Intelligent monitoring method, device and storage medium for highland barley planting

Abstract

The present application discloses an intelligent monitoring method, device and storage medium for highland barley planting, including: determining a target area and a plurality of first parameter types corresponding to the target area; collecting parameter values ​​corresponding to each first parameter type and the first highland barley planting yield in each historical planting cycle, and constructing a plurality of first feature vectors based on the parameter values ​​corresponding to each first parameter type and the first highland barley planting yield; determining one or more second parameter types based on a model determined by a pre-set factor and a plurality of first feature vectors; collecting parameter values ​​corresponding to each second parameter type in the current planting cycle, and constructing a second feature vector based on the parameter values ​​corresponding to each second parameter type; and monitoring the second highland barley planting yield in the target area using a pre-set yield warning model and based on the second feature vector. Thus, the accuracy of the monitoring and warning results of highland barley planting yield can be improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent monitoring technology, and in particular to an intelligent monitoring method, device and storage medium for barley planting. Background Art

[0002] Crop yield monitoring has always been valued by all walks of life. And crop yield monitoring information has long become an indispensable and important basis for formulating food-related policies and economic plans.

[0003] Because highland barley is cold-resistant, drought-resistant and has strong stress resistance, it is one of the important crops in my country. In recent years, there are more and more intelligent monitoring methods for highland barley planting, but the existing intelligent monitoring methods for highland barley planting usually do not change due to regional characteristics. For example, Qinghai Province has a higher terrain and has the characteristics of low temperature, large temperature difference between day and night, less and concentrated rainfall, and strong solar radiation. Some parts of Sichuan have lower terrain and are characterized by dry winter, rainy summer and more night rain. Therefore, although both Qinghai Province and Sichuan Province grow highland barley, due to the different factors affecting the highland barley yield in the two regions, the highland barley yield in the two regions is naturally different.

[0004] As mentioned above, although the factors affecting highland barley yield are different in different regions, the existing intelligent monitoring methods for highland barley planting usually do not change due to regional characteristics. Therefore, if the existing intelligent monitoring methods are still used to monitor the highland barley planting yield (for example, using the same intelligent monitoring model to monitor the highland barley planting yield in different regions), it may lead to a decrease in the accuracy of the final monitoring and early warning results.

[0005] The publication number is CN118760815A, and the name is a modern agricultural Ganoderma lucidum stress resistance planting state monitoring method, terminal and medium. Specifically, it includes determining the growth characteristic standard of Ganoderma lucidum, collecting and monitoring the growth characteristic information of Ganoderma lucidum, and collecting the growth rate information of Ganoderma lucidum through the growth status of Ganoderma lucidum at different time points, obtaining the growth status of Ganoderma lucidum in real time, and quantifying the growth status of Ganoderma lucidum through the growth status evaluation coefficient of Ganoderma lucidum, determining the impact of harmful microorganisms in the soil on Ganoderma lucidum planting through the Logistic regression model, and evaluating the stress resistance of Ganoderma lucidum planting environment by monitoring the pH value of Ganoderma lucidum soil, obtaining the impact of soil pH value on Ganoderma lucidum planting, and monitoring the status of Ganoderma lucidum at different growth stages through training neural network model.

[0006] The publication number is CN115662513A, and the name is a method for dynamically monitoring plant growth and development, comprising: obtaining two groups of single-cell transcriptome data, wherein the first group of data is a control group, and the second group of data is a change group, which correspond to different developmental stages respectively; constructing a virtual cell state matrix of the second group of data at the developmental stage corresponding to the control group through singular value analysis; obtaining the state change response characteristics of the single cells corresponding to the second group of data between different developmental stages; and clustering the single cells using the state change response characteristics.

[0007] There is no effective solution to the technical problem in the above-mentioned prior art that although the factors affecting the barley yield in different regions are different, the accuracy of the final monitoring and early warning results is reduced because the impact of the characteristics of different regions on the barley planting yield is not taken into account. Summary of the invention

[0008] The embodiments of the present disclosure provide an intelligent monitoring method, device and storage medium for highland barley planting, so as to at least solve the technical problem in the prior art that although the factors affecting highland barley yield in different regions are different, the accuracy of the final monitoring and early warning results is reduced because the influence of the characteristics of different regions on the highland barley planting yield is not taken into account.

[0009] According to one aspect of an embodiment of the present disclosure, an intelligent monitoring method for highland barley planting is provided, including: determining a target area and a plurality of first parameter types corresponding to the target area, wherein the first parameter type is used to indicate the type of influencing factors affecting the highland barley planting yield; collecting parameter values ​​corresponding to each first parameter type and the first highland barley planting yield in each historical planting cycle, and constructing a plurality of first feature vectors based on the parameter values ​​corresponding to each first parameter type and the first highland barley planting yield; determining one or more second parameter types using a preset factor determination model and based on the plurality of first feature vectors, wherein the second parameter type corresponds to the target area; collecting parameter values ​​corresponding to each second parameter type in the current planting cycle, and constructing a second feature vector based on the parameter values ​​corresponding to each second parameter type; and monitoring the second highland barley planting yield of the target area using a preset yield warning model and based on the second feature vector.

[0010] According to another aspect of an embodiment of the present disclosure, a storage medium is further provided, the storage medium including a stored program, wherein when the program is running, a processor executes any one of the methods described above.

[0011] According to another aspect of the embodiment of the present disclosure, an intelligent monitoring device for highland barley planting is also provided, including: a first parameter type determination module, used to determine a target area and multiple first parameter types corresponding to the target area, wherein the first parameter type is used to indicate the type of influencing factors affecting the highland barley planting yield; a first feature vector construction module, used to collect parameter values ​​corresponding to each first parameter type and the first highland barley planting yield in each historical planting cycle, and construct multiple first feature vectors based on the parameter values ​​corresponding to each first parameter type and the first highland barley planting yield; a second parameter type determination module, used to determine one or more second parameter types based on a preset factor determination model and multiple first feature vectors, wherein the second parameter type corresponds to the target area; a second feature vector construction module, used to collect parameter values ​​corresponding to each second parameter type in the current planting cycle, and construct a second feature vector based on the parameter values ​​corresponding to each second parameter type; and a yield monitoring module, used to monitor the second highland barley planting yield of the target area based on the second feature vector using a preset yield warning model.

[0012] According to another aspect of the embodiment of the present disclosure, an intelligent monitoring device for highland barley planting is also provided, including: a processor; and a memory, connected to the processor, for providing the processor with instructions for processing the following processing steps: determining a target area and a plurality of first parameter types corresponding to the target area, wherein the first parameter type is used to indicate the type of influencing factors affecting the highland barley planting yield; collecting parameter values ​​corresponding to each first parameter type and the first highland barley planting yield in each historical planting cycle, and constructing a plurality of first feature vectors based on the parameter values ​​corresponding to each first parameter type and the first highland barley planting yield; determining one or more second parameter types using a preset factor determination model and based on the plurality of first feature vectors, wherein the second parameter type corresponds to the target area; collecting parameter values ​​corresponding to each second parameter type in the current planting cycle, and constructing a second feature vector based on the parameter values ​​corresponding to each second parameter type; and monitoring the second highland barley planting yield in the target area using a preset yield warning model and based on the second feature vector.

[0013] The present application provides an intelligent monitoring method for highland barley planting. First, the processor determines a target area and a plurality of first parameter types corresponding to the target area. Then, the processor collects parameter values ​​corresponding to each first parameter type and the first highland barley planting yield in each historical planting cycle, and constructs a plurality of first feature vectors based on the parameter values ​​corresponding to each first parameter type and the first highland barley planting yield. Further, the processor determines one or more second parameter types based on a plurality of first feature vectors using a pre-set factor determination model. Thereafter, the processor collects parameter values ​​corresponding to each second parameter type in the current planting cycle, and constructs a second feature vector based on the parameter values ​​corresponding to each second parameter type. Finally, the processor monitors the second highland barley planting yield in the target area using a pre-set yield warning model and based on the second feature vector.

[0014] Referring to the above-mentioned contents, it can be known that, in the case of determining the target area and multiple first parameter types corresponding to the target area, the present application does not directly use multiple first parameter types to predict the barley planting yield of the current planting cycle (i.e., the second barley planting yield), but first uses a preset factor determination model to determine the second parameter type among the multiple first parameter types, and uses the second parameter type to predict the barley planting yield of the current planting cycle. The second parameter type is used to indicate the influencing factors among the multiple first parameter types that have a higher degree of influence on the barley planting yield of the target area. That is, each second parameter type corresponds to the characteristics of the target area.

[0015] That is to say, when the second parameter type is determined, the parameter value corresponding to the current planting cycle and the second parameter type is obtained, and the obtained parameter value is input into a preset yield warning model, so that the yield warning model can output the barley planting yield level of the current planting cycle, and issue a warning when the barley planting yield level is lower than the preset yield level threshold.

[0016] Therefore, different from the prior art, the present application selects the influencing factors that most affect the barley planting yield of the target area from multiple influencing factors based on the characteristics of the target area, and monitors the barley planting yield of the target area based on the influencing factors that most affect the barley planting yield of the target area, thereby improving the accuracy of the monitoring and early warning results of the barley planting yield.

[0017] This solves the technical problem in the prior art that, although the factors affecting highland barley yield in different regions are different, the accuracy of the final monitoring and early warning results is reduced because the influence of the characteristics of different regions on the highland barley planting yield is not taken into account. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of the present application. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure. In the drawings:

[0019] Figure 1 is a hardware structure block diagram of a computing device for implementing the method according to Embodiment 1 of the present disclosure;

[0020] Figure 2 It is a modular schematic diagram of the intelligent monitoring system for highland barley planting according to Example 1 of the present application;

[0021] Figure 3 It is a flow chart of the intelligent monitoring method for highland barley planting according to Example 1 of the present application;

[0022] Figure 4 is a schematic diagram of a model determined according to the factors described in Example 1 of the present application;

[0023] Figure 5 This is a modular schematic diagram of the intelligent monitoring device for highland barley planting according to Example 2 of the present application;

[0024] Figure 6 It is a modular schematic diagram of the intelligent monitoring device for highland barley planting described in Example 3 of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only embodiments of a part of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0027] Example 1

[0028] According to this embodiment, a method embodiment of intelligent monitoring of highland barley planting is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0029] The method embodiment provided in this embodiment can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Figure 1 The hardware structure block diagram of a computing device for realizing intelligent monitoring of highland barley planting is shown. Figure 1 As shown, the computing device may include one or more processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory for storing data, a transmission device for communication functions, and an input / output interface. The memory, the transmission device, and the input / output interface are connected to the processor via a bus. In addition, it may also include: a display, a keyboard, and a cursor control device connected to the input / output interface. A person skilled in the art can understand that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0030] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computing device. As involved in the embodiments of the present disclosure, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0031] The memory can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the intelligent monitoring method for highland barley planting in the embodiment of the present disclosure. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, the intelligent monitoring method for highland barley planting of the above-mentioned application program is realized. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computing device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0032] The transmission device is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computing device. In one example, the transmission device includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0033] The display may be, for example, a touch screen liquid crystal display (LCD) that may enable a user to interact with a user interface of the computing device.

[0034] It should be noted that, in some optional embodiments, the above Figure 1 The computing device shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware elements and software elements. Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computing devices described above.

[0035] Figure 2 Schematic diagram of the intelligent monitoring system for highland barley planting according to this embodiment. Figure 2As shown, the system includes: a data acquisition module, a model building module, a parameter type determination module and a monitoring and early warning module. The data acquisition module is used to determine multiple first parameter types corresponding to the target area, and collect parameter values ​​corresponding to each first parameter type in the historical planting cycle, as well as the highland barley planting yield in the historical planting cycle (i.e., the first highland barley planting yield). The model building module is used to construct a factor determination model. The parameter type determination module is used to determine one or more second parameter types using the factor determination model and based on multiple first eigenvectors. The multiple first eigenvectors correspond to the parameter values ​​corresponding to each first parameter type collected by the data acquisition module and the first highland barley planting yield. And the second parameter type is used to indicate the type of influencing factors that conform to the characteristics of the target area.

[0036] The data acquisition module is also used to collect parameter values ​​corresponding to each second parameter type in the current planting cycle based on one or more second parameter types. The model building module is also used to build a yield warning model. The monitoring module is used to monitor and warn the highland barley planting yield (i.e., the first highland barley planting yield) of the target area in the current planting cycle using the yield warning model and based on the second eigenvector. The second eigenvector corresponds to the parameter values ​​of each second parameter type collected by the data acquisition module.

[0037] Under the above operating environment, according to the first aspect of this embodiment, a method for intelligent monitoring of highland barley planting is provided. Figure 2 The system implementation shown in . Figure 3 A schematic diagram showing the process of the method is shown in FIG. Figure 3 As shown, the method includes:

[0038] S302: Determine a target area and a plurality of first parameter types corresponding to the target area, wherein the first parameter type is used to indicate the type of influencing factors affecting highland barley planting yield;

[0039] S304: collecting parameter values ​​corresponding to each first parameter type and the first highland barley planting yield in each historical planting cycle, and constructing a plurality of first feature vectors based on the parameter values ​​corresponding to each first parameter type and the first highland barley planting yield;

[0040] S306: Determine one or more second parameter types by using a preset factor determination model and based on a plurality of first feature vectors, wherein the second parameter type corresponds to the target area;

[0041] S308: collecting parameter values ​​corresponding to each second parameter type in the current planting cycle, and constructing a second feature vector based on the parameter values ​​corresponding to each second parameter type; and

[0042] S310: Using a preset yield warning model and based on a second eigenvector, the second highland barley yield in the target area is monitored.

[0043] Specifically, first, the data acquisition module determines the target area and multiple first parameter types corresponding to the target area (S302). Among them, the first parameter type is used to indicate the type of influencing factors that affect the yield of highland barley cultivation. For example, if it is necessary to use the above-mentioned intelligent monitoring system to monitor and warn a certain area, the data acquisition module determines the area as the target area. Then, the data acquisition module can crawl the first parameter type corresponding to the target area from the network, or determine the first parameter type corresponding to the target area based on the data stored in the database. Among them, the first parameter type includes air temperature, soil moisture, longitude, latitude, elevation, moisture, light and wind conditions, etc. Those skilled in the art should understand that the above is just an example of the first parameter type, and the actual situation is not limited to this.

[0044] Then, the data collection module collects the parameter values ​​corresponding to each first parameter type and the first highland barley planting yield in each historical planting cycle, and constructs multiple first feature vectors based on the parameter values ​​corresponding to each first parameter type and the first highland barley planting yield (S304). Specifically, when the data collection module determines multiple first parameter types of the target area, further determine each historical period T1~T m In the first parameter type, the parameter values ​​x1~x n And each historical period T1~T m The barley production in the area is Q1~Q m (i.e., the first highland barley planting yield). For example, the parameter values ​​x1~x1 of the first parameter type corresponding to the historical period T1 n and the highland barley planting yield Q1 corresponding to the historical period T1; the parameter values ​​x1~x1 of the first parameter type corresponding to the historical period T2 n and the barley production Q2 corresponding to the historical period T2; ...; and the historical period T m The corresponding parameter value x1~x of the first parameter type n and the historical period T m The corresponding highland barley yield Q m .

[0045] Therefore, each historical period T1~T m The parameter values ​​x1~x corresponding to each first parameter type n , and each historical period T1~T m The barley production in the area is Q1~Q m In the case of , multiple first eigenvectors F1~F can be further constructedm .For example, , , ..., .

[0046] Furthermore, the data acquisition module determines the first plurality of feature vectors F1 to F m The parameter type determination module then determines the model based on the factors pre-trained by the model building module and the first feature vectors F1~F m , determine one or more second parameter types y1~y k (S306). Figure 4 Schematic diagram of a factor determination model according to an embodiment of the present application. Figure 4 As shown, the factor determination model includes a self-attention model, a fully connected layer, and n softmax classifiers. It is worth noting that in the embodiment of the present application, since there are n first parameter types, softmax classifiers corresponding to the n first parameter types are set respectively to output the first probability values ​​H corresponding to the n first parameter types. 11 ~H n1 and the second probability value H 12 ~H n2 . And the self-attention model in the factor determination model can determine the correlation between the first parameter type in each first feature vector and the corresponding highland barley planting yield.

[0047] Thus, the parameter type determination module converts the first feature vectors F1~F m When input into the factor determination model, the final n softmax classifiers can output the first probability value H corresponding to each first parameter type. 11 ~H n1 and the second probability value H 12 ~H n2 Among them, the first probability value H 11 ~H n1 represents the probability of selecting the corresponding first parameter type, and the second probability value H 12 ~H n2 represents the probability of not selecting the corresponding first parameter type. And the first probability value H 11 ~H n1 and the second probability value H 12 ~H n2 Indicates the influence of the corresponding first parameter type on the highland barley yield in the target area. That is, the first probability value H 11 ~H n1 The larger the second probability value H 12 ~H n2The smaller the value, the greater the impact of the corresponding first parameter type on the highland barley yield in the target area; the first probability value H 11 ~H n1 The smaller the second probability value H 12 ~H n2 The larger the value is, the smaller the impact of the corresponding first parameter type on the barley planting yield in the target area is.

[0048] Furthermore, the parameter type determination module determines the first probability value H corresponding to each first parameter type. 11 ~H n1 and the second probability value H 12 ~H n2 In the case of 11 ~H n1 and the pre-set probability threshold H l Compare and determine the size relationship. When the first probability value corresponding to one or more first parameter types is greater than a preset probability threshold, the one or more first parameter types are determined as corresponding second parameter types. The second parameter type is used to indicate factors that meet the characteristics of the target area and have a greater impact on the highland barley planting yield in the target area.

[0049] For example, the parameter type determination module inputs the first feature vectors F5-F6 into a preset factor determination model, and then the factor determination model outputs the first probability values ​​H corresponding to the first parameter types x1-x5. 11 ~H 51 And the second probability value H 12 ~H 52 Furthermore, the parameter type determination module determines the first probability value H corresponding to each first parameter type x1-x5. 11 ~H 51 Respectively with the pre-set probability threshold H l Compare and determine the probability value H corresponding to the first parameter type x1 11 and the probability value H corresponding to the first parameter type x3 31 Greater than the preset probability threshold H l Therefore, the parameter type determination module determines the first parameter type x1 and the first parameter type x3 as the second parameter type.

[0050] In the case where the parameter type determination module determines one or more second parameter types, the one or more second parameter types y1~y k The data is then sent to the data acquisition module. The data acquisition module then uses the pre-set sensors 1~k to collect the data of the current planting cycle and each second parameter type y1~y in the target area.k The corresponding parameter value is based on the parameter values ​​y1~y corresponding to each second parameter type. k , construct the second characteristic vector F s (S308). Specifically, refer to Figure 2 As shown, a plurality of sensors 1-k are arranged in the target area, wherein the sensors 1-k are used to collect parameter values ​​y1-y corresponding to each second parameter type. k For example, sensor 1 is used to collect parameter value y1 of the second parameter type, sensor 2 is used to collect parameter value y2 of the second parameter type, ..., sensor k is used to collect parameter value y of the second parameter type k .

[0051] The data acquisition module collects the parameter values ​​y1~y corresponding to each second parameter type. k In the case of further constructing the second eigenvector F s It is worth noting that the second eigenvector F s The dimension corresponds to the number of the first parameter types, and when the number of the second parameter types is less than the number of the first parameter types, the data acquisition module converts the second feature vector F s Except for the parameter values ​​y1~y corresponding to each second parameter type k The vector elements outside of the .

[0052] For example, the number of first parameter types is 6, the number of second parameter types is 2, and the second eigenvector From the above, we can see that since the number of the first parameter type is 6, the second eigenvector The vector dimension is 6, and in the case of only 2 second parameter types, the second eigenvector , vector elements other than the parameter values ​​corresponding to the respective second parameter types are set to 0.

[0053] Finally, the data acquisition module converts the second eigenvector F s The monitoring and early warning module uses the production warning model pre-set by the model building module and based on the second feature vector F s , monitor the second highland barley planting yield in the target area (S310). The yield warning model may be, for example, an RNN model. Specifically, the monitoring and warning module converts the second feature vector F sInput to the pre-trained yield warning model, and then the yield warning model predicts and outputs the barley planting yield level of the target area in the current planting cycle. Among them, the barley planting yield level is divided into high, relatively high, medium, relatively low and low. After that, the monitoring and early warning module compares the barley planting level in the current planting cycle with the pre-set yield level threshold, and when the barley planting level in the current planting cycle is lower than the pre-set yield level threshold, the user is warned through the terminal device. Among them, the pre-set yield level threshold can be, for example, relatively high. And the yield level threshold can be determined by experts based on historical experience or based on historical data, which is not limited here.

[0054] As described in the background technology, although the factors affecting highland barley yields are different in different regions, the existing means of intelligent monitoring of highland barley planting usually do not change due to regional characteristics. Therefore, if the existing intelligent monitoring methods are still used to monitor the highland barley planting yield (for example, using the same intelligent monitoring model to monitor the highland barley planting yields in different regions), it may lead to a decrease in the accuracy of the final monitoring and early warning results.

[0055] In view of this, referring to the above-mentioned contents, it can be known that, when determining the target area and multiple first parameter types corresponding to the target area, the present application does not directly use multiple first parameter types to predict the barley planting yield of the current planting cycle (i.e., the second barley planting yield), but first uses a preset factor determination model to determine the second parameter type among the multiple first parameter types, and uses the second parameter type to predict the barley planting yield of the current planting cycle. The second parameter type is used to indicate the influencing factors among the multiple first parameter types that have a higher degree of influence on the barley planting yield of the target area. That is, each second parameter type corresponds to the characteristics of the target area.

[0056] That is to say, when the second parameter type is determined, the parameter value corresponding to the current planting cycle and the second parameter type is obtained, and the obtained parameter value is input into a preset yield warning model, so that the yield warning model can output the barley planting yield level of the current planting cycle, and issue a warning when the barley planting yield level is lower than the preset yield level threshold.

[0057] Therefore, different from the prior art, the present application selects the influencing factors that most affect the barley planting yield of the target area from multiple influencing factors based on the characteristics of the target area, and monitors the barley planting yield of the target area based on the influencing factors that most affect the barley planting yield of the target area, thereby improving the accuracy of the monitoring and early warning results of the barley planting yield.

[0058] This solves the technical problem in the prior art that, although the factors affecting highland barley yield in different regions are different, the accuracy of the final monitoring and early warning results is reduced because the influence of the characteristics of different regions on the highland barley planting yield is not taken into account.

[0059] Optionally, the operation of monitoring the second highland barley planting yield in the target area using a preset yield warning model and based on the second eigenvector includes: predicting the highland barley planting yield level in the target area during the current planting cycle using the yield warning model and based on the second eigenvector; and issuing an early warning when the highland barley planting yield level in the target area is lower than a preset yield level threshold.

[0060] Specifically, when the monitoring and early warning module receives the second feature vector sent by the data acquisition module In the case of Input into the yield warning model. Thus, the yield warning model can output the highland barley planting yield level of the target area in the current planting cycle. Among them, the yield warning model can be, for example, an RNN model. And among them, the highland barley planting yield level includes high, relatively high, medium, relatively low and low.

[0061] Furthermore, the yield warning model compares the highland barley planting yield level of the target area in the current planting cycle with the preset yield level threshold, and issues a warning to the user through the terminal device when the yield level is lower than the preset yield level threshold. Thus, the user can make timely adjustments to the highland barley planting method in the target area through the warning information, and ensure that the highland barley planting yield in the target area is at a high level in the next planting cycle.

[0062] In addition, it is worth noting that before the yield warning module uses the yield warning model to predict the barley yield level in the target area during the current planting cycle, the model building module also needs to train the yield warning model in advance.

[0063] Training of production warning model:

[0064] First, the data collection module determines multiple sample areas and collects parameter value samples corresponding to the second parameter types of different sample areas during each sample planting cycle. The second parameter types corresponding to different sample areas may be determined when training the factor determination model, for example.

[0065] Then, the model building model determines the highland barley planting yield grade corresponding to different sample areas based on the preset yield grade table and the highland barley planting yield corresponding to different sample areas in each sample planting cycle. The yield grade table can be pre-built by professionals based on experience, for example.

[0066] Finally, the model building model takes the parameter value samples corresponding to the second parameter type in different sample areas within each sample planting cycle as the input of the yield warning model, and takes the highland barley planting yield level corresponding to different sample areas as the output of the yield warning model, so as to train the yield warning model.

[0067] Optionally, a second feature vector is constructed based on parameter values ​​corresponding to each second parameter type collected in the current planting cycle, including: when each second parameter type is determined, obtaining the parameter values ​​corresponding to each second parameter type in the current planting cycle; based on the parameter values ​​corresponding to each second parameter type, constructing a second feature vector, wherein the dimension of the second feature vector corresponds to the number of multiple first parameter types; and when the number of first parameter types is greater than the number of second parameter types, setting the vector elements in the second feature vector except the parameter values ​​corresponding to each second parameter type to 0.

[0068] Specifically, when the parameter type determination module determines each second parameter type, the information corresponding to each second parameter type is sent to the data acquisition module. Thus, when the data acquisition module determines each second parameter type, it obtains the parameter value corresponding to each second parameter type in the current planting cycle. For example, the data acquisition module can use sensors 1~k to collect parameter values ​​y1~y1 corresponding to each second parameter type in the target area. k It is worth noting that, for example, n sensors are arranged in the target area, and each sensor is used to collect parameter values ​​of the corresponding parameter type. Thus, when the data acquisition module determines each second parameter type, it can call sensors 1~k corresponding to each second parameter type and collect parameter values ​​y1~y corresponding to each second parameter type. k .

[0069] Then the data acquisition module constructs the second feature vector F based on the parameter values ​​corresponding to each second parameter type. s . Wherein, when the number of the second parameter type is equal to the number of the first parameter type, each vector element in the second characteristic vector corresponds to a parameter value of each second parameter type, and at this time In the case where the number of the second parameter types is less than the number of the first parameter types, the vector elements in the second feature vector other than the parameter values ​​corresponding to the respective second parameter types are set to 0. The number of 0s is equal to the difference between the number of the first parameter type and the number of the second parameter type.

[0070] Therefore, it can be seen from the above that in the embodiments of the present application, although the number of second parameter types in different target areas is different, since the dimension of the second characteristic vector is certain (i.e., corresponding to the number of first parameter types), even if the number of second parameter types in different target areas is different, the production warning model can also be used as a universal model to monitor and warn different target areas, thereby achieving the technical effect of increasing the applicability of the intelligent monitoring method.

[0071] Optionally, the factor determination model includes a self-attention model, a fully connected layer and multiple softmax classifiers, and the operation of determining one or more second parameter types using a preset factor determination model and based on multiple first eigenvectors includes: inputting multiple first eigenvectors into the self-attention model and the fully connected layer, and outputting a third eigenvector; inputting the third eigenvector into multiple softmax classifiers, and outputting a first probability value for indicating the selection of the first parameter type and a second probability value for indicating not selecting the first parameter type, wherein the number of multiple softmax classifiers corresponds to the number of multiple first parameter types, and wherein the first probability value and the second probability value are used to indicate the degree of influence of each first parameter type on the highland barley planting yield in the target area; judging the relationship between the first probability value and a preset probability threshold; and taking the first parameter type whose first probability value is greater than the probability threshold as the second parameter type.

[0072] Specifically, refer to Figure 4 As shown, the factor determination model includes a self-attention model, a fully connected layer, and multiple softmax classifiers. The number of multiple softmax classifiers corresponds to the number of first parameter types. First, the parameter type determination module converts multiple first feature vectors F1~F m Input to the self-attention model and the fully connected layer, so that the fully connected layer outputs the third feature vector F g Among them, the self-attention model can determine each first eigenvector F1~F m The first parameter type x1~x n The corresponding highland barley yield is Q1~Q m The correlation relationship between them.

[0073] Then, the fully connected layer transforms the third feature vector F g Send to multiple softmax classifiers, and output the first probability value H corresponding to each first parameter type respectively11 ~H n1 And the second probability value H 12 ~H n2 Among them, the first probability value H of each first parameter type 11 ~H n1 And the second probability value H 12 ~H n2 It is used to indicate the influence of each first parameter type on the highland barley yield in the target area. That is, the larger the first probability value and the smaller the second probability value, the greater the influence of the corresponding first parameter type on the highland barley yield in the target area; the smaller the first probability value and the larger the second probability value, the smaller the influence of the corresponding first parameter type on the highland barley yield in the target area.

[0074] After that, the parameter type determination module determines the first probability value H corresponding to each first parameter type. 11 ~H n1 And the second probability value H 12 ~H n2 In the case of 11 ~H n1 With the pre-set probability threshold Finally, the first probability value H 11 ~H n1 The first parameter type that is greater than a preset probability threshold is determined as the second parameter type.

[0075] Thus, referring to the above-mentioned contents, it can be known that before monitoring and warning the highland barley planting yield in the target area, the present application pre-analyzes the relationship between each first parameter type and the corresponding highland barley planting yield in the historical planting cycle, and determines the second parameter type with a higher degree of influence on the highland barley planting yield in the target area. Thus, the second parameter type with a higher degree of correlation with the target area is ultimately used to generate the monitoring and early warning results, thereby effectively improving the accuracy of the monitoring and early warning results.

[0076] Training of the factor determination model:

[0077] First, the data acquisition module determines multiple sample areas, and collects parameter value samples corresponding to each first parameter type in different sample areas and corresponding barley planting yield samples during each sample planting cycle, and constructs multiple feature vector samples corresponding to different sample areas based on the parameter value samples corresponding to each first parameter type and the barley planting yield samples.

[0078] Then, the model building module determines the second parameter type corresponding to the highland barley planting yield of different sample areas in each sample planting cycle. The second parameter type corresponding to the highland barley planting yield of different sample areas can be pre-marked and determined by experts based on historical data of the sample area or pre-marked and determined by experts based on professional experience.

[0079] Finally, the model building module uses multiple feature vector samples corresponding to different sample areas in each sample planting cycle as input of the factor determination model, and uses the second parameter type corresponding to different sample areas as output of the factor determination model, thereby training the factor determination model.

[0080] Therefore, according to the first aspect of this embodiment, the technical effect of improving the accuracy of monitoring and early warning is achieved.

[0081] In addition, reference Figure 1 As shown, according to the second aspect of this embodiment, a storage medium is provided, wherein the storage medium includes a stored program, wherein when the program is run, a processor executes any one of the above methods.

[0082] Therefore, according to this embodiment, the technical effect of improving the accuracy of monitoring and early warning is achieved.

[0083] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0084] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0085] Example 2

[0086] Figure 5The intelligent monitoring device 500 for highland barley planting according to this embodiment is shown, and the device 500 corresponds to the method according to embodiment 1. Figure 5 As shown, the device 500 includes: a first parameter type determination module 510, which is used to determine a target area and a plurality of first parameter types corresponding to the target area, wherein the first parameter type is used to indicate the type of influencing factors affecting the highland barley planting yield; a first feature vector construction module 520, which is used to collect parameter values ​​corresponding to each first parameter type and the first highland barley planting yield in each historical planting cycle, and construct a plurality of first feature vectors based on the parameter values ​​corresponding to each first parameter type and the first highland barley planting yield; a second parameter type determination module 530, which is used to determine one or more second parameter types using a preset factor determination model and based on a plurality of first feature vectors, wherein the second parameter type corresponds to the target area; a second feature vector construction module 540, which is used to collect parameter values ​​corresponding to each second parameter type in the current planting cycle, and construct a second feature vector based on the parameter values ​​corresponding to each second parameter type; and a yield monitoring module 550, which is used to monitor the second highland barley planting yield of the target area using a preset yield warning model and based on the second feature vector.

[0087] Optionally, the yield monitoring module 550 includes: a yield grade prediction module, which is used to predict the barley yield grade of the target area in the current planting cycle by using the yield warning model and based on the second eigenvector; and an early warning module, which is used to issue an early warning when the barley yield grade of the target area is lower than the preset yield grade.

[0088] Optionally, the second feature vector construction module 540 includes: a parameter value acquisition module, which is used to obtain the parameter values ​​corresponding to each second parameter type in the current planting cycle when each second parameter type is determined; a second feature vector construction sub-module, which is used to construct a second feature vector based on the parameter values ​​corresponding to each second parameter type, wherein the dimension of the second feature vector corresponds to the number of multiple first parameter types; and a vector element setting module, which is used to set the vector elements in the second feature vector except the parameter values ​​corresponding to each second parameter type to 0 when the number of first parameter types is greater than the number of second parameter types.

[0089] Optionally, the factor determination model includes a self-attention model, a fully connected layer and multiple softmax classifiers, and the second parameter type determination module 530 includes: a third feature vector output module, used to input multiple first feature vectors into the self-attention model and the fully connected layer, and output a third feature vector; a probability value output module, used to input the third feature vector into multiple softmax classifiers, and output a first probability value indicating the selection of the first parameter type and a second probability value indicating that the first parameter type is not selected, wherein the number of multiple softmax classifiers corresponds to the number of multiple first parameter types, and wherein the first probability value and the second probability value are used to indicate the degree of influence of each first parameter type on the barley planting yield in the target area; a relationship determination module, used to determine the relationship between the first probability value and a pre-set probability threshold; and a second parameter type determination submodule, used to take the first parameter type whose first probability value is greater than the probability threshold as the second parameter type.

[0090] Therefore, according to this embodiment, the technical effect of improving the accuracy of monitoring and early warning is achieved.

[0091] Example 3

[0092] Figure 6 The intelligent monitoring device 600 for highland barley planting according to this embodiment is shown, and the device 600 corresponds to the method according to embodiment 1. Figure 6 As shown, the device 600 includes: a processor 610; and a memory 620, which is connected to the processor 610 and is used to provide the processor 610 with instructions for processing the following processing steps: determining a target area and a plurality of first parameter types corresponding to the target area, wherein the first parameter type is used to indicate the type of influencing factors affecting the barley planting yield; collecting parameter values ​​corresponding to each first parameter type and the first barley planting yield in each historical planting cycle, and constructing a plurality of first feature vectors based on the parameter values ​​corresponding to each first parameter type and the first barley planting yield; determining one or more second parameter types using a pre-set factor determination model and based on a plurality of first feature vectors, wherein the second parameter type corresponds to the target area; collecting parameter values ​​corresponding to each second parameter type in the current planting cycle, and constructing a second feature vector based on the parameter values ​​corresponding to each second parameter type; and monitoring the second barley planting yield of the target area using a pre-set yield warning model and based on the second feature vector.

[0093] Optionally, the operation of monitoring the second highland barley planting yield in the target area using a preset yield warning model and based on the second eigenvector includes: predicting the highland barley planting yield level of the target area within the current planting cycle using the yield warning model and based on the second eigenvector; and issuing an early warning when the highland barley planting yield level of the target area is lower than a preset yield level threshold.

[0094] Optionally, a second feature vector is constructed based on parameter values ​​corresponding to each second parameter type collected in the current planting cycle, including: when each second parameter type is determined, obtaining the parameter values ​​corresponding to each second parameter type in the current planting cycle; based on the parameter values ​​corresponding to each second parameter type, constructing a second feature vector, wherein the dimension of the second feature vector corresponds to the number of multiple first parameter types; and when the number of first parameter types is greater than the number of second parameter types, setting the vector elements in the second feature vector except the parameter values ​​corresponding to each second parameter type to 0.

[0095] Optionally, the factor determination model includes a self-attention model, a fully connected layer and multiple softmax classifiers, and the operation of determining one or more second parameter types using a preset factor determination model and based on multiple first eigenvectors includes: inputting multiple first eigenvectors into the self-attention model and the fully connected layer, and outputting a third eigenvector; inputting the third eigenvector into multiple softmax classifiers, and outputting a first probability value for indicating the selection of the first parameter type and a second probability value for indicating not selecting the first parameter type, wherein the number of multiple softmax classifiers corresponds to the number of multiple first parameter types, and wherein the first probability value and the second probability value are used to indicate the degree of influence of each first parameter type on the highland barley planting yield in the target area; judging the relationship between the first probability value and a preset probability threshold; and taking the first parameter type whose first probability value is greater than the probability threshold as the second parameter type.

[0096] Therefore, according to this embodiment, the technical effect of improving the accuracy of monitoring and early warning is achieved.

[0097] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0098] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0099] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0100] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0101] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0102] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0103] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An intelligent monitoring method for highland barley planting, characterized in that: include: Determine a target area and a plurality of first parameter types corresponding to the target area, wherein the first parameter type is used to indicate the type of influencing factors affecting the highland barley planting yield; Collect parameter values ​​corresponding to each first parameter type and the first highland barley planting yield in each historical planting cycle, and construct a plurality of first feature vectors based on the parameter values ​​corresponding to each first parameter type and the first highland barley planting yield; Determining one or more second parameter types based on the plurality of first feature vectors using a preset factor determination model, wherein the second parameter type corresponds to the target area, and wherein the factor determination model includes a self-attention model, a fully connected layer, and a plurality of softmax classifiers, and wherein determining one or more second parameter types based on the plurality of first feature vectors using the preset factor determination model includes: Input the plurality of first feature vectors into the self-attention model and the fully connected layer, and output a third feature vector, wherein the self-attention model is capable of determining a correlation between the first parameter type in each first feature vector and the highland barley planting yield; Input the third feature vector to the multiple softmax classifiers, and output a first probability value for indicating that the first parameter type is selected and a second probability value for indicating that the first parameter type is not selected, wherein the number of the multiple softmax classifiers corresponds to the number of the multiple first parameter types, and wherein the first probability value and the second probability value are used to indicate the degree of influence of each first parameter type on the highland barley planting yield in the target area; Determining the relationship between the first probability value and a preset probability threshold; and taking the first parameter type whose first probability value is greater than the probability threshold as the second parameter type; Collecting parameter values ​​corresponding to each second parameter type in the current planting cycle, and constructing a second feature vector based on the parameter values ​​corresponding to each second parameter type; and The second highland barley planting yield in the target area is monitored by using a preset yield warning model and based on the second characteristic vector.

2. The method according to claim 1, characterized in that: The operation of monitoring the second highland barley planting yield in the target area by using a preset yield warning model and based on the second characteristic vector includes: Using the yield warning model and based on the second feature vector, predicting the highland barley planting yield level of the target area in the current planting cycle; and When the highland barley planting yield level in the target area is lower than a preset yield level threshold, an early warning is issued.

3. The method according to claim 2, characterized in that Based on the collected parameter values ​​corresponding to each second parameter type in the current planting cycle, a second feature vector is constructed, including: When the types of the second parameters are determined, obtaining parameter values ​​corresponding to the types of the second parameters in the current planting cycle; constructing the second feature vector based on the parameter values ​​corresponding to the respective second parameter types, wherein the dimension of the second feature vector corresponds to the number of the plurality of first parameter types; and In a case where the number of the first parameter types is greater than the number of the second parameter types, vector elements in the second feature vector other than parameter values ​​corresponding to the respective second parameter types are set to zero.

4. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is run, the processor executes the method according to any one of claims 1 to 3.

5. An intelligent monitoring device for highland barley planting, characterized in that: include: A first parameter type determination module, used to determine a target area and a plurality of first parameter types corresponding to the target area, wherein the first parameter type is used to indicate the type of influencing factors affecting the highland barley planting yield; A first feature vector construction module, used to collect parameter values ​​corresponding to each first parameter type and the first highland barley planting yield in each historical planting cycle, and construct a plurality of first feature vectors based on the parameter values ​​corresponding to each first parameter type and the first highland barley planting yield; A second parameter type determination module is used to determine one or more second parameter types based on the plurality of first feature vectors using a preset factor determination model, wherein the second parameter type corresponds to the target area, wherein the factor determination model includes a self-attention model, a fully connected layer, and a plurality of softmax classifiers, and wherein the second parameter type determination module includes: A third feature vector output module, used for inputting the plurality of first feature vectors into the self-attention model and the fully connected layer, and outputting a third feature vector, wherein the self-attention model can determine the correlation between the first parameter type in each first feature vector and the highland barley planting yield; A probability value output module, used for inputting the third feature vector into the multiple softmax classifiers, and outputting a first probability value for indicating the selection of the first parameter type and a second probability value for indicating the non-selection of the first parameter type, wherein the number of the multiple softmax classifiers corresponds to the number of the multiple first parameter types, and wherein the first probability value and the second probability value are used to indicate the degree of influence of each first parameter type on the highland barley planting yield in the target area; a relationship determination module, configured to determine the relationship between the first probability value and a preset probability threshold; and A second parameter type determination submodule, configured to take the first parameter type whose first probability value is greater than the probability threshold as the second parameter type; A second feature vector construction module, used to collect parameter values ​​corresponding to each second parameter type in the current planting cycle, and construct a second feature vector based on the parameter values ​​corresponding to each second parameter type; and The yield monitoring module is used to monitor the second highland barley planting yield in the target area by using a preset yield warning model and based on the second characteristic vector.

6. The device according to claim 5, characterized in that The production monitoring module comprises: A yield grade prediction module, used for predicting the highland barley planting yield grade of the target area in the current planting cycle by using the yield warning model and based on the second feature vector; and The early warning module is used to issue an early warning when the highland barley planting yield level in the target area is lower than the preset yield level.

7. The device according to claim 6, characterized in that The second feature vector construction module includes: A parameter value acquisition module, configured to acquire parameter values ​​corresponding to the respective second parameter types in the current planting cycle when the respective second parameter types are determined; A second feature vector construction submodule, configured to construct the second feature vector based on parameter values ​​corresponding to the respective second parameter types, wherein a dimension of the second feature vector corresponds to the number of the plurality of first parameter types; and A vector element setting module is used to set the vector elements in the second feature vector except the parameter values ​​corresponding to the respective second parameter types to 0 when the number of the first parameter types is greater than the number of the second parameter types.

8. An intelligent monitoring device for highland barley planting, characterized in that: include: processor; as well as A memory, connected to the processor, configured to provide the processor with instructions for processing the following processing steps: Determine a target area and a plurality of first parameter types corresponding to the target area, wherein the first parameter type is used to indicate the type of influencing factors affecting the highland barley planting yield; Collect parameter values ​​corresponding to each first parameter type and the first highland barley planting yield in each historical planting cycle, and construct a plurality of first feature vectors based on the parameter values ​​corresponding to each first parameter type and the first highland barley planting yield; Determining one or more second parameter types based on the plurality of first feature vectors using a preset factor determination model, wherein the second parameter type corresponds to the target area, and wherein the factor determination model includes a self-attention model, a fully connected layer, and a plurality of softmax classifiers, and wherein determining one or more second parameter types based on the plurality of first feature vectors using the preset factor determination model includes: Input the plurality of first feature vectors into the self-attention model and the fully connected layer, and output a third feature vector, wherein the self-attention model is capable of determining a correlation between the first parameter type in each first feature vector and the highland barley planting yield; Input the third feature vector to the multiple softmax classifiers, and output a first probability value for indicating that the first parameter type is selected and a second probability value for indicating that the first parameter type is not selected, wherein the number of the multiple softmax classifiers corresponds to the number of the multiple first parameter types, and wherein the first probability value and the second probability value are used to indicate the degree of influence of each first parameter type on the highland barley planting yield in the target area; Determining the relationship between the first probability value and a preset probability threshold; and taking the first parameter type whose first probability value is greater than the probability threshold as the second parameter type; Collecting parameter values ​​corresponding to each second parameter type in the current planting cycle, and constructing a second feature vector based on the parameter values ​​corresponding to each second parameter type; and The second highland barley planting yield in the target area is monitored by using a preset yield warning model and based on the second characteristic vector.

Images