Alopecurus plant classification retrieval method and system based on multiple feature input
By acquiring qualitative and quantitative features and using pre-trained matching models for feature matching, the problems of low efficiency and insufficient accuracy of plant classification retrieval in the prior art are solved, and fast and accurate plant classification is achieved.
Patent Information
- Application Number
- CN202510292478.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-12
- Publication Date
- 2025-08-01
AI Technical Summary
Existing plant classification search methods are inefficient and insufficiently accurate when dealing with multiple feature inputs, especially when combining qualitative and quantitative features.
The classification search method of plant classification based on multiple feature inputs is adopted. By obtaining qualitative and quantitative feature information, the pre-trained matching model is used for feature matching and analysis, and the plant classification results are directly output to avoid step-by-step screening.
It improves the efficiency and accuracy of plant classification, and can quickly identify and output accurate plant classification results.
Smart Images
Figure CN120407890A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of plant classification, and in particular, to a method and system for classifying and retrieving Alopecurus plants based on multiple feature inputs. Background Art
[0002] Plant classification and retrieval is an important part of botanical research. Traditional retrieval methods require feature selection and matching in a strict order and hierarchical structure, which is a cumbersome and inefficient process. With the development of information technology, it has become possible to use data processing and matching algorithms for plant classification and retrieval. However, existing methods often rely on a complete retrieval table structure. In practical applications, plant features are often diverse, including qualitative features (such as leaf shape, flower color) and quantitative features (such as leaf length, plant height). However, existing technologies still have deficiencies in processing multiple feature inputs. Especially when dealing with qualitative and quantitative features simultaneously, the accuracy and efficiency of classification results still need to be improved. Therefore, a plant classification and retrieval method based on multiple feature inputs is needed to improve the accuracy and efficiency of classification. Summary of the Invention
[0003] The present invention provides a method and system for classifying and retrieving Alopecurus plants based on multiple feature inputs to solve the problems of low efficiency and poor accuracy in existing plant classification and retrieval. Through the method for classifying and retrieving Alopecurus plants based on multiple feature inputs, after inputting multiple qualitative and quantitative features, the classification results of Alopecurus plants can be directly given without screening step by step.
[0004] The present invention provides a method for classifying and retrieving Alopecurus plants based on multiple feature inputs, including: Obtaining multiple plant feature information; Inputting the multiple plant feature information into a pre-trained matching model to generate a matching result; Analyzing according to the matching result and outputting a plant classification result; Wherein, the matching model is trained based on plant feature information and corresponding plant types in a preset database.
[0005] According to the method for classifying and retrieving Alopecurus plants based on multiple feature inputs provided by the present invention, the obtaining of multiple plant feature information specifically includes: Obtaining the qualitative and quantitative features of the plant; Performing data cleaning on the qualitative and quantitative features to obtain processed plant feature information.
[0006] A classification and retrieval method for Alopecurus plants based on multiple feature inputs provided by the present invention. The matching model is trained based on plant feature information and corresponding plant types in a preset database, and specifically includes: Obtain plant feature information and corresponding plant types from the preset database as training set data and validation set data; Input the training set data into a preset neural network model for training. After a predetermined number of training rounds, a trained matching model is obtained.
[0007] A classification and retrieval method for Alopecurus plants based on multiple feature inputs provided by the present invention. After training, the matching model is verified by the validation set data to generate a verification result; Fine-tune the matching model according to the verification result to obtain the final matching model.
[0008] A classification and retrieval method for Alopecurus plants based on multiple feature inputs provided by the present invention. Inputting multiple plant feature information into a pre-trained matching model to generate a matching result specifically includes: Input the qualitative and quantitative features of the obtained plant into the matching model; The matching model performs feature matching in the preset database according to the qualitative and quantitative features of the plant to generate a matching result.
[0009] A classification and retrieval method for Alopecurus plants based on multiple feature inputs provided by the present invention. Analyzing according to the matching result and outputting a plant classification result specifically includes: Analyze according to the matching result output by the matching model to generate an analysis result; Convert the analysis result into a general plant species name to generate a plant classification result.
[0010] The present invention also provides a classification and retrieval system for Alopecurus plants based on multiple feature inputs. The system includes: A data acquisition module for acquiring multiple plant feature information; A matching module for inputting multiple plant feature information into a pre-trained matching model to generate a matching result; A result output module for analyzing according to the matching result and outputting a plant classification result; Among them, the matching model is trained based on plant feature information and corresponding plant types in a preset database.
[0011] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the method for classifying and retrieving Alopecurus plants based on multiple feature inputs as described in any one of the above is implemented.
[0012] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for classifying and retrieving Alopecurus plants based on multiple feature inputs as described in any one of the above is implemented.
[0013] The present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, the method for classifying and retrieving Alopecurus plants based on multiple feature inputs as described in any one of the above is implemented.
[0014] A method and system for classifying and retrieving Alopecurus plants based on multiple feature inputs provided by the present invention input the obtained plant feature information into a matching model, and perform matching in a database through the matching model to obtain a plant classification result. Fast processing and recognition through the matching model can improve the efficiency of plant classification and retrieval and make the classification result more accurate. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.
[0016] Figure 1 is a flowchart of the method for classifying and retrieving Alopecurus plants based on multiple feature inputs provided by the present invention.
[0017] Figure 2 is a schematic diagram of the module connection of the system for classifying and retrieving Alopecurus plants based on multiple feature inputs provided by the present invention.
[0018] Figure 3 is a schematic diagram of the structure of the electronic device provided by the present invention.
[0019] Reference numerals: 110: data acquisition module; 120: matching module; 130: result output module. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0020] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without creative efforts shall fall within the protection scope of the present invention.
[0021] The genus Alopecurus (scientific name: Alopecurus) is a genus under the family Poaceae, containing about 36 species of annual or perennial herbaceous plants. These plants are widely distributed in the temperate and frigid zones of the Northern Hemisphere and are commonly found in humid environments such as wetlands, grasslands, and the edges of farmlands. The Chinese name "Alopecurus" comes from the fact that its flowering period is synchronized with the growth cycle of wheat, and farmers often use it as a reference for the growth of field crops. Its morphology includes: Stem: erect or prostrate, usually 10 - 100 cm in height; Leaf: linear or lanceolate, flat, often clasping the stem at the base; Inflorescence: dense cylindrical spike-like panicle (similar to a "fox tail"), composed of many spikelets; Spikelet with a single flower, laterally compressed, with a short awn or without an awn; Flowering and fruiting period: mostly flowering from spring to summer, adapted to short-cycle growth. Ecological adaptability: likes humid environments, tolerates waterlogging, and is commonly found on riverbanks, paddy fields, wetlands or poorly drained soils; some species (such as Alopecurus aequalis) are farmland weeds and compete with crops for resources. Common species include: Alopecurus aequalis: an annual herb, a common weed in farmlands, especially thriving in wheat fields and paddy fields; the inflorescence is short, and the awn is extremely short or absent. Alopecurus pratensis: a perennial forage grass used for lawns or feed, with a longer inflorescence and a prominent awn. Alopecurus myosuroides: a noxious weed in European farmlands, which is resistant to herbicides. Since it competes with crops for light, water, and nutrients, reducing yields; some species (such as Alopecurus myosuroides) are difficult to control due to their strong drug resistance, so it is necessary to identify and classify them for effective control.
[0022] The following will be combined with Figure 1 Describe a classification and retrieval method for Alopecurus plants based on multiple feature inputs of the present invention, including: Step 100, obtaining multiple plant feature information.
[0023] Specifically, obtain the qualitative and quantitative features of the plant; perform data cleaning on the qualitative and quantitative features to obtain the processed plant feature information.
[0024] In the present invention, a user inputs multiple plant characteristics through an interactive interface or a command line, including qualitative characteristics (such as "glumes connate", "leaf sheath not inflated") and quantitative characteristics (such as "glume length 5 mm", "glume with 3 veins"). Or other characteristics, including: morphological characteristics, molecular sequence characteristics, physiological characteristics or other relevant characteristics of the plant.
[0025] By obtaining plant characteristic information, it can help to more accurately identify plant categories subsequently.
[0026] Step 200: Input the multiple plant characteristic information into a pre-trained matching model to generate a matching result.
[0027] In the present invention, the matching model is trained based on plant characteristic information and corresponding plant types in a preset database, specifically including: Obtain plant characteristic information and corresponding plant types from the preset database as training set data and validation set data; Input the training set data into a preset neural network model for training. After a predetermined number of rounds of training, a trained matching model is obtained.
[0028] After training, the matching model is verified by the validation set data to generate a verification result; the matching model is fine-tuned according to the verification result to obtain the final matching model.
[0029] By training the neural network model through a pre-established database, after obtaining the matching model, it can initially have the function of identifying plant categories according to plant characteristic information. After verifying the matching model with the validation set data, the process of fine-tuning the matching model makes the result generated by the matching model more accurate and more in line with the plant classification requirements.
[0030] Specifically, after the matching model is adjusted, the obtained qualitative and quantitative characteristics of the plant are input into the matching model; the matching model performs feature matching in the preset database according to the qualitative and quantitative characteristics of the plant to generate a matching result.
[0031] In the present invention, the multiple input characteristics are matched with the characteristics in the plant characteristic database. The plant characteristic database stores the characteristic information of the genus Alopecurus plants and establishes an association with the corresponding plant classification information. The system searches for plant records that are exactly the same as or highly relevant to the input characteristics through data processing and matching algorithms (such as string matching, regular expression matching, numerical range matching, etc.).
[0032] Among them, in the process of processing plant feature information, first is data preprocessing: standardize the features input by the user and those in the database, such as converting them all to lowercase, removing spaces, and processing synonyms. Feature classification: distinguish between string types, numerical range types, etc. String matching: for categorical features, use exact matching or partial string matching (such as inclusion relationships), for example, use the LIKE operator in SQL or the string containment method in code. Regular expression matching: handle more complex patterns, such as extracting numerical ranges, matching specific formats (such as color codes), or handling variant spellings. Numerical range matching: extract numerical values using regular expressions and then compare whether they are within the range in the database. Comprehensive scoring: calculate the overall matching degree based on the matching degree of each feature and return the most relevant results.
[0033] Specifically, the string matching algorithm can handle categorical features with exact or partial matches (such as leaf shape, flower color, inflorescence type).
[0034] Data standardization, convert the features input by the user and those in the database to lowercase uniformly, remove spaces and special symbols; Exact matching, directly compare whether the input feature is exactly the same as the string in the database; For example, input: leaf shape = oval; database matching: WHERE leaf shape = 'oval'; Partial matching (fuzzy matching), use wildcards (such as the LIKE operator) or string containment methods; Synonym processing, build a synonym table (such as 'oval' and 'elliptical'), map the input feature to the standard term and then match; The regular expression matching algorithm can handle complex patterns or numerical ranges (such as leaf length range, color coding, special morphological descriptions); Pattern extraction and parsing, use regular expressions to extract structured data from the input; Numerical range matching, compare the extracted numerical value with the range in the database (such as overlapping or inclusion relationships); Complex text pattern matching, use regular expressions to describe feature variants or fuzzy spellings; Special format processing, match specific formats (such as color codes, scientific nomenclature).
[0035] In the comprehensive matching process, feature classification and preprocessing, distinguish between text features (using strings / regular expressions) and numerical features (using regular expressions to extract ranges); Hierarchical matching strategy, first match key features (such as inflorescence type), and then match secondary features (such as leaf length); Weights and scoring, assign a high score to features with complete matches and appropriately reduce the weight for partial matches; Sort and return the results, arranging them in descending order of matching degree and returning relevant plant records.
[0036] Step 300: Analyze according to the matching result and output the plant classification result.
[0037] Specifically, analyze according to the matching result output by the matching model to generate an analysis result; Convert the analysis result into a general plant species name to generate a plant classification result.
[0038] In the present invention, according to the matching result, the system directly outputs the corresponding plant classification information. For example, when the input features are "glumes connate", "leaf sheath not inflated", "glume length 5 mm", "glume 3-veined", the system quickly retrieves all plants in the database with these features and outputs possible classification results such as "possibly Alopecurus myosuroides, Alopecurus japonicus".
[0039] Based on a method for classifying and retrieving Alopecurus plants based on multiple feature inputs provided by the present invention, by inputting the obtained plant feature information into a matching model, and performing matching in the database through the matching model to obtain a plant classification result; rapid processing and recognition through the matching model can improve the efficiency of plant classification and retrieval and make the classification result more accurate.
[0040] Reference Figure 2 , the present invention also discloses a system for classifying and retrieving Alopecurus plants based on multiple feature inputs, and the system includes: A data acquisition module 110 for acquiring multiple plant feature information; A matching module 120 for inputting multiple plant feature information into a pre-trained matching model to generate a matching result; A result output module 130 for analyzing according to the matching result and outputting a plant classification result; Among them, the matching model is trained based on plant feature information and corresponding plant types in a preset database.
[0041] Among them, the acquisition of multiple plant feature information specifically includes: Acquire qualitative and quantitative features of plants; Perform data cleaning on the qualitative and quantitative features to obtain processed plant feature information.
[0042] The matching model is trained based on plant feature information and corresponding plant types in a preset database, specifically including: Obtain plant feature information and corresponding plant types from a preset database as training set data and validation set data; Input the training set data into a preset neural network model for training. After a predetermined number of training rounds, a trained matching model is obtained.
[0043] The trained matching model is verified using the validation set data after training to generate a verification result; Fine-tune the matching model according to the verification result to obtain the final matching model.
[0044] Inputting multiple plant feature information into a pre-trained matching model to generate a matching result specifically includes: Input the qualitative and quantitative features of the obtained plant into the matching model; The matching model performs feature matching in the preset database based on the qualitative and quantitative features of the plant to generate a matching result.
[0045] Parsing according to the matching result and outputting a plant classification result specifically includes: Parse according to the matching result output by the matching model to generate a parsing result; Convert the parsing result into a general plant species name to generate a plant classification result.
[0046] Based on a classification and retrieval system for Alopecurus plants based on multiple feature inputs provided by the present invention, by inputting the obtained plant feature information into a matching model, and performing matching in the database through the matching model, a plant classification result is obtained; rapid processing and recognition through the matching model can improve the efficiency of plant classification and retrieval and make the classification result more accurate.
[0047] Figure 3 Illustrates a schematic physical structure diagram of an electronic device, as Figure 3 shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call the logical instructions in the memory 330 to execute a classification and retrieval method for Alopecurus plants based on multiple feature inputs, and the method includes: obtaining multiple plant feature information; inputting the multiple plant feature information into a pre-trained matching model to generate a matching result; parsing according to the matching result and outputting a plant classification result; wherein, the matching model is trained based on plant feature information and corresponding plant types in a preset database.
[0048] In addition, when the logical instructions in the above-mentioned memory 330 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.
[0049] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute a classification and retrieval method for Alopecurus plants based on multiple feature inputs provided by the above-mentioned various methods. The method includes: obtaining multiple plant feature information; inputting the multiple plant feature information into a pre-trained matching model to generate a matching result; parsing according to the matching result and outputting a plant classification result; wherein, the matching model is trained based on the plant feature information and the corresponding plant types in a preset database.
[0050] On another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute a classification and retrieval method for Alopecurus plants based on multiple feature inputs provided by the above-mentioned various methods. The method includes: obtaining multiple plant feature information; inputting the multiple plant feature information into a pre-trained matching model to generate a matching result; parsing according to the matching result and outputting a plant classification result; wherein, the matching model is trained based on the plant feature information and the corresponding plant types in a preset database.
[0051] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or 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. Those of ordinary skill in the art can understand and implement it without creative labor.
[0052] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0053] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A classification and retrieval method for Alopecurus plants based on multiple feature inputs, characterized in that, Including: Obtain multiple plant feature information; Input the multiple plant feature information into a pre-trained matching model to generate a matching result; Analyze according to the matching result and output a plant classification result; Among them, the matching model is trained based on the plant feature information and the corresponding plant types in a preset database.
2. The Alopecurus plant classification and retrieval method based on multiple feature inputs according to claim 1, characterized in that The obtaining of the multiple plant feature information specifically includes: Obtain the qualitative features and quantitative features of the plant; Perform data cleaning on the qualitative features and quantitative features to obtain the processed plant feature information.
3. The classification and retrieval method of Alopecurus plants based on multiple feature inputs according to claim 1, characterized in that The matching model is trained based on the plant feature information and the corresponding plant types in a preset database, specifically including: Obtain the plant feature information and the corresponding plant types from the preset database as training set data and validation set data; Input the training set data into a preset neural network model for training, and after a predetermined number of training rounds, obtain the trained matching model.
4. The classification and retrieval method of Alopecurus plants based on multiple feature inputs according to claim 3, characterized in that, The matching model is verified by the validation set data after training to generate a verification result; Fine-tune the matching model according to the verification result to obtain the final matching model.
5. The classification and retrieval method of Alopecurus plants based on multiple feature inputs according to claim 1, characterized in that, The inputting of the multiple plant feature information into the pre-trained matching model to generate a matching result specifically includes: Input the obtained qualitative features and quantitative features of the plant into the matching model; The matching model performs feature matching in the preset database according to the qualitative features and quantitative features of the plant to generate a matching result.
6. The classification and retrieval method of Alopecurus plants based on multiple feature inputs according to claim 1, characterized in that, The analyzing according to the matching result and outputting a plant classification result specifically includes: Analyze according to the matching result output by the matching model to generate an analysis result; Convert the analysis result into a common plant species name to generate a plant classification result.
7. A classification and retrieval system for Alopecurus plants based on multiple feature inputs, characterized in that, The system includes: A data acquisition module for obtaining multiple plant feature information; A matching module for inputting the multiple plant feature information into a pre-trained matching model to generate a matching result; A result output module for analyzing according to the matching result and outputting a plant classification result; Among them, the matching model is trained based on the plant feature information and the corresponding plant types in a preset database.
8. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and running on the processor, wherein, When the processor executes the computer program, it implements the Alopecurus plant classification and retrieval method based on multiple feature inputs according to any one of claims 1 to 6.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the Alopecurus plant classification and retrieval method based on multiple feature inputs according to any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the Alopecurus plant classification and retrieval method based on multiple feature inputs according to any one of claims 1 to 6.