ecological value analysis instruction;

[0222] Calculate the air purification value of the popular scenic area according to the biodiversity value, obtain the air purification value threshold, and compare the air purification value with the air purification value threshold;

[0223] If the air purification value is greater than or equal to the air purification value threshold, then regard the said popular scenic area as the scenic area with the optimal value;

[0224] If the air purification value is less than the air purification value threshold, then perform a green vegetation optimization operation on the said popular scenic area to obtain an optimized area scenic spot, obtain the optimization cost value of the optimized area scenic spot, regard the optimized area scenic spot as the popular scenic area, and return to the step of obtaining the biodiversity value according to the popular scenic area and the ecological value analysis instruction;

[0225] Summarize the scenic spots with the optimal value and the optimization cost value respectively to obtain the group of scenic spots with the optimal value and the group of optimization cost values corresponding to the group of popular scenic areas, and complete the value analysis of ecological products based on deep learning based on the group of optimization cost values and the group of scenic spots with the optimal value.

[0226] In several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and there can be other division methods in actual implementation.

[0227] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0228] In addition, the functional modules in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware, or in the form of hardware plus software functional modules.

[0229] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-mentioned exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for value analysis of ecological products based on deep learning, characterized in that The method includes: Determine a cultural scenic area, where the cultural scenic area includes multiple scenic spots, and each scenic spot includes a camera; Obtain a group of popular scenic spots based on multiple scenic spots, including: obtaining a group of tourist flows, a group of tourist evaluations, and a group of scenic spot revenues based on multiple scenic spots, including: Sequentially extract one scenic spot from multiple scenic spots, and perform the following operations on each of the extracted scenic spots: Use the camera and a preset shooting frequency to shoot the scenic spot, obtaining a video of the scenic spot for tour, where the video of the scenic spot for tour includes multiple images of the scenic spot for tour; Perform a blurred image screening operation on each image of the scenic spot for tour in the multiple images of the scenic spot for tour, obtaining a set of clear scenic spot images, where the set of clear scenic spot images is a set of images of multiple tourists, and one tourist corresponds to multiple clear scenic spot images in the set of clear scenic spot images; Sequentially extract tourists from multiple tourists, and obtain the first appearance time and the second appearance time of the tourists based on the set of clear scenic spot images; Obtain the residence time based on the first appearance time and the second appearance time, where the residence time is the difference obtained by subtracting the first appearance time from the second appearance time; Judge the residence time and a preset residence time threshold; If it is confirmed that the residence time is greater than or equal to the preset residence time threshold, obtain an initial tourist image based on the first appearance time; Summarize the initial tourist images to obtain an initial tourist image set, and obtain a tourist flow value based on the initial tourist image set; Summarize the tourist flow values to obtain a group of tourist flows corresponding to multiple scenic spots, and obtain a group of tourist evaluations and a group of scenic spot revenues based on multiple scenic spots; The obtaining of the tourist flow value based on the initial tourist image set includes: Sort the initial tourist image set to obtain an arranged tourist image set, sequentially extract one arranged tourist image from the arranged tourist image set, and perform the following operations on each of the extracted arranged tourist images: Take the arranged tourist image as a target tourist image, and remove the target tourist image from the arranged tourist image set to obtain a set of removed tourist images; Sequentially extract removed tourist images from the set of removed tourist images, and perform the following operations on each of the extracted removed tourist images: Perform a similarity detection operation on the target tourist image and the removed tourist image to obtain an image similarity; If the image similarity is greater than or equal to a preset image similarity threshold, take the removed tourist image as a candidate tourist image, summarize the candidate tourist images to obtain a set of candidate tourist images, identify an identified tourist image from the set of candidate tourist images, and combine the identified tourist image and the target tourist image to obtain a target tourist image group; Remove the set of candidate tourist images from the set of removed tourist images to obtain an updated tourist image set, take the updated tourist image set as the arranged tourist image set, and return to the step of sequentially extracting one arranged tourist image from the arranged tourist image set until the updated tourist image set is an empty set; Summarize the target tourist image groups to obtain a set of target tourist image groups, obtain the number of target tourist image groups in the set of target tourist image groups, and take the number of target tourist image groups as the tourist flow value; Among them, the popular scenic spot area group includes multiple popular scenic spot areas; Successively extract a popular scenic spot area from the popular scenic spot area group, and perform the following operations on each of the extracted popular scenic spot areas: Receive an ecological value analysis instruction, and obtain the biodiversity value according to the popular scenic spot area and the ecological value analysis instruction; Calculate the air purification value of the popular scenic spot area according to the biodiversity value, obtain the air purification value threshold, and compare the air purification value with the air purification value threshold; If the air purification value is greater than or equal to the air purification value threshold, then regard the popular scenic spot area as the scenic spot with the optimal value; If the air purification value is less than the air purification value threshold, then perform a green vegetation optimization operation on the popular scenic spot area to obtain an optimized area scenic spot, obtain the optimization cost value of the optimized area scenic spot, regard the optimized area scenic spot as the popular scenic spot area, and return to the step of obtaining the biodiversity value according to the popular scenic spot area and the ecological value analysis instruction; Summarize the scenic spots with the optimal value and the optimization cost value respectively to obtain the optimal value scenic spot group and the optimization cost value group corresponding to the popular scenic spot area group, and complete the value analysis of ecological products based on deep learning based on the optimization cost value group and the optimal value scenic spot group.

2. The method for value analysis of ecological products based on deep learning according to claim 1, wherein, The obtaining of the popular scenic spot area group based on multiple scenic spot areas includes: Obtain a tourist flow group, a tourist evaluation group, and a scenic spot income group based on multiple scenic spot areas. Among them, the tourist flow group includes multiple tourist flow values, the tourist evaluation group includes multiple tourist evaluation values, the scenic spot income group includes multiple scenic spot income values, and the tourist flow values, tourist evaluation values, and scenic spot income values correspond one by one to the scenic spot areas; Obtain a comprehensive evaluation index group based on multiple scenic spot areas, the tourist flow group, the tourist evaluation group, and the scenic spot income group. Among them, the comprehensive evaluation index group includes multiple comprehensive evaluation index values; After performing a descending order sorting operation on each comprehensive evaluation index value in the comprehensive evaluation index group, obtain a sequence comprehensive index group; Extract a high-order evaluation index group from the sequence comprehensive index group, and regard all the scenic spot areas corresponding to the high-order evaluation index group as the popular scenic spot area group.

3. The value analysis method for ecological products implemented based on deep learning according to claim 2, wherein The obtaining of the comprehensive evaluation index group based on multiple scenic spot areas, the tourist flow group, the tourist evaluation group, and the scenic spot income group includes: Successively extract a scenic spot area from multiple scenic spot areas, and perform the following operations on each of the extracted scenic spot areas: Successively extract tourist flow values from the tourist flow group, and perform the following operations on each of the extracted tourist flow values: Perform a standardization operation on the tourist flow value to obtain an initial tourist flow value, and determine whether the initial tourist flow value is a preset extreme value; If the initial tourist flow value is a preset extreme value, then perform a translation process on the initial tourist flow value to obtain a standard tourist flow value; If the initial tourist flow value is not a preset extreme value, then regard the initial tourist flow value as the standard tourist flow value; Calculate the tourist flow proportion of the standard tourist flow value, calculate the tourist flow entropy value according to the tourist flow proportion, and calculate the tourist flow weight according to the tourist flow entropy value; According to the tourist flow value, respectively determine the corresponding tourist evaluation value and scenic spot income value from the tourist evaluation group and the scenic spot income group, and obtain the tourist evaluation weight and the scenic spot income weight based on the tourist evaluation value and the scenic spot income value; Calculate the comprehensive evaluation index value according to the tourist flow weight, the tourist evaluation weight and the scenic spot income weight; Summarize the comprehensive evaluation index values to obtain a comprehensive evaluation index group corresponding to multiple scenic spot areas.

4. The method for value analysis of ecological products implemented based on deep learning according to claim 3, wherein The fuzzy image screening operation is performed on each of the multiple scenic spot area images to obtain a set of clear scenic spot images, including: Successively extract the scenic spot area images from the multiple scenic spot area images, perform a grayscale operation on the scenic spot image area images to obtain grayscale scenic spot area images, and perform an image segmentation operation on the grayscale scenic spot area images to obtain a set of segmented images; Successively extract the segmented images from the set of segmented images, perform a denoising operation on the segmented images using a pre-constructed filtering algorithm to obtain filtered segmented images, and calculate the variance of the filtered segmented images; Accumulate the variances to obtain a comprehensive variance, and determine whether the comprehensive variance is within a preset comprehensive variance interval; If the comprehensive variance is within the preset comprehensive variance interval, then use the scenic spot image of the corresponding scenic area of the comprehensive variance as the clear scenic spot image; If the comprehensive variance is not within the preset comprehensive variance interval, then eliminate the scenic spot area image corresponding to the comprehensive variance, summarize the remaining scenic spot area images to obtain multiple updated scenic spot area images, use the multiple updated scenic spot area images as the multiple scenic spot area images, and return to the step of successively extracting the scenic spot area images from the multiple scenic spot area images; Summarize the clear scenic spot images to obtain a set of clear scenic spot images corresponding to the multiple scenic spot area images.

5. The method for value analysis of ecological products based on deep learning according to claim 4, characterized in that The obtaining of the biodiversity value according to the popular scenic spot area and the ecological value analysis instruction includes: Obtain a set of scenic spot area images according to the popular scenic spot area and a pre-constructed drone, and obtain the scenic spot area and the set of species images according to the set of scenic spot area images; Perform the following operations on each species image in the set of species images: Match the species image with a pre-constructed species database to obtain the species type, and summarize the species types to obtain a set of species types; Perform a species type classification operation on the set of species types to obtain a set of rare and endangered species, a set of endemic species, and a set of ancient tree species, and obtain the species resource conservation value of the scenic spot area according to the ecological value analysis instruction; Calculate the biodiversity value of the popular scenic spot area according to the scenic spot area, the species resource conservation value, the set of rare and endangered species, the set of endemic species, and the set of ancient tree species. The calculation formula of the biodiversity value is as follows: Among them, represents the biodiversity value, represents the rarity and endangerment index corresponding to each rare and endangered species, represents the variable of the preset rare and endangered species, represents the endemic species index of each endemic species, represents the variable of the preset endemic species, represents the ancient tree age index of each ancient tree species, represents the variable of the preset ancient tree species, represents the scenic area area, represents the number of rare and endangered species concentrated in the rare and endangered species, represents the number of endemic species concentrated in the endemic species, represents the number of ancient tree species concentrated in the ancient tree species, represents the species resource conservation value within the scenic area area.

6. The value analysis method for ecological products implemented based on deep learning according to claim 5, wherein The performing of the green vegetation optimization operation on the popular scenic spot area to obtain an optimized regional scenic spot includes: Obtain the previous ecosystem state of the popular scenic spot area, where the previous ecosystem state includes: biodiversity value, air purification value, and tourist flow; After performing the initial green vegetation optimization operation on the popular scenic area according to the previous ecosystem state, using the preset vegetation increase area ratio and the preset introduced species type ratio, an initial optimized area is obtained; Detect the initial optimized area using the preset detection time to obtain detection data, where the detection data includes: detected biodiversity value, detected air purification value, and detected tourist flow; Calculate the initial optimization reward of the initial optimized area based on the detection data, and compare the initial optimization reward with the preset optimization reward threshold; If the initial optimization reward is less than the preset optimization reward threshold, then use the initial optimized area corresponding to the initial optimization reward less than the preset optimization reward threshold as the popular scenic area, and return to the step of performing the initial green vegetation optimization operation on the popular scenic area according to the previous ecosystem state, using the preset vegetation increase area ratio and the preset introduced species type ratio; If the initial optimization reward is greater than or equal to the preset optimization reward threshold, then use the initial optimized area as the optimized scenic area.

7. The method for value analysis of ecological products based on deep learning as described in claim 6, wherein The obtaining of the optimization cost value of the optimized scenic area includes: Obtain the required planting types and planting quantities of the optimized scenic area, and obtain the purchase cost and planting days according to the required planting types and planting quantities; Obtain the transportation starting point and the transportation ending point, obtain the transportation route according to the transportation starting point and the transportation ending point, and calculate the transportation cost according to the transportation route; Obtain the labor cost, scenic area impact cost, and rental cost according to the planting days and the preset daily per capita wage; Obtain the optimization cost value based on the purchase cost, transportation cost, labor cost, scenic area impact cost, and rental cost.

8. A system using the method for value analysis of ecological products based on deep learning as described in claim 1, characterized in that, The system includes: A scenic area determination module for determining a cultural scenic area, where the cultural scenic area includes multiple scenic areas, and each area scenic area includes a camera, and obtaining a group of popular scenic areas based on the multiple scenic areas, where the group of popular scenic areas includes multiple popular scenic areas; An air value analysis module for sequentially extracting a popular scenic area from the group of popular scenic areas and performing the following operations on each of the extracted popular scenic areas: receiving an ecological value analysis instruction, obtaining the biodiversity value according to the popular scenic area and the ecological value analysis instruction, calculating the air purification value of the popular scenic area according to the biodiversity value, obtaining the air purification value threshold, and comparing the air purification value with the air purification value threshold; A green vegetation optimization module for, if the air purification value is greater than or equal to the air purification value threshold, using the popular scenic area as the scenic area with the optimal value, and if the air purification value is less than the air purification value threshold, performing a green vegetation optimization operation on the popular scenic area to obtain an optimized scenic area, obtaining the optimization cost value of the optimized scenic area, using the optimized scenic area as the popular scenic area, and returning to the step of obtaining the biodiversity value according to the popular scenic area and the ecological value analysis instruction; The deep learning value analysis module is used to separately summarize the optimal value scenic spots and the optimized cost value, obtain the optimal value scenic spot group and the optimized cost value group corresponding to the popular scenic spot area group, and complete the value analysis of ecological products based on the deep learning implementation, based on the optimized cost value group and the optimal value scenic spot group.

Images