A method and system for identifying tea tree quality

Abstract

The application discloses a tea tree quality identification method and system, wherein the method comprises the following steps: obtaining a tea tree data set in a preset first time period; sending the tea tree data set in the preset first time period to a preset quality identification module to obtain a quality identification total score; determining an interval division level of the quality identification total score according to a preset score interval in which the quality identification total score falls; and determining a quality level of the corresponding tea tree according to the interval division level of the quality identification total score. The application comprehensively evaluates the tea tree, tea leaves, the smell of the tea leaves and the components contained in the tea leaves, and thus improves the accuracy of the quality identification of the tea tree.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of food quality identification, and more particularly to a tea tree quality identification method and system. BACKGROUND

[0002] With the increasing demand of consumers for tea quality, accurate identification of tea tree quality has become the key to meeting market demand and improving tea competitiveness; consumers pay more and more attention to the taste, aroma, nutritional ingredients and other quality characteristics of tea, which prompts the tea industry to need more scientific and accurate identification methods to protect and improve product quality; at present, the quality identification of tea trees is mainly carried out by technical personnel, which is limited by the technical level of the technical personnel and is disturbed by human factors.

[0003] Therefore, the prior art has defects and needs to be improved. SUMMARY

[0004] In view of the above problems, the purpose of the present application is to provide a tea tree quality identification method and system which can improve the accuracy of tea tree quality identification.

[0005] The first aspect of the present application provides a tea tree quality identification method, comprising:

[0006] obtaining a tea tree data set in a preset first time period;

[0007] sending the tea tree data set in the preset first time period to a preset quality identification module to obtain a quality identification total score;

[0008] determining the interval division level of the quality identification total score according to the preset score interval in which the quality identification total score falls;

[0009] determining the quality grade of the corresponding tea tree according to the interval division level of the quality identification total score.

[0010] In the present application, it also includes:

[0011] obtaining soil data information of tea tree planting;

[0012] obtaining elements in the soil and corresponding element content values according to the soil data information of tea tree planting;

[0013] obtaining current time information and corresponding tea tree information;

[0014] determining the standard element content value range of the corresponding tea tree at the current time according to the current time information and the corresponding tea tree information;

[0015] If all element content values in the soil are within the standard element content value range corresponding to the current time, the tea tree data obtained at the current time is qualified.

[0016] In the scheme, the step of sending the tea tree data set in the preset first time period to the preset quality identification module to obtain a quality identification total score specifically includes:

[0017] The tea tree data set in the preset first time period is divided into a tea tree image data subset, a tea leaf smell data subset and a tea leaf component data subset;

[0018] The tea tree image data subset is sent to an image quality identification submodule in the preset quality identification module to obtain a tea tree image quality score;

[0019] The tea leaf smell data subset is sent to a smell quality identification submodule in the preset quality identification module to obtain a tea leaf smell quality score;

[0020] The tea leaf component data subset is sent to a component quality identification submodule in the preset quality identification module to obtain a tea leaf component quality score;

[0021] The tea tree image quality score is multiplied by a preset image weight coefficient, the tea leaf smell quality score is multiplied by a preset smell weight coefficient, and the tea leaf component quality score is multiplied by a preset component weight coefficient to obtain a quality identification total score corresponding to the tea tree.

[0022] In the scheme, the step of sending the tea tree image data subset to the image quality identification submodule in the preset quality identification module to obtain the tea tree image quality score specifically includes:

[0023] Extracting a tea leaf image in the tea tree image data subset;

[0024] Extracting a feature in the tea leaf image and a corresponding feature value;

[0025] Normalizing the feature value in the tea leaf image to obtain a tea leaf feature normalized value;

[0026] Multiplying the tea leaf feature normalized value by a weight coefficient of the corresponding feature and then accumulating to obtain a feature quality score corresponding to the tea leaf image;

[0027] Traversing the tea leaf images in the tea tree image data subset to obtain a feature quality score set of the tea leaf images;

[0028] Calculating an average value of the feature quality scores in the feature quality score set of the tea leaf images to obtain a tea leaf quality score;

[0029] Extracting a crown image in the tea tree image data subset;

[0030] Labeling the crown image to obtain a crown labeled image;

[0031] The crown annotation graph is divided according to regions to obtain a plurality of crown annotation subgraphs;

[0032] The crown annotation subgraph and the preset crown annotation subgraph of the corresponding region are compared and analyzed to obtain a crown annotation subgraph similarity value;

[0033] The crown annotation subgraph similarity value set is obtained by traversing the crown image in the tea tree image data subset;

[0034] The crown annotation subgraph similarity value in the crown annotation subgraph similarity value set is averaged to obtain a crown similarity value, and the corresponding crown similarity value is set as a corresponding crown quality score weight coefficient;

[0035] The crown quality score weight coefficient is multiplied by the corresponding preset value of the crown to obtain a crown quality score;

[0036] The tea leaf quality score is multiplied by the tea leaf weight coefficient, and the crown quality score is multiplied by the corresponding crown weight coefficient to obtain a corresponding tea tree image quality score.

[0037] In the scheme, the step of labeling the crown image in the tea tree image to obtain a crown annotation graph specifically includes:

[0038] The tea leaf region, tea tree branch region and non-tea leaf tea tree branch region in the crown image are extracted;

[0039] The tea leaf image in the tea leaf region in the crown image is compared and analyzed with the preset tea leaf image to obtain a tea leaf similarity value;

[0040] If the tea leaf similarity value is greater than or equal to a preset first similarity threshold value, the corresponding tea leaf region is labeled according to a preset first numerical value; if the tea leaf similarity value is less than the preset first similarity threshold value, the corresponding tea leaf region is labeled according to a preset third numerical value;

[0041] The tea tree branch image in the tea tree branch region in the crown image is compared and analyzed with the preset tea tree branch image to obtain a tea tree branch similarity value;

[0042] If the tea tree branch similarity value is greater than or equal to a preset second similarity threshold value, the corresponding tea tree branch region is labeled according to a preset second numerical value; if the tea tree branch similarity value is less than the preset second similarity threshold value, the corresponding tea tree branch region is labeled according to a preset third numerical value;

[0043] The non-tea leaf tea tree branch region is labeled according to a preset third numerical value.

[0044] In the scheme, the step of comparing and analyzing the crown annotation subgraph and the preset crown annotation subgraph of the corresponding region to obtain a crown annotation subgraph similarity value specifically includes:

[0045] Extract the area values marked by the preset first value, the preset second value and the preset third value in the tree crown annotation subgraph, and set them as a first area, a second area and a third area respectively;

[0046] Extract the area values marked by the preset first value, the preset second value and the preset third value in the preset tree crown annotation subgraph of the corresponding area, and set them as a preset first area, a preset second area and a preset third area respectively;

[0047] Obtain a first ratio value by comparing the first area with the preset first area, a second ratio value by comparing the second area with the preset second area, and a third ratio value by comparing the third area with the preset third area;

[0048] Extract the minimum value among the first ratio value, the second ratio value and the third ratio value, and set it as a tree crown annotation subgraph similarity value of the tree crown annotation subgraph and the preset tree crown annotation subgraph of the corresponding area.

[0049] In the scheme, the step of sending the tea leaf smell data subset to the smell quality identification submodule in the preset quality identification module to obtain a tea leaf smell quality score specifically includes:

[0050] Extract the smell data in the tea leaf smell data subset;

[0051] Extract the smell components and corresponding smell component content values in the smell data;

[0052] Compare the smell components in the smell data with preset smell components, if consistent, save the corresponding smell components, and if inconsistent, delete the corresponding smell components;

[0053] Determine the corresponding smell score according to the preset smell content range in which the corresponding smell component content value falls;

[0054] Multiply different smell scores by the weight proportion coefficient of the corresponding smell, and then accumulate to obtain the score of the corresponding smell data;

[0055] Iterate through the entire tea leaf smell data subset to obtain a score set of smell data;

[0056] Average the scores of the smell data in the score set of the smell data to obtain a corresponding tea leaf smell quality score.

[0057] In the scheme, the step of sending the tea leaf component data subset to the component quality identification submodule in the preset quality identification module to obtain a tea leaf component quality score specifically includes:

[0058] Extract the tea leaf component data in the tea leaf component data subset;

[0059] Extract tea ingredients in tea ingredient data and content values corresponding to the tea ingredients;

[0060] Comparing the tea ingredients with the preset tea ingredients, if consistent, the corresponding tea ingredients are saved, and if inconsistent, the tea ingredients are deleted;

[0061] According to the content value of the corresponding tea ingredient falling into the preset tea ingredient content range, the score of the corresponding tea ingredient is determined;

[0062] The score of the tea ingredient is multiplied by the weight proportion coefficient of the corresponding element, and then accumulated to obtain the score of the corresponding tea ingredient;

[0063] The score set of the tea ingredient is obtained by traversing the entire tea ingredient data subset;

[0064] The score of the tea ingredient in the score set of the tea ingredient is averaged to obtain the quality score of the corresponding tea ingredient.

[0065] The second aspect of the present application provides a tea tree quality identification system comprising a memory and a processor, wherein the memory stores a tea tree quality identification method program.

[0066] The present application discloses a tea tree quality identification method and system, which comprehensively evaluates tea trees, tea leaves, the smell of tea leaves and the ingredients contained therein, thereby improving the accuracy of tea tree quality identification. BRIEF DESCRIPTION OF DRAWINGS

[0067] Figure 1 A flowchart of a tea tree quality identification method of the present application is shown;

[0068] Figure 2 A step flowchart of the present application is shown.

[0069] Figure 3 A block diagram of a tea tree quality identification system of the present application is shown. DETAILED DESCRIPTION

[0070] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the present application will be further described in detail below in combination with the drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0071] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, however, the present application can also be implemented in other ways different from those described herein, therefore, the scope of protection of the present application is not limited by the specific embodiments disclosed below.

[0072] Figure 1 A flow chart of a tea tree quality identification method is shown.

[0073] As shown in Figure 1 The present application discloses a tea tree quality identification method, comprising:

[0074] S101, obtaining a tea tree data set in a preset first time period;

[0075] S102, sending the tea tree data set in the preset first time period to a preset quality identification module to obtain a quality identification total score;

[0076] S103, determining an interval division level of the quality identification total score according to the preset score interval in which the quality identification total score falls;

[0077] S104, determining the quality grade of the corresponding tea tree according to the interval division level of the quality identification total score.

[0078] According to the embodiment of the present application, the preset first time period is a continuous time period, for example, the preset first time period is 30 days, so the corresponding tea tree data set is the tea tree data set in a continuous 30-day time period. The preset quality identification module stores a method and system for processing tea tree data in the tea tree data set to obtain a quality identification total score. Then, the quality identification total score is divided into multiple preset score intervals by a preset score base, for example, the preset score base is 2, so the preset score intervals can be divided into (0, 2], (2, 4], (4, 6]…(n-2, n], where n is an even number. Then, each preset score interval is set to a division level, where the larger the score in the preset score interval, the higher the division level of the corresponding preset score interval, for example, the preset score interval (0, 2] is set to a first level, the preset score interval (2, 4] is set to a second level, and so on. Then, the interval division level and the quality grade of the tea tree are associated, where the higher the interval division level, the higher the quality grade of the tea tree, and each interval division level corresponds to a quality grade of the tea tree.

[0079] According to the embodiment of the present application, it further comprises:

[0080] Obtaining soil data information of tea tree planting;

[0081] Obtaining elements in the soil and corresponding element content values according to the soil data information of tea tree planting;

[0082] Obtaining current time information and corresponding tea tree information;

[0083] Determining the standard element content value range of the corresponding tea tree at the current time according to the current time information and the corresponding tea tree information;

[0084] If the content of all elements in the soil quality is within the standard element content value range corresponding to the current time, the tea tree data obtained at the current time is qualified.

[0085] It should be noted that when obtaining the tea tree data, the soil quality data of the tea tree planting is obtained in advance, and the elements in the soil quality include water, nitrogen, phosphorus and the like. For example, the nitrogen element can promote plant growth, and the phosphorus element is helpful for root development. Different plants or the same plant have different needs for nutrients at different time periods. Therefore, the corresponding standard element content value range is matched according to the time and the tea tree information, the standard element content value range is used to ensure that the current tea tree is in a normal living environment, thereby improving the accuracy of the current obtained tea tree data.

[0086] According to the embodiment of the present application, the step of sending the tea tree data set in the preset first time period to the preset quality identification module to obtain a total quality identification score specifically includes:

[0087] The tea tree data set in the preset first time period is divided into a tea tree image data subset, a tea leaf smell data subset and a tea leaf component data subset;

[0088] The tea tree image data subset is sent to an image quality identification submodule in the preset quality identification module to obtain a tea tree image quality score;

[0089] The tea leaf smell data subset is sent to a smell quality identification submodule in the preset quality identification module to obtain a tea leaf smell quality score;

[0090] The tea leaf component data subset is sent to a component quality identification submodule in the preset quality identification module to obtain a tea leaf component quality score;

[0091] The tea tree image quality score is multiplied by a preset image weight coefficient, the tea leaf smell quality score is multiplied by a preset smell weight coefficient, and the tea leaf component quality score is multiplied by a preset component weight coefficient, and the total quality identification score corresponding to the tea tree is obtained.

[0092] According to the embodiment of the present application, the preset quality identification module is divided into an image quality identification submodule, a smell quality identification submodule and a component quality identification submodule. The image quality identification submodule analyzes the tea tree image, the smell quality identification submodule analyzes the smell of the tea leaf, and the component quality identification submodule analyzes the components in the tea leaf. Through comprehensive analysis from the aspects of color, smell and taste, the accuracy of the tea tree quality identification is improved.

[0093] According to the embodiment of the present application, the step of sending the tea tree image data subset to the image quality identification submodule in the preset quality identification module to obtain a tea tree image quality score specifically includes:

[0094] extracting the tea leaf images in the tea tree image data subset;

[0095] extracting the features in the tea leaf images and corresponding feature values;

[0096] normalizing the feature values in the tea leaf images to obtain tea leaf feature normalized values;

[0097] multiplying the tea leaf feature normalized values by the weight coefficients of the corresponding features and then accumulating to obtain feature quality scores of the corresponding tea leaf images;

[0098] traversing the tea leaf images in the entire tea tree image data subset to obtain a feature quality score set of the tea leaf images;

[0099] calculating the average value of the feature quality scores in the feature quality score set of the tea leaf images to obtain a tea leaf quality score;

[0100] extracting the crown images in the tea tree image data subset;

[0101] annotating the crown images to obtain crown annotation maps;

[0102] dividing the crown annotation maps according to regions to obtain a plurality of crown annotation sub-maps;

[0103] comparing and analyzing the crown annotation sub-maps and preset crown annotation sub-maps of the corresponding regions to obtain crown annotation sub-map similarity values;

[0104] traversing the crown images in the entire tea tree image data subset to obtain a crown annotation sub-map similarity value set;

[0105] calculating the average value of the crown annotation sub-map similarity values in the crown annotation sub-map similarity value set to obtain a crown similarity value, and setting the corresponding crown similarity value as a crown quality score weight coefficient;

[0106] multiplying the crown quality score weight coefficient by a preset score base of the corresponding crown to obtain a crown quality score;

[0107] multiplying the tea leaf quality score by a tea leaf weight coefficient and adding the crown quality score multiplied by a corresponding crown weight coefficient to obtain a tea tree image quality score.

[0108] It should be noted that the tea tree image quality score is mainly evaluated in terms of the visual effect of the tea tree, and the features in the tea leaf images include the size, shape and color of the corresponding tea leaves, for example, the shape of the tea leaves is complete and uniform, and the color is bright green, so the tea leaf image quality score is higher.

[0109] Figure 2 A step flowchart of annotating the crown image is shown.

[0110] As shown in the embodiment of the present application, the step of marking the tree crown image in the tea tree image to obtain the tree crown marked image specifically includes: Figure 2

[0111] S201, extracting the tea leaf region, tea tree branch region and non-tea leaf tea tree branch region in the tree crown image;

[0112] S202, comparing and analyzing the tea leaf image in the tea leaf region in the tree crown image with the preset tea leaf image to obtain a tea leaf similarity value;

[0113] S203, if the tea leaf similarity value is greater than or equal to a preset first similarity threshold value, marking the corresponding tea leaf region according to a preset first numerical value; if the tea leaf similarity value is less than the preset first similarity threshold value, marking the corresponding tea leaf region according to a preset third numerical value;

[0114] S204, comparing and analyzing the tea tree branch image in the tea tree branch region in the tree crown image with the preset tea tree branch image to obtain a tea tree branch similarity value;

[0115] S205, if the tea tree branch similarity value is greater than or equal to a preset second similarity threshold value, marking the corresponding tea tree branch region according to a preset second numerical value; if the tea tree branch similarity value is less than the preset second similarity threshold value, marking the corresponding tea tree branch region according to a preset third numerical value;

[0116] S206, marking the non-tea leaf tea tree branch region according to a preset third numerical value.

[0117] According to the embodiment of the present application, by analyzing the tree crown image, it is evaluated whether the overall shape of the corresponding tea tree is symmetrical and the branches are reasonable, so as to evaluate the tree crown quality score. The non-tea leaf tea tree branch region is the gap region of the tree crown. For example, if there is a defect in the tea leaf, the corresponding tea leaf similarity value will be less than the preset first similarity threshold value, and the corresponding defective tea leaf region is marked according to the third numerical value. For example, if there is no tea leaf on the tea tree branch, the corresponding tea tree branch similarity value is less than the preset second similarity threshold value, the corresponding dead tea tree branch is set, and the corresponding dead tea tree branch region is marked according to the third numerical value.

[0118] According to the embodiment of the present application, the step of comparing and analyzing the tree crown marked sub-image and the preset tree crown marked sub-image of the corresponding region to obtain a tree crown marked sub-image similarity value specifically includes:

[0119] extracting the area value of the area marked by the preset first numerical value, the preset second numerical value and the preset third numerical value in the tree crown marked sub-image, and setting the first area, the second area and the third area respectively;

[0120] ​Extract the area values marked by the preset first value, the preset second value and the preset third value in the preset tree crown annotation subgraph of the corresponding region, and set them as a preset first area, a preset second area and a preset third area respectively;

[0121] The first area and the preset first area are compared to obtain a first ratio value, the second area and the preset second area are compared to obtain a second ratio value, and the third area and the preset third area are compared to obtain a third ratio value;

[0122] The minimum value of the first ratio value, the second ratio value and the third ratio value is extracted, and is set as a tree crown annotation subgraph similarity value of the tree crown annotation subgraph of the corresponding region and the preset tree crown annotation subgraph.

[0123] It should be noted that the tea tree is photographed from the side by the preset camera device to ensure that the tea tree image contains the entire tree crown image of the corresponding tea tree, and the area values marked by the preset first value, the preset second value and the preset third value in the preset tree crown annotation subgraphs of different regions are all inconsistent, for example, the preset first value in the preset tree crown annotation subgraph corresponding to the tree crown top region accounts for a large proportion, and the preset first value in the preset tree crown annotation subgraph of the region closer to the ground accounts for a smaller proportion.

[0124] According to the embodiment of the present application, the step of sending the tea leaf smell data subset to the smell quality identification submodule in the preset quality identification module to obtain a tea leaf smell quality score specifically includes:

[0125] Extracting smell data in the tea leaf smell data subset;

[0126] Extracting the smell components and the corresponding smell component content values in the smell data;

[0127] Comparing and analyzing the smell components in the smell data with preset smell components, if they are consistent, the corresponding smell components are saved, and if they are inconsistent, the corresponding smell components are deleted;

[0128] Determining the corresponding smell score according to the preset smell content range in which the corresponding smell component content value falls;

[0129] Multiplying different smell scores by the weight proportion coefficient of the corresponding smell, and then accumulating to obtain the score of the corresponding smell data;

[0130] Traversing the entire tea leaf smell data subset to obtain a smell data score set;

[0131] Calculating the average value of the smell data scores in the smell data score set to obtain the corresponding tea leaf smell quality score.

[0132] It should be noted that the smell emitted by the tea tree is obtained by a preset electronic nose or aroma analyzer, and the smell is detected and identified to obtain the smell component and the corresponding smell component content value; the unique smell is saved, and then the smell content value is divided into ranges, each smell content range corresponds to a smell score, and the smell content value ranges corresponding to different smells are different, and the corresponding smell scores are also different; the tea leaf smell data subset includes tea leaf smell data at different time points, and the average value of the smell data in the tea leaf smell data subset is calculated to obtain the tea leaf smell quality score, thereby improving the accuracy of the tea leaf smell quality score and reducing the detection error and contingency.

[0133] According to the embodiment of the present application, the step of sending the tea leaf component data subset to a component quality identification submodule in a preset quality identification module to obtain a tea leaf component quality score specifically includes:

[0134] Extracting tea leaf component data in the tea leaf component data subset;

[0135] Extracting tea leaf components and the content values of the corresponding tea leaf components in the tea leaf component data;

[0136] Comparing and analyzing the tea leaf components with the preset tea leaf components, if they are consistent, the corresponding tea leaf components are saved, and if they are inconsistent, the tea leaf components are deleted;

[0137] Determining the score of the corresponding tea leaf component according to the preset tea leaf component content range in which the content value of the corresponding tea leaf component falls;

[0138] Multiplying the score of the tea leaf component by the weight proportion coefficient of the corresponding element, and then accumulating to obtain the score of the corresponding tea leaf component;

[0139] Traversing the entire tea leaf component data subset to obtain a score set of tea leaf components;

[0140] Calculating the average value of the scores of the tea leaf components in the score set of the tea leaf components to obtain a corresponding tea leaf component quality score.

[0141] It should be noted that the tea leaf components include tea polyphenols, amino acids, caffeine and other components, and multiple tea leaf component content ranges are set for each tea leaf component, and each tea leaf component content range corresponds to a score, so that the score of the corresponding tea leaf component can be determined according to the preset tea leaf component content range in which the content value of the tea leaf component falls; the tea leaf component data subset includes tea leaf component data collected at different times.

[0142] Figure 3 A block diagram of a tea tree quality identification system of the present application is shown.

[0143] AsFigure 3 As shown, the second aspect of the present application provides a tea tree quality identification system 3 comprising a memory 31 and a processor 32, wherein the memory stores a program of a tea tree quality identification method.

[0144] The present application discloses a tea tree quality identification method and system, which comprehensively evaluates the tea tree, the tea leaf, the smell of the tea leaf and the components contained therein, thereby improving the accuracy of the quality identification of the tea tree.

[0145] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other manners. The above described device embodiments are merely schematic, for example, the division of the units is merely a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the various components shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0146] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units; they can be located in one place, or distributed on a plurality of network units; and some or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0147] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be realized in the form of hardware, or in the form of hardware plus software functional unit.

[0148] Those skilled in the art can understand that all or part of the steps of the above method embodiments can be completed by program instruction related hardware, and the foregoing program can be stored in a computer readable storage medium, and the program executes the steps of the above method embodiments when executed; and the foregoing storage medium includes mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic discs or optical discs and various storage media that can store program codes.

[0149] Alternatively, the above-mentioned integrated unit of the present application, if realized in the form of a software function module and sold or used as an independent product, can also be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: mobile storage devices, ROM, RAM, magnetic disks or optical disks, and various media that can store program codes.

Claims

1. A method of identifying the quality of tea tree, characterized by, The application relates to a tea tree quality identification method and device. The method comprises the following steps: acquiring a tea tree data set within a preset first time period; sending the tea tree data set within the preset first time period to a preset quality identification module to obtain a quality identification total score; determining an interval division level of the quality identification total score according to a preset score interval into which the quality identification total score falls; determining a quality level of the corresponding tea tree according to the interval division level of the quality identification total score; the step of sending the tea tree data set within the preset first time period to the preset quality identification module to obtain the quality identification total score specifically comprises the following steps: dividing the tea tree data set within the preset first time period into a tea tree image data subset, a tea leaf smell data subset and a tea leaf component data subset; sending the tea tree image data subset to an image quality identification submodule in the preset quality identification module to obtain a tea tree image quality score; sending the tea leaf smell data subset to a smell quality identification submodule in the preset quality identification module to obtain a tea leaf smell quality score; sending the tea leaf component data subset to a component quality identification submodule in the preset quality identification module to obtain a tea leaf component quality score; multiplying the tea tree image quality score by a preset image weight coefficient, adding the tea leaf smell quality score multiplied by a preset smell weight coefficient, and adding the tea leaf component quality score multiplied by a preset component weight coefficient to obtain the quality identification total score of the corresponding tea tree; the step of sending the tea tree image data subset to the image quality identification submodule in the preset quality identification module to obtain the tea tree image quality score specifically comprises the following steps: extracting a tea leaf image in the tea tree image data subset; extracting features and corresponding feature values in the tea leaf image; normalizing the feature values in the tea leaf image to obtain tea leaf feature normalized values; multiplying the tea leaf feature normalized values by weight coefficients of the corresponding features, and then accumulating to obtain a feature quality score of the corresponding tea leaf image; traversing the tea leaf images in the tea tree image data subset to obtain a feature quality score set of the tea leaf image; performing average value calculation on the feature quality scores in the feature quality score set of the tea leaf image to obtain a tea leaf quality score; extracting a crown image in the tea tree image data subset; labeling the crown image to obtain a crown label map; dividing the crown label map according to regions to obtain a plurality of crown label submaps; comparing and analyzing the crown label submap and a preset crown label submap of the corresponding region to obtain a crown label submap similarity value; traversing the crown images in the tea tree image data subset to obtain a crown label submap similarity value set; performing average value calculation on the crown label submap similarity values in the crown label submap similarity value set to obtain a crown similarity value, and setting the corresponding crown similarity value as a corresponding crown quality score weight coefficient; multiplying the crown quality score weight coefficient by a preset score base of the corresponding crown to obtain a crown quality score; multiplying the tea leaf quality score by a tea leaf weight coefficient, adding the crown quality score multiplied by a corresponding crown weight coefficient to obtain the corresponding tea tree image quality score; the step of sending the tea leaf smell data subset to the smell quality identification submodule in the preset quality identification module to obtain the tea leaf smell quality score specifically comprises the following steps: Extracting the odor data in the odor data subset of the tea leaves; Extracting the odor components in the odor data and the corresponding odor component content values; Comparatively analyzing the odor components in the odor data and the preset odor components, if consistent, saving the corresponding odor components, if inconsistent, deleting the corresponding odor components; Determining the corresponding odor component score according to the preset odor content range in which the corresponding odor component content value falls; Multiplying the different odor component scores by the weight proportion coefficient of the corresponding odor, and then accumulating to obtain the score of the corresponding odor data; Traversing the entire tea odor data subset to obtain a score set of the odor data; Calculating the average value of the scores of the odor data in the score set of the odor data to obtain the tea odor quality score; The step of sending the tea component data subset to the preset component quality identification submodule in the quality identification module to obtain the tea component quality score specifically includes: Extracting the tea component data in the tea component data subset; Extracting the tea components in the tea component data and the content values of the corresponding tea components; Comparatively analyzing the tea components and the preset tea components, if consistent, saving the corresponding tea components, if inconsistent, deleting the corresponding tea components; Determining the score of the corresponding tea component according to the preset tea component content range in which the content value of the corresponding tea component falls; Multiplying the score of the tea component by the weight proportion coefficient of the corresponding tea component, and then accumulating to obtain the score of the corresponding tea component; Traversing the entire tea component data subset to obtain a score set of the tea component; Calculating the average value of the scores of the tea components in the score set of the tea component to obtain the tea component quality score.

2. The method of claim 1, wherein the tea tree is Camellia sinensis var. assamica. Further comprising: Obtaining the soil data information of the tea tree planting; Obtaining the elements in the soil and the content values of the corresponding elements according to the soil data information of the tea tree planting; Obtaining the current time information and the corresponding tea tree information; Determining the standard element content value range of the corresponding tea tree at the current time according to the current time information and the corresponding tea tree information; If all the element content values in the soil are within the standard element content value range corresponding to the current time, the tea tree data obtained at the current time is qualified.

3. The method of claim 1, wherein the tea tree is Camellia sinensis var. assamica. The step of labeling the crown image in the tea tree image to obtain a crown labeled image specifically includes: Extracting the tea leaf region, tea tree branch region and non-tea tea tree branch region in the crown image; Comparatively analyzing the tea leaf image in the tea leaf region in the crown image and the preset tea leaf image to obtain a tea leaf similarity value; If the tea leaf similarity value is greater than or equal to a preset first similarity threshold, the corresponding tea leaf region is labeled according to a preset first numerical value, if the tea leaf similarity value is less than the preset first similarity threshold, the corresponding tea leaf region is labeled according to a preset third numerical value; Comparatively analyzing the tea tree branch image in the tea tree branch region in the crown image and the preset tea tree branch image to obtain a tea tree branch similarity value; If the tea tree branch similarity value is greater than or equal to a preset second similarity threshold, the corresponding tea tree branch region is labeled according to a preset second numerical value, if the tea tree branch similarity value is less than the preset second similarity threshold, the corresponding tea tree branch region is labeled according to a preset third numerical value; The non-tea-leaf tea tree branch region is marked according to a preset third value.

4. The method for identifying the quality of tea trees according to claim 1, characterized in that, The step of comparing and analyzing the tree crown marking subgraph and the preset tree crown marking subgraph of the corresponding region to obtain a tree crown marking subgraph similarity value specifically comprises: Extracting area values marked by the preset first value, the preset second value and the preset third value in the tree crown marking subgraph and setting the area values as a first area, a second area and a third area respectively; Extracting area values marked by the preset first value, the preset second value and the preset third value in the preset tree crown marking subgraph of the corresponding region and setting the area values as a preset first area, a preset second area and a preset third area respectively; Carrying out ratio of the first area and the preset first area to obtain a first ratio, carrying out ratio of the second area and the preset second area to obtain a second ratio, and carrying out ratio of the third area and the preset third area to obtain a third ratio; Extracting a minimum value in the first ratio, the second ratio and the third ratio and setting the minimum value as a tree crown marking subgraph similarity value of the tree crown marking subgraph and the preset tree crown marking subgraph of the corresponding region.

5. A tea tree quality identification system characterised by, The tea tree quality identification method program is stored in the memory and the processor.

Images