Agricultural information collection system and collection method based on big data

Abstract

The present invention provides an agricultural information collection method based on big data, which includes the following steps: collecting environmental data and current growth characteristic data of the same type of crops in multiple regions; preprocessing the environmental data and the current growth characteristic data; obtaining the correlation coefficient between the environmental data and the current growth characteristic data; constructing multiple prediction models and training the multiple prediction models using environmental data and current growth characteristic data with correlation coefficients greater than a preset coefficient value; estimating the crop yield based on the trained multiple prediction models. The present invention can comprehensively estimate the final yield of crops well, so that the final yield of crops comprehensively estimated will not have a large error with the actual final yield. Accordingly, the present invention also provides an agricultural information collection method based on big data.

Description

Technical Field

[0001] The present invention relates to the technical field of big data processing, and in particular to an agricultural information collection system and collection method based on big data. Background Art

[0002] Data information is the basis and foundation for decision-making. Agricultural data information refers to various material data and energy data involved in agricultural production or agricultural economic activities. Agricultural data information is the basis for agricultural decision-making, including agricultural production data, soil quality data, meteorological and hydrological observation data and other agricultural spatial data information.

[0003] For crops in different regions of the same longitude and latitude zone, the yields will be different due to the different planting times and regional environmental data information. By collecting and analyzing agricultural big data information, such as collecting and analyzing the soil information, environmental information and crop information itself, the yield of crops can be comprehensively estimated.

[0004] In the prior art, crop yields are generally estimated only by collecting relevant data information of crops in the same area to build a single crop yield estimation model. However, due to the limitations of relevant data information of crops in the same area, it cannot fully reflect the physiological and biochemical characteristics of crops. The estimated crop yields often have large errors compared with the final actual yields, which needs to be improved. Summary of the invention

[0005] Based on this, in order to solve the problem that the existing technology only estimates the crop yield by collecting relevant data information of crops in the same area to build a single crop yield estimation model, and the estimated crop yield often has a large error with the final actual yield, the present invention provides an agricultural information collection system and collection method based on big data, and its specific technical solution is as follows:

[0006] An agricultural information collection system based on big data comprises a big data collection module, a preprocessing module, a correlation coefficient acquisition module, a model building module and a prediction module.

[0007] The big data acquisition module is used to collect environmental data and current growth characteristic data of the same type of crops in multiple regions, and the preprocessing module is used to preprocess the environmental data and the current growth characteristic data.

[0008] The correlation coefficient acquisition module is used to obtain the correlation coefficient between the environmental data and the current growth characteristic data, and the model construction module is used to construct multiple prediction models and train the multiple prediction models using the environmental data whose correlation coefficient is greater than a preset coefficient value and the current growth characteristic data respectively.

[0009] The prediction module is used to estimate the crop yield based on the trained multiple prediction models.

[0010] The correlation coefficient represents the correlation degree between the environmental data and the current growth characteristic data of the crop. When the correlation coefficient is greater than a preset coefficient value, it indicates that there is a strong correlation between the environmental data and the current growth characteristic data.

[0011] The agricultural information collection system collects environmental data and current growth characteristic data of the same type of crops in multiple regions through a big data module, and uses the strongly correlated environmental data and the current growth characteristic data to train multiple prediction models, so that the crop yield can be estimated through multiple trained prediction models, and then the final crop yield can be comprehensively estimated using multiple estimated crop yields.

[0012] To summarize, the agricultural information collection system can make a good comprehensive estimate of the final yield of crops by constructing multiple prediction models and using the strongly correlated environmental data and the current growth characteristic data to train the multiple prediction models, so that the comprehensive estimated final yield of crops will not have a large error from the actual yield. It overcomes the problem of the prior art that crop yields are estimated by only collecting relevant data information of crops in the same area to construct a single crop yield estimation model, and the estimated crop yield often has a large error from the final actual yield.

[0013] Furthermore, the correlation coefficient acquisition module includes a first fitting curve acquisition module and a first correlation coefficient value acquisition module.

[0014] The first fitting curve acquisition module is used to fit the spatial environment parameters of different regions of the same type of crops with the corresponding current growth characteristic data of the crops to obtain a first fitting curve.

[0015] The first correlation coefficient value acquisition module is used to respectively acquire the first correlation coefficient value between the first fitting curve corresponding to the crops in any area and the first fitting curves corresponding to the crops in other areas.

[0016] Among them, the correlation coefficient includes the first correlation coefficient value, and the model building module is used to train multiple prediction models respectively using the spatial environment parameters whose first correlation coefficient value is greater than the preset coefficient value and the corresponding current growth characteristic data of the crops.

[0017] Furthermore, the correlation coefficient acquisition module also includes a second fitting curve acquisition module and a second correlation coefficient value acquisition module.

[0018] The second fitting curve acquisition module is used to fit underground soil parameters in different areas of the same type of crops with the current growth characteristic data of the corresponding crops to obtain a second fitting curve.

[0019] The second correlation coefficient value acquisition module is used to respectively acquire the second correlation coefficient value between the second fitting curve corresponding to the crops in any area and the second fitting curves corresponding to the crops in other areas.

[0020] Among them, the correlation coefficient also includes the second correlation coefficient value, and the model building module is also used to train multiple prediction models respectively using the underground soil parameters whose second correlation coefficient value is greater than the preset coefficient value and the corresponding current growth characteristic data of the crops.

[0021] Furthermore, the current growth characteristic data is the change in a certain plant part of the crop within a preset time period, and the spatial environmental parameters include the average values ​​of air temperature and humidity, the average value of light intensity, the average value of oxygen content, and the average value of carbon dioxide content.

[0022] Furthermore, the underground soil parameters include an average soil light sensitivity, an average soil temperature and humidity, and an average soil pH.

[0023] A method for collecting agricultural information based on big data comprises the following steps:

[0024] S1, collects environmental data and current growth characteristic data of the same type of crops in multiple regions.

[0025] S2, preprocessing the environmental data and the current growth characteristic data.

[0026] S4, obtaining a correlation coefficient between the environmental data and the current growth characteristic data.

[0027] S4, constructing a plurality of prediction models and using the environmental data whose correlation coefficient is greater than a preset coefficient value and the current growth characteristic data to train the plurality of prediction models.

[0028] S5, estimating crop yields based on the trained multiple prediction models.

[0029] Furthermore, the specific method for obtaining the correlation coefficient between the environmental data and the current growth characteristic data comprises the following steps:

[0030] Fitting the spatial environmental parameters of different regions of the same type of crops with the corresponding current growth characteristic data of the crops to obtain a first fitting curve;

[0031] Respectively obtaining first correlation coefficient values ​​between a first fitting curve corresponding to crops in any region and first fitting curves corresponding to crops in other regions;

[0032] Fitting underground soil parameters of different regions of the same type of crops with the corresponding current growth characteristic data of the crops to obtain a second fitting curve;

[0033] Respectively obtaining second correlation coefficient values ​​between the second fitting curve corresponding to the crops in any area and the second fitting curves corresponding to the crops in other areas;

[0034] The correlation coefficient includes the first correlation coefficient value and the second correlation coefficient value.

[0035] Furthermore, the specific method of training the prediction model using the environmental data whose correlation coefficient is greater than the preset coefficient value and the current growth characteristic data comprises the following steps:

[0036] Training the plurality of prediction models respectively using the spatial environment parameters whose first correlation coefficient values ​​are greater than a preset coefficient value and the corresponding current growth characteristic data of the crops;

[0037] The plurality of prediction models are trained respectively using the underground soil parameters whose second correlation coefficient values ​​are greater than the preset coefficient values ​​and the corresponding current growth characteristic data of the crops.

[0038] Furthermore, the current growth characteristic data is the change in a certain plant part of the crop within a preset time period, the spatial environment parameters include the average air temperature and humidity, the average light intensity, the average oxygen content and the average carbon dioxide content, and the underground soil parameters include the average soil light sensitivity, the average soil temperature and humidity, and the average soil pH.

[0039] A computer-readable storage medium stores a computer program, which implements the agricultural information collection method based on big data when executed. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The present invention can be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily drawn to scale, but the emphasis is placed on illustrating the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0041] Figure 1 It is a schematic diagram of the overall process of a method for collecting agricultural information based on big data in one embodiment of the present invention;

[0042] Figure 2It is a flowchart of a specific method for obtaining the correlation coefficient between environmental data and current growth characteristic data in one embodiment of the present invention. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with its embodiments. It should be understood that the specific implementation methods described herein are only used to explain the present invention and do not limit the scope of protection of the present invention.

[0044] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only and do not represent the only implementation method.

[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0046] The “first” and “second” mentioned in the present invention do not represent specific quantities and orders, but are merely used to distinguish names.

[0047] An agricultural information collection system based on big data in one embodiment of the present invention includes a big data collection module, a preprocessing module, a correlation coefficient acquisition module, a model construction module and a prediction module.

[0048] The big data acquisition module is used to collect environmental data and current growth characteristic data of the same type of crops in multiple regions, and the preprocessing module is used to preprocess the environmental data and the current growth characteristic data.

[0049] Specifically, the big data acquisition module can be various sensors installed in multiple areas to collect environmental data and current growth characteristic data of the same type of crops, such as image sensors, temperature and humidity sensors, light intensity sensors, etc.

[0050] The preprocessing method includes screening, filtering and noise reduction to eliminate invalid data in the environmental data and current growth characteristic data.

[0051] The correlation coefficient acquisition module is used to obtain the correlation coefficient between the environmental data and the current growth characteristic data, and the model construction module is used to construct multiple prediction models and train the multiple prediction models using the environmental data whose correlation coefficient is greater than a preset coefficient value and the current growth characteristic data respectively.

[0052] The correlation coefficient represents the correlation degree between the environmental data and the current growth characteristic data of the crop. When the correlation coefficient is greater than a preset coefficient value, it indicates that there is a strong correlation between the environmental data and the current growth characteristic data.

[0053] The environmental data include but are not limited to spatial environmental parameters and underground soil parameters; the current growth characteristic data include but are not limited to the change in a certain plant part of the crop within a preset time period; the spatial environmental parameters include but are not limited to the average air temperature and humidity, the average light intensity, the average oxygen content and the average carbon dioxide content; the underground soil parameters include but are not limited to the average soil light sensitivity, the average soil temperature and humidity and the average soil pH.

[0054] The above average value may be an average value of parameters within a preset time period, and the preset time period may be, for example, daytime, nighttime, or N consecutive hours.

[0055] A plant part includes but is not limited to roots, stems, branches, flowers and fruits of crops. Accordingly, the change amount may be an elongation amount, a contraction amount or a change rate.

[0056] By analyzing the correlation between the environmental data and the change in a certain plant part of the crop within a preset time period, and using the strongly correlated environmental data and the current growth characteristic data to train a prediction model, the growth trend of the crop can be well predicted, and the crop yield can be well predicted.

[0057] The prediction module is used to estimate the crop yield based on the trained multiple prediction models.

[0058] The agricultural information collection system collects environmental data and current growth characteristic data of the same type of crops in multiple regions through a big data module, and uses the strongly correlated environmental data and the current growth characteristic data to train multiple prediction models, so that the crop yield can be estimated through multiple trained prediction models, and then the final crop yield can be comprehensively estimated using multiple estimated crop yields.

[0059] To summarize, the agricultural information collection system can make a good comprehensive estimate of the final yield of crops by constructing multiple prediction models and using the strongly correlated environmental data and the current growth characteristic data to train the multiple prediction models, so that the comprehensive estimated final yield of crops will not have a large error from the actual yield. It overcomes the problem of the prior art that crop yields are estimated by only collecting relevant data information of crops in the same area to construct a single crop yield estimation model, and the estimated crop yield often has a large error from the final actual yield.

[0060] In one embodiment, the correlation coefficient acquisition module includes a first fitting curve acquisition module, a first correlation coefficient value acquisition module, a second fitting curve acquisition module and a second correlation coefficient value acquisition module.

[0061] The first fitting curve acquisition module is used to fit the spatial environment parameters of different regions of the same type of crops with the corresponding current growth characteristic data of the crops to obtain a first fitting curve, and the first correlation coefficient value acquisition module is used to respectively obtain the first correlation coefficient value between the first fitting curve corresponding to the crops in any region and the first fitting curve corresponding to the crops in the remaining regions.

[0062] The second fitting curve acquisition module is used to fit the underground soil parameters of different areas of the same type of crops with the corresponding current growth characteristic data of the crops to obtain a second fitting curve, and the second correlation coefficient value acquisition module is used to respectively obtain the second correlation coefficient value between the second fitting curve corresponding to the crops in any area and the second fitting curve corresponding to the crops in the remaining areas.

[0063] Among them, the first fitting curve represents a function curve between the spatial environment parameters and current growth characteristic data in each growth cycle of the crop, the correlation coefficient includes the first correlation coefficient value and the second correlation coefficient value, and the model building module is used to train multiple prediction models respectively using the spatial environment parameters whose first correlation coefficient value is greater than the preset coefficient value and the corresponding current growth characteristic data of the crop.

[0064] The model building module is also used to train the multiple prediction models using the underground soil parameters whose second correlation coefficient values ​​are greater than the preset coefficient values ​​and the corresponding current growth characteristic data of the crops.

[0065] In actual practice, due to differences in crop sowing time and spatial environmental parameters in different areas of the same longitude and latitude zone, there will also be differences in crop growth trends and crop yields. The correlation between the first fitting curves of different regions may vary greatly, that is, there may be strong correlation, weak correlation, or no correlation.

[0066] The model building module is used to train multiple prediction models using the spatial environment parameters whose first correlation coefficient value is greater than the preset coefficient value and the corresponding current growth characteristic data of the crops, respectively. The prediction model can be trained by fully utilizing the spatial environment parameters and the current growth characteristic data that have strong correlations, and the spatial environment parameters and current growth characteristic data of the same type of crops collected in multiple regions can be fully utilized to give play to the advantages of big data itself, so as to better estimate crop yields through prediction models.

[0067] The model building module is used to train multiple prediction models using the empty underground soil whose second correlation coefficient value is greater than the preset coefficient value and the corresponding current growth characteristic data of the crops, respectively. It can fully utilize the underground soil parameters and the current growth characteristic data that have strong correlation to train the prediction model, and fully utilize the underground soil parameters and current growth characteristic data of the same type of crops collected in multiple regions, give full play to the advantages of big data itself, so as to better estimate the crop yield through the prediction model.

[0068] By constructing multiple prediction models, the differences in crop sowing time and spatial environmental parameters in different regions of the same longitude and latitude zone are fully taken into account, so that the constructed multiple prediction models can make targeted predictions for crops in multiple different regions, avoiding the problem that a single prediction model cannot meet the estimation needs of crop yields in all regions and that the crop yields in different regions estimated by a single prediction model are prone to large errors compared with the actual final yields.

[0069] In one embodiment, if Figure 1 As shown, a method for collecting agricultural information based on big data includes the following steps:

[0070] S1, collects environmental data and current growth characteristic data of the same type of crops in multiple regions.

[0071] S2, preprocessing the environmental data and the current growth characteristic data.

[0072] S3, obtaining a correlation coefficient between the environmental data and the current growth characteristic data.

[0073] S4, constructing a plurality of prediction models and using the environmental data whose correlation coefficient is greater than a preset coefficient value and the current growth characteristic data to train the plurality of prediction models.

[0074] S5, estimating crop yields based on the trained multiple prediction models.

[0075] In step S1, the environmental data and current growth characteristic data of the same type of crops in multiple areas are collected by installing big data collection modules in different areas, such as various types of data sensors.

[0076] The environmental data include spatial environmental parameters and underground soil parameters. The current growth characteristic data is the change in a certain plant part of the crop within a preset time period. The spatial environmental parameters include the average air temperature and humidity, the average light intensity, the average oxygen content, and the average carbon dioxide content. The underground soil parameters include the average soil light sensitivity, the average soil temperature and humidity, and the average soil pH.

[0077] The multiple prediction models constructed may correspond to each region one by one, and at least two prediction models may be set for each region, so that the prediction models may be trained using spatial environmental parameters, underground soil parameters, and current growth characteristic data, respectively. The prediction models include but are not limited to neural networks.

[0078] Since neural networks are conventional technical means, they will not be described in detail here.

[0079] The correlation coefficient represents the correlation degree between the environmental data and the current growth characteristic data of the crop. When the correlation coefficient is greater than a preset coefficient value, it indicates that there is a strong correlation between the environmental data and the current growth characteristic data.

[0080] By analyzing the correlation between the environmental data and the change in a certain plant part of the crop within a preset time period, and using the strongly correlated environmental data and the current growth characteristic data to train a prediction model, the growth trend of the crop can be well predicted, and the crop yield can be well predicted.

[0081] By constructing multiple prediction models and using the strongly correlated environmental data and the current growth characteristic data to train the multiple prediction models, the final yield of crops can be comprehensively estimated well, so that the comprehensive estimated final yield of crops will not have a large error from the actual final yield. This overcomes the problem of the prior art of estimating crop yields by only collecting relevant data information of crops in the same area to construct a single crop yield estimation model, and the estimated crop yield often has a large error from the final actual yield.

[0082] In one embodiment, if Figure 2 As shown, the specific method for obtaining the correlation coefficient between the environmental data and the current growth characteristic data includes the following steps:

[0083] S30, fitting the spatial environment parameters of different regions of the same type of crops with the corresponding current growth characteristic data of the crops to obtain a first fitting curve.

[0084] S31, respectively obtaining first correlation coefficient values ​​between a first fitting curve corresponding to crops in any region and first fitting curves corresponding to crops in other regions.

[0085] S32, fitting underground soil parameters of different areas of the same type of crops with the corresponding current growth characteristic data of the crops to obtain a second fitting curve.

[0086] S33, respectively obtaining second correlation coefficient values ​​between the second fitting curve corresponding to the crops in any region and the second fitting curves corresponding to the crops in other regions.

[0087] The correlation coefficient includes the first correlation coefficient value and the second correlation coefficient value.

[0088] The plurality of prediction models are trained respectively using the spatial environment parameters whose first correlation coefficient value is greater than the preset coefficient value and the corresponding current growth characteristic data of the crops, and the plurality of prediction models are trained respectively using the empty underground soil whose second correlation coefficient value is greater than the preset coefficient value and the corresponding current growth characteristic data of the crops. The prediction models can be trained by making full use of the spatial environment parameters and the current growth characteristic data with strong correlation as well as the underground soil parameters and the current growth characteristic data, and by making full use of the spatial environment parameters, underground soil parameters and current growth characteristic data of the same type of crops collected in multiple regions, and by giving full play to the advantages of big data itself, so as to better estimate the crop yield through the prediction model.

[0089] In one embodiment, the specific method of training the prediction model using the environmental data with a correlation coefficient greater than a preset coefficient value and the current growth characteristic data comprises the following steps:

[0090] S40, training the plurality of prediction models respectively by using the spatial environment parameters whose first correlation coefficient values ​​are greater than a preset coefficient value and the corresponding current growth characteristic data of the crops.

[0091] S41, training the plurality of prediction models respectively by using the underground soil parameters whose second correlation coefficient values ​​are greater than a preset coefficient value and the corresponding current growth characteristic data of the crops.

[0092] In one of the embodiments, a computer-readable storage medium stores a computer program, which implements the agricultural information collection method based on big data when executed.

[0093] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0094] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. An agricultural information collection system based on big data, characterized in that: include: Big data collection module, used to collect environmental data and current growth characteristics data of the same type of crops in multiple regions; A preprocessing module, used for preprocessing the environmental data and the current growth characteristic data; A correlation coefficient acquisition module, used to acquire the correlation coefficient between the environmental data and the current growth characteristic data; A model building module, used to build multiple prediction models and train the multiple prediction models using the environmental data with correlation coefficients greater than a preset coefficient value and the current growth characteristic data respectively; A prediction module, used for estimating crop yields based on the trained multiple prediction models; The correlation coefficient acquisition module comprises: A first fitting curve acquisition module, used for fitting the spatial environment parameters of different regions of the same type of crops with the corresponding current growth characteristic data of the crops to obtain a first fitting curve; A first correlation coefficient value acquisition module, used to respectively acquire first correlation coefficient values ​​between a first fitting curve corresponding to crops in any region and first fitting curves corresponding to crops in other regions; Wherein, the correlation coefficient includes the first correlation coefficient value, and the model building module is used to respectively train the plurality of prediction models using the spatial environment parameters whose first correlation coefficient value is greater than a preset coefficient value and the corresponding current growth characteristic data of the crop; The correlation coefficient acquisition module also includes: A second fitting curve acquisition module, used for fitting underground soil parameters of different regions of the same type of crops with the current growth characteristic data of the corresponding crops to obtain a second fitting curve; A second correlation coefficient value acquisition module, used to respectively acquire second correlation coefficient values ​​between a second fitting curve corresponding to crops in any region and second fitting curves corresponding to crops in other regions; Among them, the correlation coefficient also includes the second correlation coefficient value, and the model building module is also used to train multiple prediction models respectively using the underground soil parameters whose second correlation coefficient value is greater than the preset coefficient value and the corresponding current growth characteristic data of the crops.

2. The agricultural information collection system based on big data as claimed in claim 1, characterized in that: The current growth characteristic data is the change amount of a certain plant part of the crop within a preset time period, and the spatial environment parameters include the average value of air temperature and humidity, the average value of light intensity, the average value of oxygen content and the average value of carbon dioxide content.

3. The agricultural information collection system based on big data as claimed in claim 2, characterized in that: The underground soil parameters include the average soil light sensitivity, the average soil temperature and humidity, and the average soil pH.

4. A method for collecting agricultural information based on big data, characterized in that: The steps include: S1, collects environmental data and current growth characteristic data of the same type of crops in multiple regions; S2, preprocessing the environmental data and the current growth characteristic data; S4, obtaining a correlation coefficient between the environmental data and the current growth characteristic data; S4, constructing a plurality of prediction models and using the environmental data with a correlation coefficient greater than a preset coefficient value and the current growth characteristic data to train the plurality of prediction models; S5, estimating crop yields according to the trained multiple prediction models; The specific method for obtaining the correlation coefficient between the environmental data and the current growth characteristic data comprises the following steps: Fitting the spatial environmental parameters of different regions of the same type of crops with the corresponding current growth characteristic data of the crops to obtain a first fitting curve; Respectively obtaining first correlation coefficient values ​​between a first fitting curve corresponding to crops in any region and first fitting curves corresponding to crops in other regions; Fitting underground soil parameters of different regions of the same type of crops with the corresponding current growth characteristic data of the crops to obtain a second fitting curve; Respectively obtaining second correlation coefficient values ​​between the second fitting curve corresponding to the crops in any area and the second fitting curves corresponding to the crops in other areas; Wherein, the correlation coefficient includes the first correlation coefficient value and the second correlation coefficient value; The specific method of training the prediction model using the environmental data with a correlation coefficient greater than a preset coefficient value and the current growth characteristic data comprises the following steps: Training the plurality of prediction models respectively using the spatial environment parameters whose first correlation coefficient values ​​are greater than a preset coefficient value and the corresponding current growth characteristic data of the crops; The plurality of prediction models are trained respectively using the underground soil parameters whose second correlation coefficient values ​​are greater than the preset coefficient values ​​and the corresponding current growth characteristic data of the crops.

5. The method for collecting agricultural information based on big data as claimed in claim 4, characterized in that: The current growth characteristic data is the change in a certain plant part of the crop within a preset time period. The spatial environment parameters include the average air temperature and humidity, the average light intensity, the average oxygen content, and the average carbon dioxide content. The underground soil parameters include the average soil light sensitivity, the average soil temperature and humidity, and the average soil pH.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed, implements the agricultural information collection method based on big data as described in any one of claims 4-5.

Images