An integrated cultivation management system and method for phellinus baumii

Abstract

The application discloses an integrated cultivation management system and method for Phellinus baumii, relates to the technical field of integrated cultivation management, and comprises the following steps: based on cultivation environment and growth data set, a nonlinear relationship between environmental characteristics and growth characteristics is extracted through a data mining method, and a multi-factor influence regression and prediction model is constructed; the influence degree of the environmental characteristics on the growth of Phellinus baumii is evaluated through the multi-factor influence regression and prediction model, key influencing factors are identified, and an environmental adjustment suggestion is generated; the cultivation environment is adjusted according to the environmental adjustment suggestion, the adjustment range and frequency are optimized in combination with Phellinus baumii cultivation environment data, and an optimized cultivation environment is generated; based on the optimized cultivation environment, the colonization of Phellinus baumii mycelium and the development of fruiting bodies are measured, the effect of the current cultivation environment is evaluated through statistical regression, and a cultivation management evaluation report is generated. The application optimizes the growth conditions of Phellinus baumii, and improves the cultivation efficiency and yield.

Description

Technical Field

[0001] This invention relates to the field of integrated cultivation and management technology, and in particular to an integrated cultivation and management system and method for Sanghuang (a type of medicinal mushroom). Background Technology

[0002] With advancements in environmental monitoring technology, agricultural cultivation methods, particularly for edible fungi, have also changed. The application of sensor technology, the Internet of Things, and artificial intelligence has enabled modern agriculture to gradually achieve real-time monitoring and automatic regulation of the cultivation environment. Especially for environmentally sensitive fungi like *Sanghuang*, precisely controlling factors such as temperature, humidity, and light in complex and variable environments to improve yield and quality has become a research hotspot.

[0003] Current technologies still have room for improvement in precisely optimizing cultivation environments. Existing environmental data processing methods mainly rely on traditional statistical or empirical models, lacking in-depth analysis of the nonlinear relationships between complex environmental factors, which limits the effectiveness and accuracy of optimization strategies. Furthermore, existing technologies have limited capabilities in dynamically adjusting cultivation environments. Although environmental data can be collected in real time via sensors, these methods typically lack systematic analysis of the complex correlations between different environmental characteristics, thus affecting the precise regulation and continuous optimization of the cultivation environment. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides an integrated cultivation and management method for Sanghuang (a type of medicinal mushroom) to solve the problems of insufficient precision and dynamic adjustment capability in optimizing the cultivation environment.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides an integrated cultivation and management method for *Phellinus linteus*, comprising,

[0008] Collect and preprocess the cultivation environment data of Sanghuang, extract the growth characteristics of the preprocessed cultivation environment data, and generate a cultivation environment and growth dataset.

[0009] Based on cultivation environment and growth datasets, data mining methods are used to extract the nonlinear relationship between environmental characteristics and growth characteristics, and a multi-factor influence regression and prediction model is constructed.

[0010] By using a multi-factor impact regression and prediction model, the influence of environmental characteristics on the growth of Phellinus linteus is assessed, key influencing factors are identified, and environmental adjustment suggestions are generated.

[0011] The cultivation environment was adjusted according to the environmental adjustment recommendations, and the adjustment range and frequency were optimized by combining the cultivation environment data of Sanghuang to generate the optimized cultivation environment.

[0012] Based on the optimized cultivation environment, the colonization of Phellinus linteus mycelium and the development of fruiting bodies were measured, and the effect of the current cultivation environment was evaluated through statistical regression, generating a cultivation management evaluation report.

[0013] As a preferred embodiment of the integrated cultivation and management method for Sanghuang as described in this invention, the steps of collecting Sanghuang cultivation environment data and preprocessing it, extracting the growth characteristics of the preprocessed Sanghuang cultivation environment data, and generating a cultivation environment and growth dataset are as follows.

[0014] The environmental data for the cultivation of Sanghuang includes temperature data, humidity data, light intensity data, carbon dioxide concentration data, soil moisture data, air pressure and wind speed data, precipitation data, and soil pH value.

[0015] The preprocessing includes data cleaning, format conversion, deduplication, normalization, and outlier handling;

[0016] Based on the preprocessed Sanghuang cultivation environment data, the characteristics of Sanghuang growth were extracted through correlation analysis, and a cultivation environment and growth dataset was generated.

[0017] As a preferred embodiment of the integrated cultivation and management method for Sanghuang described in this invention, the step of extracting the nonlinear relationship between the environment and growth characteristics based on the cultivation environment and growth dataset using data mining methods is as follows:

[0018] Based on the cultivation environment and growth dataset, environmental features and growth features of Sanghuang were extracted, and data standardization and normalization were performed to generate a standardized set of environmental and growth features.

[0019] Redundant features in the standardized environment and growth characteristics are removed, and features closely related to the growth of Phellinus linteus are selected to generate key predictive features.

[0020] Based on key predictive features and the nonlinear relationship between cultivation environment features and the growth of Sanghuang, a preliminary version of a multifactor regression and prediction model was constructed using data mining methods.

[0021] As a preferred embodiment of the integrated cultivation and management method for Sanghuang described in this invention, the construction of the multi-factor influence regression and prediction model refers to training and validating the initial version of the multi-factor regression and prediction model through cross-validation, and adjusting the learning rate and regularization coefficient according to the validation results to generate the multi-factor influence regression and prediction model.

[0022] As a preferred embodiment of the integrated cultivation and management method for Sanghuang as described in this invention, the steps of assessing the influence of environmental characteristics on the growth of Sanghuang through a multi-factor influence regression and prediction model, identifying key influencing factors, and generating environmental adjustment suggestions are as follows.

[0023] The cultivation environment and growth dataset were input into a multi-factor influence regression and prediction model to obtain the degree of influence of environmental characteristics on the growth of Sanghuang.

[0024] Screen environmental features whose impact exceeds the impact threshold, identify environmental features that need to be adjusted first, and obtain key influencing factors;

[0025] Based on key influencing factors and combined with the optimal growth conditions for Sanghuang, environmental parameters were optimized to generate environmental adjustment recommendations.

[0026] As a preferred embodiment of the integrated cultivation and management method for Sanghuang described in this invention, the steps for adjusting the cultivation environment according to environmental adjustment suggestions are as follows:

[0027] Based on the environmental adjustment recommendations, calculate the direction and magnitude of deviation of the cultivation environment characteristics, and generate environmental adjustment goals and directions;

[0028] Adjust the characteristics of the cultivation environment according to the environmental adjustment goals and directions, and record the adjusted environmental data.

[0029] As a preferred embodiment of the integrated cultivation and management method for Sanghuang described in this invention, the steps for optimizing the adjustment range and frequency by combining Sanghuang cultivation environment data to generate an optimized cultivation environment are as follows:

[0030] Assess whether the adjusted environmental data is suitable for the growth requirements of Sanghuang, and generate optimized adjustment range and frequency based on feedback from cultivation environment data;

[0031] Based on the optimized adjustment range and frequency, the characteristics of the cultivation environment are fine-tuned to generate an optimized cultivation environment.

[0032] As a preferred embodiment of the integrated cultivation and management method for Sanghuang described in this invention, the step of measuring the colonization of Sanghuang mycelium and the development of fruiting bodies based on the optimized cultivation environment refers to selecting multiple sampling points in the cultivation area based on the optimized cultivation environment, marking the colonization time, the initial growth stage and the maturity stage of the fruiting bodies, and generating Sanghuang growth data.

[0033] As a preferred embodiment of the integrated cultivation and management method for Sanghuang described in this invention, the steps for evaluating the effect of the current cultivation environment through statistical regression and generating a cultivation management evaluation report are as follows:

[0034] Based on the growth data of Sanghuang, the influence of the optimized cultivation environment on the growth characteristics of Sanghuang was quantified by statistical regression method, and cultivation environment effect evaluation data was generated.

[0035] The data on the effects of cultivation environment and the growth data of Sanghuang were integrated into a cultivation management assessment report.

[0036] Secondly, the present invention provides an integrated cultivation and management system for Phellinus linteus, comprising,

[0037] The data acquisition module is used to collect and preprocess the cultivation environment data of Sanghuang, extract the growth characteristics of the preprocessed cultivation environment data, and generate a cultivation environment and growth dataset.

[0038] The model building module is used to extract the nonlinear relationship between environmental features and growth features based on cultivation environment and growth datasets through data mining methods, and to build a multi-factor influence regression and prediction model.

[0039] The suggestion generation module is used to assess the impact of environmental characteristics on the growth of Sanghuang through multi-factor influence regression and prediction models, identify key influencing factors, and generate environmental adjustment suggestions.

[0040] The environment adjustment module is used to adjust the cultivation environment according to the environmental adjustment suggestions, and optimize the adjustment range and frequency by combining the cultivation environment data of Sanghuang, and generate the optimized cultivation environment.

[0041] The report generation module is used to measure the colonization of Phellinus linteus mycelium and the development of fruiting bodies based on the optimized cultivation environment, and to evaluate the effect of the current cultivation environment through statistical regression, thereby generating a cultivation management evaluation report.

[0042] The beneficial effects of this invention are as follows: a multi-factor influence regression and prediction model was constructed using data mining methods, which revealed the nonlinear relationship between environmental characteristics and the growth of Sanghuang, and generated accurate environmental adjustment suggestions; by adjusting the cultivation environment, the growth conditions of Sanghuang were optimized, and cultivation efficiency and yield were improved. Attached Figure Description

[0043] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a flowchart of an integrated cultivation and management method for Sanghuang (a type of medicinal mushroom).

[0045] Figure 2 This is a schematic diagram of an integrated cultivation and management system for Sanghuang (a type of medicinal mushroom).

[0046] Figure 3 The flowchart for constructing a multi-factor influence regression and prediction model.

[0047] Figure 4 A flowchart for environmental adjustment and optimization. Detailed Implementation

[0048] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0049] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0050] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0051] Reference Figures 1-4 This is one embodiment of the present invention, which provides an integrated cultivation and management method for Phellinus linteus, comprising the following steps:

[0052] S1: Collect Sanghuang cultivation environment data and preprocess it, extract the growth characteristics of the preprocessed Sanghuang cultivation environment data, and generate cultivation environment and growth dataset.

[0053] S1.1: Environmental data for Sanghuang cultivation includes temperature data, humidity data, light intensity data, carbon dioxide concentration data, soil moisture data, air pressure and wind speed data, precipitation data, and soil pH value;

[0054] It should be noted that temperature data is recorded in real-time by a temperature sensor to monitor changes in air temperature in the cultivation area; humidity data is monitored by a humidity sensor to monitor the water vapor content in the air; light intensity data is captured and recorded by a light sensor to capture and record changes in light intensity; and carbon dioxide concentration data is monitored by a carbon dioxide sensor to monitor the concentration of carbon dioxide in the air. Soil moisture data is measured periodically by a soil moisture sensor to measure the moisture content in the soil. Air pressure and wind speed data are recorded by air pressure sensors and wind speed sensors, respectively, and precipitation data is recorded in real-time by a rain gauge. Soil pH value is monitored by a pH sensor to monitor the acidity and alkalinity of the soil.

[0055] S1.2: Preprocessing includes data cleaning, format conversion, deduplication, normalization, and outlier handling;

[0056] It should be noted that the collected data on the cultivation environment of *Sanghuang* (a type of medicinal mushroom) underwent data cleaning to remove incomplete, erroneous, or irrelevant data records. Format conversion was performed to ensure all data sources adhered to a unified format standard for subsequent processing. Deduplication was performed to eliminate duplicate data entries, ensuring the uniqueness of the dataset. Normalization was used to map data values ​​from different sources to the same scale, preventing undue influence on the results due to significant differences in magnitude between the *Sanghuang* cultivation environment data. Outlier handling was used to identify and correct anomalous data points (e.g., temperature values ​​significantly higher or lower than normal, humidity values ​​outside the reasonable range, and soil pH values ​​deviating from the normal acidity / alkalinity range for plant growth), ensuring the accuracy and reliability of the dataset.

[0057] S1.3: Based on the preprocessed Sanghuang cultivation environment data, the characteristics of Sanghuang growth are extracted through correlation analysis to generate a cultivation environment and growth dataset.

[0058] Furthermore, based on the preprocessed Sanghuang cultivation environment data, correlation analysis was conducted to evaluate the relationship between each environmental feature and Sanghuang growth characteristics. By using the correlation coefficients between each environmental feature (such as temperature, humidity, and light intensity) and Sanghuang growth characteristics (such as mycelial colonization rate and fruiting body growth rate), environmental factors closely related to Sanghuang growth were identified. The correlation values ​​between environmental features and growth characteristics were calculated, and environmental features with strong correlations were selected. These environmental features were then extracted as inputs for growth characteristics, generating a cultivation environment and growth dataset containing both environmental and growth characteristics closely related to Sanghuang growth.

[0059] The formula for calculating the correlation value between environmental characteristics and growth characteristics is:

[0060] ;

[0061] in, This represents the correlation value between environmental characteristics and growth characteristics. The first characteristic representing environmental features One observation value, The first characteristic representing the growth of Phellinus linteus One observation value, The sample mean representing environmental characteristics. The sample mean representing the growth characteristics of Sanghuang. Indicates the number of paired observations.

[0062] S2: Based on the cultivation environment and growth dataset, the nonlinear relationship between environmental characteristics and growth characteristics is extracted through data mining methods, and a multi-factor influence regression and prediction model is constructed.

[0063] S2.1: Based on the cultivation environment and growth dataset, extract environmental features and Sanghuang growth features, and perform data standardization and normalization to generate a standardized set of environmental and growth features;

[0064] Furthermore, based on the cultivation environment and growth dataset, environmental features and Sanghuang growth features are extracted according to the field directory. A field mapping list is established with unified naming. Environmental features and Sanghuang growth features are aligned according to the timestamp and the sampling frequency is unified. Unit calibration and dimension consistency processing are performed. Missing time periods are filled by interpolation and missing marks are set for positions that cannot be filled. The center value and dispersion of environmental features and Sanghuang growth features are obtained to complete the centering and scaling processing. Based on the value range of the whole sample, interval mapping is performed on each centered feature to complete the normalization and generate a standardized environmental and growth feature set.

[0065] S2.2: Remove redundant features from the standardized environment and growth characteristics, and select features closely related to the growth of Phellinus linteus to generate key predictive features;

[0066] Furthermore, the correlation intensity of the environmental feature set in the standardized environment and growth feature set is obtained and a correlation intensity matrix is ​​generated. Based on the correlation intensity threshold (example range: 0-1, set according to the median and quantile interval of the absolute value of the Pearson correlation coefficient between the environmental feature set and the Sanghuang growth feature set), highly correlated pairs are marked. Based on the correlation stability of the Sanghuang growth feature set and the prediction error of the time window, representative environmental features are retained and redundant environmental features are deleted. Low variance environmental features in the standardized environment and growth feature set are removed. The retained environmental feature set is paired with the Sanghuang growth feature set one by one to generate an influence degree sequence and form an environmental feature influence ranking list. Coupling conflict verification is performed on the environmental feature influence ranking list. When physical coupling or collinear interference is encountered, a single representative environmental feature is selected and conflicting items are merged based on the influence degree stability and collection reliability. For the environmental feature set that passes the verification, a comprehensive score is established based on the influence degree stability, influence degree magnitude and adjustable observability, and the top few items are truncated from high to low score (example: top 500) to generate key prediction features.

[0067] S2.3: Based on key prediction features and combined with the nonlinear relationship between cultivation environment features and the growth of Sanghuang, a preliminary multi-factor regression and prediction model was constructed using data mining methods.

[0068] Furthermore, key predictive features reflecting the potential relationship between the environment and the growth of *Sanghuang* are used to model a linear relationship between each environmental feature and the growth characteristics of *Sanghuang*. Through regression analysis, the influence weights of environmental features on *Sanghuang* growth are calculated, and regression equations are generated. These regression equations predict changes in *Sanghuang* growth characteristics based on changes in environmental features. The regression coefficients are adjusted based on the input data to fit the relationship between environmental features and *Sanghuang* growth characteristics, generating an initial version of the multi-factor regression and prediction model.

[0069] The weighting formula for calculating the influence of environmental characteristics on the growth of Phellinus linteus is as follows:

[0070] ;

[0071] in, This indicates the weight of the influence of environmental characteristics on the growth of Sanghuang. Indicates the sample number is The The environmental characteristic values ​​are selected. Indicates the first The arithmetic mean of each environmental characteristic. Indicates the first The sample standard deviation of each environmental characteristic. Indicates the sample number is The growth characteristics of Phellinus linteus are taken as follows: Indicates the first The arithmetic mean of the growth characteristics of each type of Phellinus linteus. This represents the sample standard deviation of the g-th growth characteristic of *Sanghuang*. Represents the total number of samples. Indicates the total number of environmental features. Indicates the sample number is The The environmental characteristic values ​​are selected. Indicates the first The arithmetic mean of each environmental characteristic. Indicates the first The sample standard deviation of each environmental characteristic.

[0072] It should be noted that the cultivation environment characteristic sequence and the Sanghuang growth characteristic sequence are first centered and scaled to obtain a dimensionless standardized sequence. Within the standardized space, each environmental characteristic and Sanghuang growth characteristic are multiplied sample by sample and summed along the sample dimension to serve as a linear correlation measure for a single feature. The absolute value of the linear correlation measure is taken to obtain the correlation strength of a single feature. The sum of the correlation strengths of all environmental characteristics is used as a normalization factor, and the influence weight is obtained by dividing the single feature strength by the total strength. Since the correlation coefficients of each single feature contain the same sample size constant term, the common constants in the numerator and denominator can be canceled out simultaneously. Therefore, the final weight is obtained only by normalizing the sum of the absolute values ​​of the standardized products, which is equivalent to measuring the linear contribution of each environmental characteristic to the Sanghuang growth characteristics by the relative magnitude of the standardized correlation strength.

[0073] S2.4: Train and validate the initial version of the multifactor regression and prediction model through cross-validation, and adjust the learning rate and regularization coefficient according to the validation results to generate a multifactor influence regression and prediction model.

[0074] Furthermore, the cultivation environment and growth dataset is randomly divided into several equal parts. In each iteration, one part is fixed as the validation subset and the rest as the training subset. The parameters of the initial multifactor regression and prediction model are estimated on the training subset, and the prediction error and stability index are obtained on the validation subset. The average error, variance, overfitting signs, and key residual distribution of each iteration are recorded. All iteration results are summarized, and the learning rate is fine-tuned stepwise according to the error trend, and the regularization coefficient is adjusted according to the complexity penalty requirement to form several candidate hyperparameter combinations. The candidate hyperparameter combinations are substituted into the initial multifactor regression and prediction model to repeat the cross-validation process. The learning rate and regularization coefficient that achieve the best balance between prediction accuracy and generalization ability are selected. The initial multifactor regression and prediction model is retrained and finalized on the complete cultivation environment and growth dataset to generate a multifactor influence regression and prediction model.

[0075] S3: Through multi-factor impact regression and prediction models, assess the degree of influence of environmental characteristics on the growth of Phellinus linteus, identify key influencing factors, and generate environmental adjustment suggestions;

[0076] S3.1: Input the cultivation environment and growth dataset into the multi-factor influence regression and prediction model to obtain the degree of influence of environmental characteristics on the growth of Sanghuang;

[0077] Furthermore, the cultivation environment and growth datasets were mapped, calibrated, and aligned with timestamps according to the field order and unit specifications of the multi-factor influence regression and prediction model training phase. The cultivation environment and growth datasets were then batch-input into the multi-factor influence regression and prediction model to obtain baseline prediction outputs for growth characteristics such as mycelial colonization speed and fruiting body growth speed. While keeping all environmental characteristics except the target environmental characteristics unchanged, small positive and negative perturbations were performed on individual environmental characteristics within the permissible range. For each perturbation, the prediction output was re-obtained and the difference from the baseline prediction output was recorded. The differences of the same environmental characteristic under all samples and all perturbations were normalized and summarized to form a single metric. The above process was repeated sequentially for temperature data, humidity data, light intensity data, carbon dioxide concentration data, soil moisture data, air pressure and wind speed data, precipitation data, and soil pH value to generate influence results sorted by strength, thus generating the degree of influence of environmental characteristics on the growth of Sanghuang.

[0078] It should be noted that the permissible range refers to the range of values ​​that can be taken for a single environmental characteristic without violating the optimal growth conditions of Sanghuang, the adjustable range of the equipment, and the safety of cultivation, and is constrained by the statistical boundaries of the cultivation environment and growth dataset.

[0079] S3.2: Filter environmental features whose impact is higher than the impact threshold, identify environmental features that need to be adjusted first, and obtain key influencing factors;

[0080] Furthermore, using the degree of influence of environmental characteristics on the growth of Sanghuang as input, a ranking list of environmental characteristics is generated from high to low. For each environmental characteristic in the ranking list, an executable identifier is established by combining the permissible range, cultivation safety, adjustability information, and adjustment cost information, and unadjustable or restricted environmental characteristics are eliminated. For environmental characteristics with high correlation, a relevant overlap removal process is performed to retain only representative environmental characteristics (for example, when the influence of temperature data and humidity data is similar and the adjustment coupling is high, temperature data is retained). For the retained environmental characteristics, a comprehensive priority score is constructed based on the stability of the degree of influence, adjustability, and adjustment cost, and a priority adjustment list is generated according to the ranking rules (for example, the stability of the degree of influence is used as the primary ranking factor). The priority adjustment list is used to determine the environmental characteristics that need to be adjusted first and generate key influencing factors.

[0081] It should be noted that the ranking rule refers to a fixed criterion that compares factors hierarchically, with the stability of the degree of influence as the first factor, the magnitude of the degree of influence as the second factor, adjustability as the third factor, and adjustment cost as the fourth factor, and determines the priority in order of permissible range width and safety margin when the factors are the same.

[0082] S3.3: Based on key influencing factors and combined with the optimal growth conditions of Sanghuang, environmental parameters are optimized to generate environmental adjustment suggestions.

[0083] Furthermore, based on key influencing factors, the current values ​​of temperature, humidity, light intensity, carbon dioxide concentration, soil moisture, air pressure and wind speed, precipitation, and soil pH are retrieved from the cultivation environment and growth dataset. The deviation direction and magnitude of each key influencing factor relative to the target range given by the optimal growth conditions for *Sanghuang* are obtained. Within the permissible range and cultivation safety, adjustment target values ​​and adjustment step sizes are determined for each key influencing factor, and priority and execution order are assigned according to sorting rules. Coupling between temperature and humidity data, light intensity data, and soil moisture data, etc., are addressed. For key influencing factors of the relationship (reflecting the degree of linkage and interdependence between two factors under environmental changes), conflict verification is carried out (comparing the adjustment direction, deviation direction and historical linkage trend of key influencing factors). If the adjustment direction of two key influencing factors may cause mutual cancellation or excessive superposition, the execution order is rearranged according to priority and permissible range width, and the adjustment step size of the lower priority key influencing factors is reduced. For each key influencing factor, a monitoring time interval and recommended adjustment frequency are configured to form a list containing parameter name, adjustment direction, adjustment target value, adjustment step size, recommended adjustment frequency, monitoring time interval and execution order, and environmental adjustment recommendations are output.

[0084] It should be noted that the optimal growth conditions for Sanghuang refer to the set of target intervals determined based on the cultivation environment and growth data. These intervals encompass the optimal values ​​and permissible fluctuations of data such as temperature, humidity, light intensity, carbon dioxide concentration, soil moisture, soil pH, air pressure and wind speed, and precipitation, and are used as a reference standard for cultivation regulation.

[0085] S4: Adjust the cultivation environment according to the environmental adjustment suggestions, and optimize the adjustment range and frequency by combining the cultivation environment data of Sanghuang, and generate the optimized cultivation environment;

[0086] S4.1: Based on the environmental adjustment recommendations, calculate the direction and magnitude of deviation of the cultivation environment characteristics, and generate environmental adjustment targets and directions;

[0087] Furthermore, based on the environmental adjustment recommendations, the parameters of the cultivation environment feature set are read and aligned. The current value of each cultivation environment feature is extracted and compared with the target range of optimal growth conditions for Sanghuang. Under the same time index, the deviation direction and deviation magnitude of the cultivation environment feature are calculated. The deviation direction determines whether the feature value is too high or too low relative to the target range. The deviation magnitude is used to obtain the proportion of the deviation amount to the target range width, and the adjustment target value and adjustment step size for each cultivation environment feature are determined. Joint analysis is performed on parameter pairs with coupling relationships in the cultivation environment feature set. The conflict trend between adjustment directions is identified through covariance and cross-correlation coefficient. When the deviation directions show opposite or superimposed effects, the execution order is reordered according to the priority order and the permissible range width, and the adjustment step size of low-priority parameters is reduced. Based on the deviation magnitude and cultivation sensitivity of each cultivation environment feature, the recommended adjustment frequency and monitoring time interval are determined. The execution cycle is configured under the premise of ensuring environmental stability, and the environmental adjustment target and direction are generated.

[0088] The formula for calculating the direction of deviation of cultivation environment characteristics is:

[0089] ;

[0090] in, Indicates the direction of deviation from the characteristics of the cultivation environment. Indicates the first The characteristics of the cultivation environment at any time The current value, Indicates the first The lower limit of the target range for the characteristics of the cultivation environment. Indicates the first The upper limit of the target range for the characteristics of the cultivation environment.

[0091] The formula for calculating the deviation of cultivation environment characteristics is:

[0092] ;

[0093] in, This indicates the degree of deviation from the characteristics of the cultivation environment. Indicates the first The target interval width for the characteristics of the cultivation environment.

[0094] S4.2: Adjust the characteristics of the cultivation environment according to the environmental adjustment goals and directions, and record the adjusted environmental data;

[0095] Furthermore, according to the environmental adjustment goals and directions, the cultivation environment feature set is adjusted item by item. In each execution cycle, the parameter name, adjustment direction, adjustment target value, and adjustment step size in the cultivation environment feature set are extracted. The step size is adjusted to the target value successively within the permissible range. After each parameter change, the timestamp, adjustment step size, target value, and current value are recorded to generate a single adjustment record. The changing trend of the cultivation environment feature set values ​​is monitored over multiple consecutive adjustment cycles. The fluctuation range and reversal of the changing trend are statistically analyzed. If the fluctuation exceeds the permissible range defined by the environmental adjustment goals and directions, the adjustment step size is reduced and the adjustment interval is extended. If the deviation direction remains consistent and the deviation magnitude does not decrease, the adjustment step size is increased to accelerate convergence. In the case of coupling relationships between parameter pairs, interactive checks are performed on the interrelated parameters in the cultivation environment feature set. When the adjustment directions of parameter pairs are opposite or the superposition effect is too strong, they are reordered according to priority and the magnitude of low-priority parameters is corrected to generate adjusted environmental data.

[0096] S4.3: Evaluate whether the adjusted environmental data is suitable for the growth requirements of Sanghuang, and generate optimized adjustment range and frequency based on feedback from cultivation environment data;

[0097] Furthermore, the adjusted environmental data and cultivation environment data are aligned by timestamp. The mean, variance, and trend of the set of cultivation environment features within the same monitoring period are compared with the target range of optimal growth conditions for Sanghuang. This determines whether each cultivation environment feature operates stably within the target range. If the number of deviations from the target range within a continuous monitoring period exceeds the deviation threshold (example range: 0-1, determined by the quantile median of the normalized deviation amplitude mean of the cultivation environment feature from the target range), it is recorded as an environmental mismatch. A deviation sequence is generated, and the concentration interval and fluctuation intensity of the deviation distribution are analyzed. Based on the feedback from the cultivation environment data, the optimization direction is determined according to the statistical characteristics of the deviation amplitude, fluctuation intensity, and deviation direction. For cultivation environment features with low fluctuation intensity and large deviation amplitude, the adjustment amplitude is increased and the adjustment period is shortened. For cultivation environment features with high fluctuation intensity or repeated changes in direction, the adjustment amplitude is reduced and the adjustment period is extended. For cultivation environment features with coupling relationships, the adjustment step size is synchronously corrected based on the covariance results to avoid mutual interference. Optimized adjustment amplitude and frequency are generated.

[0098] S4.4: Based on the optimized adjustment amplitude and frequency, fine-tune the characteristics of the cultivation environment to generate the optimized cultivation environment.

[0099] Furthermore, based on the optimized adjustment amplitude and frequency, continuous fine-tuning operations are performed on the cultivation environment feature set. Within each monitoring cycle, the difference between the current value of the cultivation environment feature set and the target value for environmental adjustment is read. The step size for each adjustment is determined according to the optimized adjustment amplitude, and the adjustment interval is set according to the optimized adjustment frequency. Small increases and decreases are performed on each cultivation environment feature set. After each fine-tuning, the time index, adjustment step size, adjustment direction, and adjusted parameter values ​​are recorded. The changes in the deviation direction and the stabilization time after adjustment are also obtained. When the deviation amplitude shows a decreasing trend and the deviation direction remains consistent, the existing step size is maintained. When the deviation amplitude fluctuates or reverses, the step size is reduced and the interval is extended. For cultivation environment feature sets with coupling relationships, their mutual influence is monitored synchronously. By comparing the adjustment directions and value change trends of the two in real time, if mutual cancellation or superposition exceeding the permissible range is found, the execution order is adjusted according to priority, and the adjustment amplitude of lower priority features is corrected. Within a complete observation cycle, the fine-tuning records of all cultivation environment feature sets are uniformly summarized and subjected to consistency verification. Abnormal and duplicate records are removed, generating the optimized cultivation environment.

[0100] S5: Based on the optimized cultivation environment, measure the colonization of Phellinus linteus mycelium and the development of fruiting bodies, and evaluate the effect of the current cultivation environment through statistical regression to generate a cultivation management evaluation report.

[0101] S5.1: Based on the optimized cultivation environment, multiple sampling points are selected in the cultivation area to mark the planting time, initial growth stage and maturity stage of Sanghuang fruiting body, and generate Sanghuang growth data.

[0102] Furthermore, in the optimized cultivation environment, multiple sampling points covering different microenvironments were set up within the cultivation area according to differences in terrain, shading, and substrate moisture. Each sampling point was assigned a unique number and location description. An observation schedule was established, and the sampling point number and observer information were recorded with a timestamp at each observation. The moment when the mycelium formed a continuous cover on the cultivation substrate surface was recorded as the planting time, and textual descriptions of the mycelial coverage range, density, and color grade were added. After the planting time, the initial growth stage marker events and corresponding start and end times of the fruiting bodies were recorded in chronological order, and the maturity stage marker events and corresponding start and end times of the fruiting bodies were continuously recorded. Simultaneously, textual quantitative descriptions of changes in fruiting body size, quantity, and growth rate were recorded. The sampling point number, timestamp, planting time, the start and end times of the initial growth stage of the fruiting bodies, the start and end times of the maturity stage of the fruiting bodies, and the morphological descriptions related to growth were integrated into a structured record and summarized in chronological order as Sanghuang growth data.

[0103] S5.2: Based on the growth data of Sanghuang, the influence of the optimized cultivation environment on the growth characteristics of Sanghuang is quantified by statistical regression method, and cultivation environment effect evaluation data is generated.

[0104] Furthermore, based on the growth data of *Sanghuang*, and aligned with the optimized cultivation environment's temperature, humidity, light intensity, carbon dioxide concentration, soil moisture, air pressure and wind speed, precipitation, and soil pH values ​​according to timestamps, and with missing data processing, the mycelial colonization rate, fruiting body growth rate, and fruiting body quantity in the *Sanghuang* growth data were established as a list of response variables. Various environmental characteristics in the optimized cultivation environment were established as a list of explanatory variables. Statistical regression methods were used to establish mapping relationships and output the influence direction, influence intensity, and interval uncertainty expression for each explanatory variable. The stability test and error measurement summary of the residual sequence obtained by the statistical regression method were performed. Interaction sensitivity checks were performed on easily coupled features such as temperature and humidity data, light intensity data, and soil moisture data, and interaction effect notes were recorded. The environmental feature names, influence directions, influence intensity, interval uncertainty, error measurement, and interaction effect notes were summarized as structured fields to generate cultivation environment effect evaluation data.

[0105] S5.3: Integrate the cultivation environment effect assessment data with the Sanghuang growth data into a cultivation management assessment report.

[0106] Furthermore, the cultivation environment effect assessment data and Sanghuang growth data were aligned and calibrated using unified timestamps, sampling locations, and sampling batches. A list of correspondences between environmental characteristics and Sanghuang growth characteristics was established. Based on the influence direction, influence intensity, interval uncertainty, and interactive influence notes in the cultivation environment effect assessment data, the target interval compliance rate, deviation magnitude statistics, and out-of-bounds duration were obtained for the mycelial colonization speed, fruiting body growth speed, and fruiting body quantity in the Sanghuang growth data. The environmental characteristics were then sorted by influence intensity to determine their contribution. Interactive influence summaries were generated for coupled items such as temperature and humidity data, and light intensity and soil moisture data. For each environmental characteristic, a description of the gap with the optimal growth conditions for Sanghuang and key management points were provided. A structured text containing data source descriptions, observation time ranges, indicator definitions, sub-item descriptions of influence results, interactive influence summaries, priority adjustment lists, and monitoring time arrangements was formed. Tabular entries for parameter names, target intervals, deviation directions, deviation magnitudes, and suggested adjustment frequencies were also included. This information was integrated into a cultivation management assessment report and output as such.

[0107] This embodiment also provides an integrated cultivation and management system for Phellinus linteus, including:

[0108] The data acquisition module is used to collect and preprocess the cultivation environment data of Sanghuang, extract the growth characteristics of the preprocessed cultivation environment data, and generate a cultivation environment and growth dataset.

[0109] The model building module is used to extract the nonlinear relationship between environmental features and growth features based on cultivation environment and growth datasets through data mining methods, and to build a multi-factor influence regression and prediction model.

[0110] The suggestion generation module is used to assess the impact of environmental characteristics on the growth of Sanghuang through multi-factor influence regression and prediction models, identify key influencing factors, and generate environmental adjustment suggestions.

[0111] The environment adjustment module is used to adjust the cultivation environment according to the environmental adjustment suggestions, and optimize the adjustment range and frequency by combining the cultivation environment data of Sanghuang, and generate the optimized cultivation environment.

[0112] The report generation module is used to measure the colonization of Phellinus linteus mycelium and the development of fruiting bodies based on the optimized cultivation environment, and to evaluate the effect of the current cultivation environment through statistical regression, thereby generating a cultivation management evaluation report.

[0113] In summary, this invention utilizes data mining methods to construct a multi-factor influence regression and prediction model, revealing the nonlinear relationship between environmental characteristics and the growth of *Sanghuang* (a type of medicinal mushroom), and generating precise environmental adjustment suggestions. By adjusting the cultivation environment, the growth conditions of *Sanghuang* are optimized, improving cultivation efficiency and yield.

[0114] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An integrated cultivation and management method for Phellinus linteus, characterized in that: include, Collect and preprocess the cultivation environment data of Sanghuang, extract the growth characteristics of the preprocessed cultivation environment data, and generate a cultivation environment and growth dataset. Based on cultivation environment and growth datasets, data mining methods were used to extract the nonlinear relationship between environmental characteristics and growth characteristics, and a multi-factor influence regression and prediction model was constructed. The steps are as follows. Based on the cultivation environment and growth dataset, environmental features and growth features of Sanghuang were extracted, and data standardization and normalization were performed to generate a standardized set of environmental and growth features. Redundant features in the standardized environment and growth characteristics are removed, and features closely related to the growth of Phellinus linteus are selected to generate key predictive features. Based on key predictive features and the nonlinear relationship between cultivation environment features and the growth of Sanghuang, a preliminary version of a multifactor regression and prediction model was constructed using data mining methods. Furthermore, key predictive features that can reflect the potential relationship between the environment and the growth of Sanghuang are used to model the linear relationship between each environmental feature and the growth characteristics of Sanghuang. Through regression analysis, the influence weight of environmental features on the growth of Sanghuang is calculated, and a regression equation is generated. The regression equation predicts the changes in the growth characteristics of Sanghuang based on the changes in environmental features. The regression coefficients are adjusted according to the input data to fit the relationship between environmental features and the growth characteristics of Sanghuang, generating an initial version of the multi-factor regression and prediction model. The weighting formula for calculating the influence of environmental characteristics on the growth of Phellinus linteus is as follows: ； The initial version of the multifactor regression and prediction model was trained and validated through cross-validation. The learning rate and regularization coefficient were adjusted based on the validation results to generate a multifactor influence regression and prediction model. The impact of environmental characteristics on the growth of *Phellinus linteus* was assessed using a multi-factor regression and prediction model. Key influencing factors were identified, and environmental adjustment recommendations were generated. The steps are as follows. The cultivation environment and growth dataset were input into a multi-factor influence regression and prediction model to obtain the degree of influence of environmental characteristics on the growth of Sanghuang. Screen environmental features whose impact exceeds the impact threshold, identify environmental features that need to be adjusted first, and obtain key influencing factors; Based on key influencing factors and combined with the optimal growth conditions of Phellinus linteus, environmental parameters were optimized to generate environmental adjustment suggestions. The cultivation environment was adjusted according to the environmental adjustment recommendations. The adjustment range and frequency were optimized based on the data from the Sanghuang cultivation environment to generate the optimized cultivation environment. The steps are as follows. Based on the environmental adjustment recommendations, calculate the direction and magnitude of deviation of the cultivation environment characteristics, and generate environmental adjustment goals and directions; The formula for calculating the direction of deviation of cultivation environment characteristics is: ； in, Indicates the direction of deviation from the characteristics of the cultivation environment. Indicates the first The characteristics of the cultivation environment at any time The current value, Indicates the first The lower limit of the target range for the characteristics of the cultivation environment. Indicates the first Upper limit of the target range for the characteristics of the cultivation environment; The formula for calculating the deviation of cultivation environment characteristics is: ； in, This indicates the degree of deviation from the characteristics of the cultivation environment. Indicates the first The target interval width for the characteristics of the cultivation environment; Adjust the characteristics of the cultivation environment according to the environmental adjustment goals and directions, and record the environmental data after adjustment; Based on the optimized cultivation environment, the colonization of Phellinus linteus mycelium and the development of fruiting bodies were measured, and the effect of the current cultivation environment was evaluated through statistical regression, generating a cultivation management evaluation report.

2. The integrated cultivation and management method for *Sanghuang* as described in claim 1, characterized in that: The steps for collecting and preprocessing the cultivation environment data of *Sanghuang* (a type of medicinal mushroom), extracting the growth characteristics of the preprocessed cultivation environment data, and generating a cultivation environment and growth dataset are as follows. The environmental data for the cultivation of Sanghuang includes temperature data, humidity data, light intensity data, carbon dioxide concentration data, soil moisture data, air pressure and wind speed data, precipitation data, and soil pH value. The preprocessing includes data cleaning, format conversion, deduplication, normalization, and outlier handling; Based on the preprocessed Sanghuang cultivation environment data, the characteristics of Sanghuang growth were extracted through correlation analysis, and a cultivation environment and growth dataset was generated.

3. The integrated cultivation and management method for *Sanghuang* as described in claim 1, characterized in that: The optimization of the adjustment range and frequency by combining data from the Sanghuang cultivation environment to generate the optimized cultivation environment is described in the following steps. Assess whether the adjusted environmental data is suitable for the growth requirements of Sanghuang, and generate optimized adjustment range and frequency based on feedback from cultivation environment data; Based on the optimized adjustment range and frequency, the characteristics of the cultivation environment are fine-tuned to generate an optimized cultivation environment.

4. The integrated cultivation and management method for *Sanghuang* as described in claim 3, characterized in that: The measurement of the colonization of Phellinus linteus mycelium and the development of fruiting bodies based on the optimized cultivation environment refers to selecting multiple sampling points in the cultivation area based on the optimized cultivation environment, marking the colonization time, the initial growth stage and the maturity stage of the fruiting bodies, and generating Phellinus linteus growth data.

5. The integrated cultivation and management method for *Sanghuang* as described in claim 4, characterized in that: The steps for evaluating the effectiveness of the current cultivation environment through statistical regression and generating a cultivation management evaluation report are as follows. Based on the growth data of Sanghuang, the influence of the optimized cultivation environment on the growth characteristics of Sanghuang was quantified by statistical regression method, and cultivation environment effect evaluation data was generated. The data on the effects of cultivation environment and the growth data of Sanghuang were integrated into a cultivation management assessment report.

6. An integrated cultivation and management system for *Sanghuang*, based on the integrated cultivation and management method for *Sanghuang* according to any one of claims 1 to 5, characterized in that: include, The data acquisition module is used to collect and preprocess the cultivation environment data of Sanghuang, extract the growth characteristics of the preprocessed cultivation environment data, and generate a cultivation environment and growth dataset. The model building module is used to extract the nonlinear relationship between environmental features and growth features based on cultivation environment and growth datasets through data mining methods, and to build a multi-factor influence regression and prediction model. The suggestion generation module is used to assess the impact of environmental characteristics on the growth of Sanghuang through multi-factor influence regression and prediction models, identify key influencing factors, and generate environmental adjustment suggestions. The environment adjustment module is used to adjust the cultivation environment according to the environmental adjustment suggestions, and optimize the adjustment range and frequency by combining the cultivation environment data of Sanghuang, and generate the optimized cultivation environment. The report generation module is used to measure the colonization of Phellinus linteus mycelium and the development of fruiting bodies based on the optimized cultivation environment, and to evaluate the effect of the current cultivation environment through statistical regression, thereby generating a cultivation management evaluation report.

Images