Integrated planting data management method and system combined with strawberry growth and development model

Abstract

The invention discloses an integrated planting data management method and system combined with a strawberry growth and development model, and relates to the technical field of data processing, and the method comprises the steps: obtaining K sample plant growth monitoring data set sequences and K planting environment monitoring data set sequences; obtaining K planting environment monitoring data set value sets; obtaining a planting environment monitoring data set value mean value set; determining an environment deviation factor set; obtaining a sample plant growth monitoring data mean value set sequence; obtaining an interactive fusion sample plant growth feature set; determining strawberry growth and development evaluation factors, and performing integrated planting data management according to the planting data extraction frequency. The technical problems that in the prior art, the fitting degree of strawberry planting data management and actual strawberry growth and development conditions is low, and the management quality is poor are solved, and the technical effect of improving planting data management reliability and management efficiency is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an integrated planting data management method and system combined with a strawberry growth and development model. Background Art

[0002] In order to obtain high-quality strawberry fruits, it is necessary to conduct multi-dimensional data monitoring of the strawberry planting process, which generates a large amount of planting data that needs to be managed. At present, the integrated planting data is often extracted in real time or at a fixed monitoring frequency. The former requires a large amount of data to be processed, which is easy to cause data redundancy, a long data processing cycle, and the inability to respond quickly to the strawberry status. The latter is easy to cause a delayed analysis of changes in the strawberry status. The existing technology has technical problems such as low fit between strawberry planting data management and the actual growth and development of strawberries, and poor management quality. Summary of the invention

[0003] The present application provides an integrated planting data management method and system combined with a strawberry growth and development model, which is used to solve the technical problems in the prior art that the strawberry planting data management has a low fit with the actual growth and development of strawberries and the management quality is poor.

[0004] In view of the above problems, the present application provides an integrated planting data management method and system combined with a strawberry growth and development model.

[0005] In a first aspect of the present application, an integrated planting data management method combined with a strawberry growth and development model is provided, the method comprising:

[0006] Conditionally sampling strawberry plants in a target strawberry growth area to obtain K sample plants, performing plant growth monitoring and planting environment monitoring on the K sample plants in a preset monitoring window to obtain K sample plant growth monitoring data set sequences and K planting environment monitoring data set sequences, wherein K is an integer greater than or equal to 1;

[0007] Traversing the K planting environment monitoring data set sequences to perform median analysis of the data sets within the sequences, and obtaining median sets of K planting environment monitoring data sets;

[0008] Taking the planting environment monitoring data type as an index, respectively performing mean processing on the same type of planting environment monitoring data in the median value sets of the K planting environment monitoring data sets to obtain a median mean set of the planting environment monitoring data sets;

[0009] Determine an environment deviation factor set according to the deviation degree between the median mean set of the planting environment monitoring data set and the preset planting environment data set, wherein the environment deviation factor set includes M environment deviation factors, and each environment deviation factor corresponds to a planting environment monitoring data type;

[0010] Performing cross-sample data mean calculation on the K sample plant growth monitoring data set sequences to obtain a sample plant growth monitoring data mean set sequence;

[0011] Based on the M environmental deviation factors, M adaptive convolutional network layers are constructed, and the M adaptive convolutional network layers are used to perform multi-scale feature analysis on the mean set sequence of the sample plant growth monitoring data, and feature correlation interactive fusion analysis is performed on the analysis results to obtain an interactive fusion sample plant growth feature set;

[0012] The interactive fusion sample plant growth feature set is analyzed using a strawberry growth and development model to determine a strawberry growth and development evaluation factor, and the frequency of planting data extraction for strawberry plants in the target strawberry growth area is determined according to the size of the strawberry growth and development evaluation factor, and integrated planting data management is performed according to the planting data extraction frequency.

[0013] A second aspect of the present application provides an integrated planting data management system combined with a strawberry growth and development model, the system comprising:

[0014] A planting environment monitoring data set sequence acquisition module is used to perform conditional sampling on strawberry plants in a target strawberry growth area to obtain K sample plants, perform plant growth monitoring and planting environment monitoring on the K sample plants in a preset monitoring window, and obtain K sample plant growth monitoring data set sequences and K planting environment monitoring data set sequences, wherein K is an integer greater than or equal to 1;

[0015] A data set median value set acquisition module is used to traverse the K planting environment monitoring data set sequences to perform data set median analysis within the sequences to obtain K planting environment monitoring data set median value sets;

[0016] A planting environment monitoring data set median mean set acquisition module is used to perform mean processing on the same type of planting environment monitoring data in the K planting environment monitoring data set median sets, using the planting environment monitoring data type as an index, to obtain a planting environment monitoring data set median mean set;

[0017] An environmental deviation factor determination module is used to determine an environmental deviation factor set according to the deviation degree between the median mean set of the planting environment monitoring data set and the preset planting environment data set, wherein the environmental deviation factor set includes M environmental deviation factors, each environmental deviation factor corresponds to a planting environment monitoring data type;

[0018] A monitoring data mean set sequence acquisition module is used to perform cross-sample data mean calculation on the K sample plant growth monitoring data set sequences to obtain the sample plant growth monitoring data mean set sequence;

[0019] An interactive fusion sample plant growth feature set acquisition module is used to construct M adaptive convolutional network layers based on the M environmental deviation factors, use the M adaptive convolutional network layers to perform multi-scale feature analysis on the mean set sequence of the sample plant growth monitoring data, and perform feature correlation interactive fusion analysis on the analysis results to obtain an interactive fusion sample plant growth feature set;

[0020] The data management module is used to analyze the interactive fusion sample plant growth feature set using a strawberry growth and development model, determine a strawberry growth and development evaluation factor, and determine the frequency of extracting planting data for strawberry plants in the target strawberry growth area according to the size of the strawberry growth and development evaluation factor, and perform integrated planting data management according to the planting data extraction frequency.

[0021] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0022] The present application obtains K sample plants by conditional sampling of strawberry plants in a target strawberry growth area, and performs plant growth monitoring and planting environment monitoring on the K sample plants in a preset monitoring window to obtain a sequence of K sample plant growth monitoring data sets and a sequence of K planting environment monitoring data sets, wherein K is an integer greater than or equal to 1, and then traverses the K planting environment monitoring data set sequences to perform median analysis of the data sets in the sequences to obtain a median set of K planting environment monitoring data sets; using the planting environment monitoring data type as an index, respectively performing mean processing on the same type of planting environment monitoring data in the median set of the K planting environment monitoring data sets to obtain a median mean set of the planting environment monitoring data sets, and then determining an environmental deviation factor set according to the degree of deviation between the median mean set of the planting environment monitoring data sets and the preset planting environment data set, wherein the environmental deviation factor set includes M environmental deviation factors, each of which corresponds to a type of planting environment monitoring data, then the cross-sample data mean calculation is performed on the K sample plant growth monitoring data set sequence to obtain the sample plant growth monitoring data mean set sequence, then M adaptive convolutional network layers are constructed based on the M environmental deviation factors, and the M adaptive convolutional network layers are used to perform multi-scale feature analysis on the sample plant growth monitoring data mean set sequence, and the analysis results are subjected to feature correlation interactive fusion analysis to obtain the interactive fusion sample plant growth feature set, and then the strawberry growth and development model is used to analyze the interactive fusion sample plant growth feature set to determine the strawberry growth and development evaluation factor, and the frequency of planting data extraction for strawberry plants in the target strawberry growth area is determined according to the size of the strawberry growth and development evaluation factor, and integrated planting data management is performed according to the planting data extraction frequency. The strawberry growth and development model is used to analyze the strawberry growth characteristics with high reliability, obtain the strawberry growth status, determine the extraction frequency of reliable data extraction for planting data according to the strawberry growth status, and improve the reliability and efficiency of data management. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A schematic diagram of the flow chart of the integrated planting data management method combined with the strawberry growth and development model provided in the embodiment of the present application;

[0025] Figure 2 A schematic diagram of the structure of an integrated planting data management system combined with a strawberry growth and development model provided in an embodiment of the present application.

[0026] Explanation of the accompanying drawings: planting environment monitoring data set sequence acquisition module 11, data set median value set acquisition module 12, planting environment monitoring data set median mean set acquisition module 13, environmental deviation factor determination module 14, monitoring data mean set sequence acquisition module 15, interactive fusion sample plant growth feature set acquisition module 16, data management module 17. DETAILED DESCRIPTION

[0027] The present application provides an integrated planting data management method and system combined with a strawberry growth and development model, which is used to solve the technical problems in the prior art that the strawberry planting data management has a low fit with the actual growth and development of strawberries and the management quality is poor.

[0028] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0029] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0030] Embodiment 1, as Figure 1 As shown, the present application provides an integrated planting data management method combined with a strawberry growth and development model, wherein the method comprises:

[0031] Step S100: conditionally sampling strawberry plants in the target strawberry growth area to obtain K sample plants, performing plant growth monitoring and planting environment monitoring on the K sample plants in a preset monitoring window to obtain K sample plant growth monitoring data set sequences and K planting environment monitoring data set sequences, wherein K is an integer greater than or equal to 1;

[0032] Further, conditional sampling is performed on plants in the target strawberry growth area to obtain K sample plants. Step S100 of the embodiment of the present application further includes:

[0033] Obtaining a preset sampling number, and randomly sampling the plants in the target strawberry growth area based on the preset sampling number to obtain K random sample plants, wherein the preset sampling number is K;

[0034] Enumerating the K random sample plants in pairs to obtain multiple plant enumeration combinations, and calculating the distribution position similarity of the multiple plant enumeration combinations using cosine similarity to obtain multiple position combination similarities;

[0035] Determine whether the similarities of the multiple position combinations meet the preset sampling conditions. If so, use sampling authentication to take the K random sample plants as K sample plants, wherein the preset sampling condition is that the number of combinations of the multiple position combination similarities that are greater than or equal to the preset position combination similarity is less than a preset number threshold.

[0036] In a possible embodiment, the number K of random sampling is set by a technician in this field according to the plant scale and monitoring requirements of the target strawberry growth area, where K is an integer greater than or equal to 1. The target strawberry growth area is any area that requires integrated planting data management. The K sample plants meet the requirements of the preset sampling conditions, that is, the plants that pass the sampling certification. The preset monitoring window is a time period for monitoring the growth of the sample plants and the planting environment, which can be 3 days, 5 days, etc., and is set by the technicians in this field according to the actual situation.

[0037] In one embodiment, plant growth monitoring indicators (including plant height, leaf area, stem thickness, flower bud differentiation status, fruit weight, etc.) and planting environment monitoring indicators (including temperature, humidity, light intensity, soil moisture, soil pH, etc.) are obtained, and then the K sample plants are respectively monitored for plant growth and planting environment in the preset monitoring window using a sensor array (an integrated sensor for monitoring the growth status and environmental status of the sample plants, such as sensors, cameras, etc.), and the monitoring data are recorded in time series to form K sample plant growth monitoring data set sequences and K planting environment monitoring data set sequences. The K sample plant growth monitoring data set sequences reflect the changes in the plant growth status of the sample plants within the preset monitoring window, and the K planting environment monitoring data set sequences reflect the changes in the planting environment status of the sample plants within the preset monitoring window.

[0038] By obtaining the K sample plant growth monitoring data set sequences and the K planting environment monitoring data set sequences, the goal of comprehensively monitoring the growth conditions and planting environment of the K sample plants is achieved, and corresponding data set sequences are generated, achieving the technical effect of providing high-quality data support for subsequent feature analysis and planting data management.

[0039] Exemplarily, assuming that there are 500 strawberry plants in the target area, the preset sampling number K=10, and 10 plants are randomly selected from the 500 strawberry plants as the initial sample. Enumerate the pairwise combinations of the 10 plants to obtain 45 combinations. The cosine similarity formula is used to calculate the distribution position similarity of each combination, and the number of combinations with a similarity higher than a preset threshold (such as 0.8) is counted. If the number of combinations with high similarity is less than the preset threshold (such as 15), it passes the authentication and enters data monitoring; otherwise, re-sample.

[0040] By performing conditional sampling, representative sample plants are obtained in terms of distribution, avoiding the situation where the sample distribution is too concentrated and unable to provide reliable sample data for subsequent monitoring and analysis. This has achieved the technical effect of improving the quality of sample plant selection and providing a sample basis for subsequent analysis.

[0041] Step S200: traversing the K planting environment monitoring data set sequences to perform median analysis on the data sets within the sequences, and obtaining median sets of K planting environment monitoring data sets;

[0042] Further, the K planting environment monitoring data set sequences are traversed to perform median analysis of the data sets in the sequences to obtain median sets of K planting environment monitoring data sets. Step S200 of the embodiment of the present application further includes:

[0043] Extracting a first planting environment monitoring data set sequence from the K planting environment monitoring data set sequences, wherein the first planting environment monitoring data set sequence includes a plurality of first planting environment monitoring data subsequences of a plurality of planting environment monitoring data types;

[0044] Traversing the plurality of first planting environment monitoring data subsequences to perform data mean calculation, determining a plurality of first data means, taking the plurality of first data means as a plurality of concentration value analysis starting points, performing iterative analysis in the plurality of first planting environment monitoring data subsequences respectively according to a preset iteration step length, determining a plurality of first planting environment monitoring data median values, and summarizing the plurality of first planting environment monitoring data median values ​​to obtain a set of the first planting environment monitoring data median values;

[0045] Performing data median analysis within the sequence on the K planting environment monitoring data set sequences to determine the median set of the K planting environment monitoring data sets.

[0046] Furthermore, step S200 of the embodiment of the present application further includes:

[0047] Iterate the multiple concentrated value analysis starting points in the multiple first planting environment monitoring data subsequences according to the preset iteration step length to obtain multiple iteration data;

[0048] Determine whether the concentration density of the multiple iterative data is greater than or equal to the concentration density of the multiple concentration value analysis starting points, and if so, update the multiple iterative data to multiple concentration value analysis starting points, and iterate in the multiple first planting environment monitoring data subsequences according to the preset iteration step size;

[0049] Until the preset number of iterations is met, the plurality of first planting environment monitoring data corresponding to the plurality of iteration data obtained in the last iteration are taken as the median of the plurality of first planting environment monitoring data.

[0050] In one possible embodiment, the K planting environment monitoring data set sequences are analyzed for the general distribution of data within the sequences, and the median value of the planting environment monitoring data set that can represent the general situation of each planting environment monitoring data in the preset monitoring window is determined, thereby obtaining the median value set of the K planting environment monitoring data sets. The technical effect of performing data concentration analysis on the median value set of the K planting environment monitoring data sets, obtaining the representative median value of the planting environment monitoring data sets, and providing reliable data for subsequent analysis on the basis of reducing the amount of data analysis is achieved.

[0051] In one embodiment, each planting environment monitoring data set sequence includes multiple planting environment monitoring data types (such as temperature, humidity, light intensity, etc.). A first planting environment monitoring data set sequence is extracted from the K planting environment monitoring data set sequences, and the first planting environment monitoring data set sequence is analyzed to determine the corresponding first planting environment monitoring data set median value set.

[0052] Optionally, the first planting environment monitoring data set sequence includes a plurality of first planting environment monitoring data subsequences of a plurality of planting environment monitoring data types, and each first planting environment monitoring data subsequence corresponds to a planting environment monitoring data type.

[0053] Optionally, the plurality of first planting environment monitoring data subsequences are traversed to perform data mean calculation to determine a plurality of first data means, wherein the plurality of first data means reflect the average level of monitoring data corresponding to each planting environment monitoring data type when accidental data is included.

[0054] Then, the multiple first data means are used as multiple concentration value analysis starting points, and iterative analysis is performed in the multiple first planting environment monitoring data subsequences according to a preset iteration step length to obtain multiple iterative data. The preset iteration step length is the data difference between two adjacent iterations preset by a person skilled in the art.

[0055] Optionally, a plurality of iterative neighborhoods of the plurality of iterative data are constructed with the plurality of iterative data as the center and the preset iterative step as the radius, wherein each iterative neighborhood includes a plurality of first planting environment monitoring data whose difference with the iterative data is a preset iterative step, and then the amount of data contained in the plurality of iterative neighborhoods is counted, and the statistical result is compared with the preset iterative step to obtain the concentration density of the plurality of iterative data. The concentration density of the plurality of iterative data reflects the density of the first planting environment monitoring data gathered around the plurality of iterative data. Based on the same principle as that of obtaining the concentration density of the plurality of iterative data, the concentration density of the plurality of concentration value analysis starting points is obtained.

[0056] Optionally, determine whether the concentration density of the multiple iterative data is greater than or equal to the concentration density of the multiple concentrated value analysis starting points. If so, it indicates that the data density distributed around the multiple iterative data is higher than that of the multiple concentrated value analysis starting points. At this time, update the multiple iterative data to multiple concentrated value analysis starting points, and iterate the multiple first planting environment monitoring data subsequences according to the preset iteration step size until the preset number of iterations is met, and use the multiple first planting environment monitoring data corresponding to the multiple iterative data obtained in the last iteration as the median of the multiple first planting environment monitoring data.

[0057] If not, it indicates that the data density around the multiple iterative data is not higher than the multiple concentrated value analysis starting points, and the iteration is stopped at this time, and the multiple concentrated value analysis starting points are used as the median values ​​of the multiple first planting environment monitoring data sets. Then, the median values ​​of the multiple first planting environment monitoring data sets are summarized to obtain the median value set of the first planting environment monitoring data sets.

[0058] Optionally, based on the same principle as that of obtaining the median set of the first planting environment monitoring data set, the median analysis of the K planting environment monitoring data set sequences is performed to determine the median set of the K planting environment monitoring data sets. This achieves the technical effect of obtaining the median of the planting environment monitoring data set with high representativeness, ensuring the accuracy and reliability of the environmental data, and providing high-quality input data for subsequent model analysis.

[0059] Step S300: using the planting environment monitoring data type as an index, respectively performing mean processing on the same type of planting environment monitoring data in the median value sets of the K planting environment monitoring data sets to obtain a median mean set of the planting environment monitoring data sets;

[0060] Step S400: determining an environment deviation factor set according to the deviation degree between the median mean set of the planting environment monitoring data set and the preset planting environment data set, wherein the environment deviation factor set includes M environment deviation factors, and each environment deviation factor corresponds to a planting environment monitoring data type;

[0061] Step S500: performing cross-sample data mean calculation on the K sample plant growth monitoring data set sequences to obtain a sample plant growth monitoring data mean set sequence;

[0062] In one possible embodiment, K planting environment monitoring data set median sets are classified according to the planting environment monitoring data type (such as temperature, humidity, light intensity, soil moisture, etc.) to generate multiple planting environment monitoring data set median subsets of the same type. Each planting environment monitoring data set median subset corresponds to a planting environment monitoring data type. The mean within the subset is calculated for multiple planting environment monitoring data set median subsets of the same type to obtain multiple planting environment monitoring data set median means of the same type, and the planting environment monitoring data set median mean set is obtained after summarizing. Among them, the planting environment monitoring data set median mean set is a set obtained after fusing the environmental monitoring data of multiple sample plants, reflecting the general situation of the strawberry plant planting environment in the target strawberry growth area.

[0063] Optionally, the difference between the mean value set of the planting environment monitoring data set and the corresponding data in the preset planting environment data set is calculated respectively, and the calculated result is compared with the corresponding data in the preset planting environment data set to obtain an environmental deviation factor set, wherein the environmental deviation factor set includes M environmental deviation factors, each environmental deviation factor corresponds to a planting environment monitoring data type. Each environmental deviation factor reflects the deviation of the planting environment monitoring data type in the actual planting process.

[0064] Using the plant growth monitoring data type as an index, the cross-sample data mean calculation is performed on the K sample plant growth monitoring data set sequence, the general data situation of each plant growth monitoring data type changing over time within a preset window is determined, and the sample plant growth monitoring data mean set sequence is obtained. The technical effect of providing reliable data support for subsequent analysis is achieved.

[0065] Step S600: constructing M adaptive convolutional network layers based on the M environmental deviation factors, using the M adaptive convolutional network layers to perform multi-scale feature analysis on the mean set sequence of the sample plant growth monitoring data, and performing feature correlation interactive fusion analysis on the analysis results to obtain an interactive fusion sample plant growth feature set;

[0066] Further, based on the M environmental deviation factors, M adaptive convolutional network layers are constructed, and the M adaptive convolutional network layers are used to perform multi-scale feature analysis on the mean set sequence of the sample plant growth monitoring data, and feature correlation interactive fusion analysis is performed on the analysis results to obtain an interactive fusion sample plant growth feature set. Step S600 of the embodiment of the present application also includes:

[0067] The M adaptive convolutional network layers perform data feature extraction on the mean set sequence of the sample plant growth monitoring data according to the M receptive fields to obtain M sample plant growth feature sets, wherein the receptive field is the extraction width when the adaptive convolutional network layer performs feature extraction on the mean set sequence of the sample plant growth monitoring data;

[0068] Mapping and sorting the M sample plant growth feature sets according to the order of the M receptive fields from large to small to obtain a sample plant growth feature set sequence;

[0069] The sample plant growth feature sets in the sample plant growth feature set sequence are sequentially subjected to feature association interactive fusion analysis to obtain an interactively fused sample plant growth feature set.

[0070] Further, feature association interactive fusion analysis is performed on the sample plant growth feature sets in the sample plant growth feature set sequence in sequence to obtain an interactive fusion sample plant growth feature set. Step S600 of the embodiment of the present application further includes:

[0071] Performing feature correlation interaction fusion analysis on the first sample plant growth feature set and the second sample plant growth feature set of the sample plant growth feature set sequence to obtain a first correlation interaction fusion sample plant growth feature set;

[0072] Extracting a third sample plant growth feature set from the sample plant growth feature set sequence, performing feature correlation interaction fusion analysis on the third sample plant growth feature set and the first correlation interaction fusion sample plant growth feature set to determine a second correlation interaction fusion sample plant growth feature set;

[0073] Based on the second associated interactively fused sample plant growth feature set, feature associated interactively fused analysis is continued on the sample plant growth feature set sequence until the end of the sample plant growth feature set sequence is reached to obtain the interactively fused sample plant growth feature set.

[0074] Further, feature correlation interaction fusion analysis is performed on the first sample plant growth feature set and the second sample plant growth feature set of the sample plant growth feature set sequence to obtain a first correlation interaction fusion sample plant growth feature set. Step S600 of the embodiment of the present application includes:

[0075] Performing inner product calculation on the first sample plant growth feature set and the second sample plant growth feature set to determine a first associated interactive fusion feature similarity set;

[0076] Traversing the first association interaction fusion feature similarity set to perform similarity normalization processing, and embedding the processing result into a matrix to obtain a first association interaction fusion matrix;

[0077] The first association interaction fusion matrix and the second sample plant growth feature set are convolved to determine the first association interaction fusion sample plant growth feature set.

[0078] In one possible embodiment, the M receptive fields of the M adaptive convolutional network layers are determined according to the size of the M environmental deviation factors. The receptive field is the extraction width when the adaptive convolutional network layer extracts features from the mean set sequence of sample plant growth monitoring data. The larger the environmental deviation factor, the greater the degree of deviation of the planting environment monitoring data type in the actual planting process, and the more sophisticated analysis is required, so the corresponding receptive field is smaller.

[0079] Optionally, the ratio of the M environmental deviation factors to the sum of the M environmental deviation factors is calculated respectively, and the calculated result is multiplied by the preset receptive field to obtain the M receptive fields. The preset receptive field is the extraction width pre-set by a person skilled in the art when extracting features from the mean set sequence of sample plant growth monitoring data. Then, the parameters of the initial adaptive convolutional network layer are configured based on the M receptive fields to obtain the configured M adaptive convolutional network layers.

[0080] Optionally, multiple historical sample plant growth monitoring data mean set sequences and multiple historical sample plant growth feature sets are obtained as training data, and supervised training is performed on an adaptive convolutional network layer constructed based on a convolutional neural network. The mapping relationship between the sample plant growth monitoring data mean set sequence and the sample plant growth feature set is learned until the training converges, thereby obtaining the initial adaptive convolutional network layer that has completed the training.

[0081] The M adaptive convolutional network layers are used to perform multi-scale feature analysis on the mean set sequence of the sample plant growth monitoring data, and feature correlation interactive fusion analysis is performed on the analysis results to obtain an interactive fusion sample plant growth feature set. The interactive fusion sample plant growth feature set reflects the growth status of the strawberry plants in the target strawberry growth area. This achieves the goal of performing a before-and-after correlation analysis on the plant growth status within the preset monitoring window, deeply digging into the growth status of the strawberry plants, and achieving the technical effect of providing reliable analysis data support for subsequent analysis of the growth and development of strawberries.

[0082] In one embodiment, the M adaptive convolutional network layers are used to perform multi-scale data feature extraction on the mean set sequence of the sample plant growth monitoring data to obtain M sample plant growth feature sets. According to the order of the M receptive fields from large to small, the corresponding M sample plant growth feature sets are mapped and sorted to obtain a sample plant growth feature set sequence.

[0083] Furthermore, feature correlation interaction fusion analysis is performed on the first sample plant growth feature set and the second sample plant growth feature set of the sample plant growth feature set sequence to obtain a first correlation interaction fusion sample plant growth feature set. Specifically, the inner product of the first sample plant growth feature set and the second sample plant growth feature set is calculated using the cosine similarity formula to determine the first correlation interaction fusion feature similarity set. Each first correlation interaction fusion feature similarity reflects the degree of similarity between a growth feature in the first sample plant growth feature set and the corresponding growth feature in the second sample plant growth feature set.

[0084] The softmax formula is used to traverse the first association interaction fusion feature similarity set to perform similarity normalization processing, determine the normalized value of each first association interaction fusion feature similarity, and embed the processing result into the matrix to obtain the first association interaction fusion matrix. The first association interaction fusion matrix is ​​a matrix that has been normalized and eliminates data dimension differences. Furthermore, a convolutional network is used to perform convolution calculation on the first association interaction fusion matrix and the second sample plant growth feature set to determine the first association interaction fusion sample plant growth feature set. The technical effect of deeply fusing the first sample plant growth feature set with the second sample plant growth feature set and further extracting more refined growth features is achieved.

[0085] Optionally, a third sample plant growth feature set of the sample plant growth feature set sequence is extracted, and feature correlation interaction fusion analysis is performed on it and the first correlation interaction fusion sample plant growth feature set, and based on the same principle as for obtaining the first correlation interaction fusion sample plant growth feature set, a second correlation interaction fusion sample plant growth feature set is determined.

[0086] Optionally, based on the same principle as for obtaining the first associated interactively fused sample plant growth feature set, feature associated interactively fused analysis of the sample plant growth feature set sequence is continued based on the second associated interactively fused sample plant growth feature set until the end of the sample plant growth feature set sequence is reached to obtain the interactively fused sample plant growth feature set.

[0087] By using M adaptive convolutional network layers, multi-scale feature extraction of sample plant growth monitoring data was performed, and in-depth analysis of plant growth characteristics was achieved through interactive fusion and inner product calculation processing. Through this process, a comprehensive interactive fusion sample plant growth feature set was finally obtained, achieving the technical effect of providing an important basis for subsequent growth trend analysis.

[0088] Step S700: Analyze the interactive fusion sample plant growth feature set using the strawberry growth and development model to determine the strawberry growth and development evaluation factor, and determine the frequency of planting data extraction for the strawberry plants in the target strawberry growth area according to the size of the strawberry growth and development evaluation factor, and perform integrated planting data management according to the planting data extraction frequency.

[0089] In a possible embodiment, the strawberry growth and development model is a functional model that reliably analyzes the growth and development of strawberries based on the growth characteristics of strawberry plants. Optionally, multiple historical strawberry plant growth characteristics and multiple historical strawberry growth and development assessment factors are obtained as training data, and the training data is used to supervise the training of the framework built based on the convolutional neural network. During the training, the mapping relationship between the strawberry plant growth characteristics and the strawberry growth and development assessment factors is learned until the training converges, thereby obtaining the trained strawberry growth and development model.

[0090] Optionally, the interactive fusion sample plant growth feature set is input into the strawberry growth and development model for analysis to obtain a strawberry growth and development assessment factor. Wherein, the strawberry growth and development assessment factor reflects the growth and development state of strawberries. Obtain the strawberry growth and development assessment factor-extraction frequency mapping relationship preset by a person skilled in the art, use the strawberry growth and development assessment factor as an index, retrieve the strawberry growth and development assessment factor-extraction frequency mapping relationship, and obtain the planting data extraction frequency. Preferably, if the assessment factor is close to the ideal value range, it indicates that the strawberry growth state is stable and the data extraction frequency can be reduced (such as once a day). If the assessment factor deviates from the ideal value range, it indicates that there is abnormal growth in strawberries and the data extraction frequency needs to be increased (such as once an hour). According to the obtained planting data extraction frequency, the plant growth and planting environment data of the target strawberry growth area are managed. The technical effect of determining the planting data extraction frequency and improving the efficiency and quality of integrated planting data management according to the analysis results of the strawberry growth and development model is achieved.

[0091] In summary, the embodiments of the present application have at least the following technical effects:

[0092] This application selects representative sample plants through conditional sampling, realizes a scientific conditional sampling method, ensures that the sample plants are representative, and reduces the goal of data deviation. Then, the data is optimized by using concentrated value analysis and mean processing, random fluctuations in environmental data are eliminated, and the most representative data features are extracted. M environmental deviation factors are determined to construct M adaptive convolutional network layers to perform multi-scale feature analysis on the mean set sequence of sample plant growth monitoring data, and an in-depth correlation analysis of capturing strawberry growth is achieved. The interactive fusion sample plant growth feature set is determined, and then the interactive fusion sample plant growth feature set is analyzed using a strawberry growth and development model to determine the strawberry growth and development assessment factor, and the frequency of extracting planting data for strawberry plants in the target strawberry growth area is determined according to the size of the strawberry growth and development assessment factor, and integrated planting data management is performed according to the planting data extraction frequency. The technical effect of managing planting data according to the corresponding extraction frequency according to the actual growth state of the strawberry is achieved.

[0093] Embodiment 2 is based on the same inventive concept as the integrated planting data management method combined with the strawberry growth and development model in the above embodiment. Figure 2 As shown, the present application provides an integrated planting data management system combined with a strawberry growth and development model. The system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0094] The planting environment monitoring data set sequence acquisition module 11 is used to perform conditional sampling on strawberry plants in the target strawberry growth area to obtain K sample plants, perform plant growth monitoring and planting environment monitoring on the K sample plants in a preset monitoring window, and obtain K sample plant growth monitoring data set sequences and K planting environment monitoring data set sequences, wherein K is an integer greater than or equal to 1;

[0095] A data set median value set obtaining module 12 is used to traverse the K planting environment monitoring data set sequences to perform data set median analysis within the sequences to obtain K planting environment monitoring data set median value sets;

[0096] The planting environment monitoring data set median mean set obtaining module 13 is used to perform mean processing on the same type of planting environment monitoring data in the K planting environment monitoring data set median sets respectively, using the planting environment monitoring data type as an index, to obtain the planting environment monitoring data set median mean set;

[0097] An environmental deviation factor determination module 14 is used to determine an environmental deviation factor set according to the deviation degree between the median mean set of the planting environment monitoring data set and the preset planting environment data set, wherein the environmental deviation factor set includes M environmental deviation factors, each environmental deviation factor corresponds to a planting environment monitoring data type;

[0098] The monitoring data mean set sequence obtaining module 15 is used to perform cross-sample data mean calculation on the K sample plant growth monitoring data set sequences to obtain the sample plant growth monitoring data mean set sequence;

[0099] An interactive fusion sample plant growth feature set acquisition module 16 is used to construct M adaptive convolutional network layers based on the M environmental deviation factors, perform multi-scale feature analysis on the mean set sequence of the sample plant growth monitoring data using the M adaptive convolutional network layers, and perform feature correlation interactive fusion analysis on the analysis results to obtain an interactive fusion sample plant growth feature set;

[0100] The data management module 17 is used to analyze the interactive fusion sample plant growth feature set using the strawberry growth and development model, determine the strawberry growth and development evaluation factor, and determine the frequency of planting data extraction for the strawberry plants in the target strawberry growth area according to the size of the strawberry growth and development evaluation factor, and perform integrated planting data management according to the planting data extraction frequency.

[0101] Furthermore, the interactive fusion sample plant growth feature set acquisition module 16 is used to perform the following steps:

[0102] The M adaptive convolutional network layers perform data feature extraction on the mean set sequence of the sample plant growth monitoring data according to the M receptive fields to obtain M sample plant growth feature sets, wherein the receptive field is the extraction width when the adaptive convolutional network layer performs feature extraction on the mean set sequence of the sample plant growth monitoring data;

[0103] Mapping and sorting the M sample plant growth feature sets according to the order of the M receptive fields from large to small to obtain a sample plant growth feature set sequence;

[0104] The sample plant growth feature sets in the sample plant growth feature set sequence are sequentially subjected to feature association interactive fusion analysis to obtain an interactively fused sample plant growth feature set.

[0105] Furthermore, the interactive fusion sample plant growth feature set acquisition module 16 is used to perform the following steps:

[0106] Performing feature correlation interaction fusion analysis on the first sample plant growth feature set and the second sample plant growth feature set of the sample plant growth feature set sequence to obtain a first correlation interaction fusion sample plant growth feature set;

[0107] Extracting a third sample plant growth feature set from the sample plant growth feature set sequence, performing feature correlation interaction fusion analysis on the third sample plant growth feature set and the first correlation interaction fusion sample plant growth feature set to determine a second correlation interaction fusion sample plant growth feature set;

[0108] Based on the second associated interactively fused sample plant growth feature set, feature associated interactively fused analysis is continued on the sample plant growth feature set sequence until the end of the sample plant growth feature set sequence is reached to obtain the interactively fused sample plant growth feature set.

[0109] Furthermore, the interactive fusion sample plant growth feature set acquisition module 16 is used to perform the following steps:

[0110] Performing inner product calculation on the first sample plant growth feature set and the second sample plant growth feature set to determine a first associated interactive fusion feature similarity set;

[0111] Traversing the first association interaction fusion feature similarity set to perform similarity normalization processing, and embedding the processing result into a matrix to obtain a first association interaction fusion matrix;

[0112] The first association interaction fusion matrix and the second sample plant growth feature set are convolved to determine the first association interaction fusion sample plant growth feature set.

[0113] Furthermore, the data set median value set obtaining module 12 is used to perform the following steps:

[0114] Extracting a first planting environment monitoring data set sequence from the K planting environment monitoring data set sequences, wherein the first planting environment monitoring data set sequence includes a plurality of first planting environment monitoring data subsequences of a plurality of planting environment monitoring data types;

[0115] Traversing the plurality of first planting environment monitoring data subsequences to perform data mean calculation, determining a plurality of first data means, taking the plurality of first data means as a plurality of concentration value analysis starting points, performing iterative analysis in the plurality of first planting environment monitoring data subsequences respectively according to a preset iteration step length, determining a plurality of first planting environment monitoring data median values, and summarizing the plurality of first planting environment monitoring data median values ​​to obtain a set of the first planting environment monitoring data median values;

[0116] Performing data median analysis within the sequence on the K planting environment monitoring data set sequences to determine the median set of the K planting environment monitoring data sets.

[0117] Furthermore, the data set median value set obtaining module 12 is used to perform the following steps:

[0118] Iterate the multiple concentrated value analysis starting points in the multiple first planting environment monitoring data subsequences according to the preset iteration step length to obtain multiple iteration data;

[0119] Determine whether the concentration density of the multiple iterative data is greater than or equal to the concentration density of the multiple concentration value analysis starting points, and if so, update the multiple iterative data to multiple concentration value analysis starting points, and iterate in the multiple first planting environment monitoring data subsequences according to the preset iteration step size;

[0120] Until the preset number of iterations is met, the plurality of first planting environment monitoring data corresponding to the plurality of iteration data obtained in the last iteration are taken as the median of the plurality of first planting environment monitoring data.

[0121] Furthermore, the planting environment monitoring data set sequence acquisition module 11 is used to perform the following steps:

[0122] Obtaining a preset sampling number, and randomly sampling the plants in the target strawberry growth area based on the preset sampling number to obtain K random sample plants, wherein the preset sampling number is K;

[0123] Enumerating the K random sample plants in pairs to obtain multiple plant enumeration combinations, and calculating the distribution position similarity of the multiple plant enumeration combinations using cosine similarity to obtain multiple position combination similarities;

[0124] Determine whether the similarities of the multiple position combinations meet the preset sampling conditions. If so, use sampling authentication to take the K random sample plants as K sample plants, wherein the preset sampling condition is that the number of combinations of the multiple position combination similarities that are greater than or equal to the preset position combination similarity is less than a preset number threshold.

[0125] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0126] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0127] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An integrated planting data management method based on a strawberry growth and development model, characterized in that: The method comprises: Conditionally sampling strawberry plants in a target strawberry growth area to obtain K sample plants, performing plant growth monitoring and planting environment monitoring on the K sample plants in a preset monitoring window to obtain K sample plant growth monitoring data set sequences and K planting environment monitoring data set sequences, wherein K is an integer greater than or equal to 1; Traversing the K planting environment monitoring data set sequences to perform median analysis of the data sets within the sequences, and obtaining median sets of K planting environment monitoring data sets; Taking the planting environment monitoring data type as an index, respectively performing mean processing on the same type of planting environment monitoring data in the median value sets of the K planting environment monitoring data sets to obtain a median mean set of the planting environment monitoring data sets; Determine an environment deviation factor set according to the deviation degree between the median mean set of the planting environment monitoring data set and the preset planting environment data set, wherein the environment deviation factor set includes M environment deviation factors, and each environment deviation factor corresponds to a planting environment monitoring data type; Performing cross-sample data mean calculation on the K sample plant growth monitoring data set sequences to obtain a sample plant growth monitoring data mean set sequence; Based on the M environmental deviation factors, M adaptive convolutional network layers are constructed, and the M adaptive convolutional network layers are used to perform multi-scale feature analysis on the mean set sequence of the sample plant growth monitoring data, and feature correlation interactive fusion analysis is performed on the analysis results to obtain an interactive fusion sample plant growth feature set; The interactive fusion sample plant growth feature set is analyzed using a strawberry growth and development model to determine a strawberry growth and development evaluation factor, and the frequency of planting data extraction for strawberry plants in the target strawberry growth area is determined according to the size of the strawberry growth and development evaluation factor, and integrated planting data management is performed according to the planting data extraction frequency.

2. The method according to claim 1, characterized in that Based on the M environmental deviation factors, M adaptive convolutional network layers are constructed, and the M adaptive convolutional network layers are used to perform multi-scale feature analysis on the mean set sequence of the sample plant growth monitoring data, and feature correlation interactive fusion analysis is performed on the analysis results to obtain an interactive fusion sample plant growth feature set, including: The M adaptive convolutional network layers perform data feature extraction on the mean set sequence of the sample plant growth monitoring data according to the M receptive fields to obtain M sample plant growth feature sets, wherein the receptive field is the extraction width when the adaptive convolutional network layer performs feature extraction on the mean set sequence of the sample plant growth monitoring data; Mapping and sorting the M sample plant growth feature sets according to the order of the M receptive fields from large to small to obtain a sample plant growth feature set sequence; The sample plant growth feature sets in the sample plant growth feature set sequence are sequentially subjected to feature association interactive fusion analysis to obtain an interactively fused sample plant growth feature set.

3. The method according to claim 2, characterized in that The sample plant growth feature sets in the sample plant growth feature set sequence are sequentially subjected to feature association interactive fusion analysis to obtain an interactive fusion sample plant growth feature set, including: Performing feature correlation interaction fusion analysis on the first sample plant growth feature set and the second sample plant growth feature set of the sample plant growth feature set sequence to obtain a first correlation interaction fusion sample plant growth feature set; Extracting a third sample plant growth feature set from the sample plant growth feature set sequence, performing feature correlation interaction fusion analysis on the third sample plant growth feature set and the first correlation interaction fusion sample plant growth feature set to determine a second correlation interaction fusion sample plant growth feature set; Based on the second associated interactively fused sample plant growth feature set, feature associated interactively fused analysis is continued on the sample plant growth feature set sequence until the end of the sample plant growth feature set sequence is reached to obtain the interactively fused sample plant growth feature set.

4. The method according to claim 3, characterized in that Performing feature correlation interaction fusion analysis on the first sample plant growth feature set and the second sample plant growth feature set of the sample plant growth feature set sequence to obtain a first correlation interaction fusion sample plant growth feature set, including: Performing inner product calculation on the first sample plant growth feature set and the second sample plant growth feature set to determine a first associated interactive fusion feature similarity set; Traversing the first association interaction fusion feature similarity set to perform similarity normalization processing, and embedding the processing result into a matrix to obtain a first association interaction fusion matrix; The first association interaction fusion matrix and the second sample plant growth feature set are convolved to determine the first association interaction fusion sample plant growth feature set.

5. The method according to claim 1, characterized in that Traversing the K planting environment monitoring data set sequences to perform median analysis of the data sets within the sequences, and obtaining K planting environment monitoring data set median sets, including: Extracting a first planting environment monitoring data set sequence from the K planting environment monitoring data set sequences, wherein the first planting environment monitoring data set sequence includes a plurality of first planting environment monitoring data subsequences of a plurality of planting environment monitoring data types; Traversing the plurality of first planting environment monitoring data subsequences to perform data mean calculation, determining a plurality of first data means, taking the plurality of first data means as a plurality of concentration value analysis starting points, performing iterative analysis in the plurality of first planting environment monitoring data subsequences respectively according to a preset iteration step length, determining a plurality of first planting environment monitoring data median values, and summarizing the plurality of first planting environment monitoring data median values ​​to obtain a set of the first planting environment monitoring data median values; Performing data median analysis within the sequence on the K planting environment monitoring data set sequences to determine the median set of the K planting environment monitoring data sets.

6. The method according to claim 5, characterized in that include: Iterate the multiple concentrated value analysis starting points in the multiple first planting environment monitoring data subsequences according to the preset iteration step length to obtain multiple iteration data; Determine whether the concentration density of the multiple iterative data is greater than or equal to the concentration density of the multiple concentration value analysis starting points, and if so, update the multiple iterative data to multiple concentration value analysis starting points, and iterate in the multiple first planting environment monitoring data subsequences according to the preset iteration step size; Until the preset number of iterations is met, the plurality of first planting environment monitoring data corresponding to the plurality of iteration data obtained in the last iteration are taken as the median of the plurality of first planting environment monitoring data.

7. The method according to claim 1, characterized in that Conditional sampling is performed on the plants in the target strawberry growing area to obtain K sample plants, including: Obtaining a preset sampling number, and randomly sampling the plants in the target strawberry growth area based on the preset sampling number to obtain K random sample plants, wherein the preset sampling number is K; Enumerating the K random sample plants in pairs to obtain multiple plant enumeration combinations, and calculating the distribution position similarity of the multiple plant enumeration combinations using cosine similarity to obtain multiple position combination similarities; Determine whether the similarities of the multiple position combinations meet the preset sampling conditions. If so, use sampling authentication to take the K random sample plants as K sample plants, wherein the preset sampling condition is that the number of combinations of the multiple position combination similarities that are greater than or equal to the preset position combination similarity is less than a preset number threshold.

8. An integrated planting data management system combined with a strawberry growth and development model, characterized in that: The system is used to execute the integrated planting data management method combined with the strawberry growth and development model according to any one of claims 1 to 7, and the system comprises: A planting environment monitoring data set sequence acquisition module is used to perform conditional sampling on strawberry plants in a target strawberry growth area to obtain K sample plants, perform plant growth monitoring and planting environment monitoring on the K sample plants in a preset monitoring window, and obtain K sample plant growth monitoring data set sequences and K planting environment monitoring data set sequences, wherein K is an integer greater than or equal to 1; A data set median value set acquisition module is used to traverse the K planting environment monitoring data set sequences to perform data set median analysis within the sequences to obtain K planting environment monitoring data set median value sets; A planting environment monitoring data set median mean set acquisition module is used to perform mean processing on the same type of planting environment monitoring data in the K planting environment monitoring data set median sets, using the planting environment monitoring data type as an index, to obtain a planting environment monitoring data set median mean set; An environmental deviation factor determination module is used to determine an environmental deviation factor set according to the deviation degree between the median mean set of the planting environment monitoring data set and the preset planting environment data set, wherein the environmental deviation factor set includes M environmental deviation factors, each environmental deviation factor corresponds to a planting environment monitoring data type; A monitoring data mean set sequence acquisition module is used to perform cross-sample data mean calculation on the K sample plant growth monitoring data set sequences to obtain the sample plant growth monitoring data mean set sequence; An interactive fusion sample plant growth feature set acquisition module is used to construct M adaptive convolutional network layers based on the M environmental deviation factors, use the M adaptive convolutional network layers to perform multi-scale feature analysis on the mean set sequence of the sample plant growth monitoring data, and perform feature correlation interactive fusion analysis on the analysis results to obtain an interactive fusion sample plant growth feature set; The data management module is used to analyze the interactive fusion sample plant growth feature set using a strawberry growth and development model, determine a strawberry growth and development evaluation factor, and determine the frequency of extracting planting data for strawberry plants in the target strawberry growth area according to the size of the strawberry growth and development evaluation factor, and perform integrated planting data management according to the planting data extraction frequency.

Images