Search

CN-121998578-A - Agricultural planting system based on artificial intelligence model

CN121998578ACN 121998578 ACN121998578 ACN 121998578ACN-121998578-A

Abstract

The embodiment of the invention provides an agricultural planting system based on an artificial intelligence model. The system comprises a data acquisition module, a model deployment module and a decision execution module, wherein the data acquisition module is used for acquiring multi-mode data of a target planting area, the multi-mode data comprises crop data of a target crop and environment data of the target planting area, the model deployment module is deployed with an artificial intelligent model and is used for analyzing the multi-mode data by utilizing the artificial intelligent model to obtain crop information of the target planting area and generating a decision instruction according to the crop information, the crop information comprises one or more of crop growth state information, plant disease and insect pest prediction information, water and fertilizer requirement information and environment adaptation information, and the decision execution module is used for generating a control signal based on the decision instruction and transmitting the control signal to the execution equipment to control the execution equipment to execute a corresponding operation task. The system can realize the accurate, real-time and intelligent management of agricultural planting.

Inventors

  • WU YINGJIE
  • LIU RUOHAN

Assignees

  • 浙江镁浦绿动未来科技有限公司

Dates

Publication Date
20260508
Application Date
20251230

Claims (10)

  1. 1. An artificial intelligence model-based agricultural planting system, comprising: The data acquisition module is used for acquiring multi-mode data of a target planting area, wherein the multi-mode data comprises crop data of target crops and environment data of the target planting area; The model deployment module is in communication connection with the data acquisition module and is used for analyzing the multi-mode data by utilizing the artificial intelligent model to obtain crop information of the target planting area and generating a decision instruction according to the crop information, wherein the crop information comprises one or more of crop growth state information, plant disease and insect pest prediction information, water and fertilizer requirement information and environment adaptation information; The decision execution module is in communication connection with the model deployment module, and is used for generating a control signal based on the decision instruction and transmitting the control signal to execution equipment to control the execution equipment to execute a corresponding operation task, wherein the execution equipment comprises one or more of a patrol robot, a mobile execution terminal, irrigation equipment, fertilization equipment, light supplementing equipment, ventilation equipment, sunshade equipment, pesticide applying equipment and a plant protection robot.
  2. 2. The agricultural planting system of claim 1, wherein the model deployment module includes a cloud server and edge nodes communicatively connected to each other; the edge node is in communication connection with the data acquisition module and is used for preprocessing the multi-mode data to obtain preprocessed data, carrying out emergency recognition on the basis of the preprocessed data to obtain event recognition results, and uploading the preprocessed data and abnormal event results to the cloud server, wherein the abnormal event results are the event recognition results indicating that the target planting area is abnormal; the cloud server is deployed with the artificial intelligent model and is used for analyzing the preprocessing data and/or the abnormal event result by utilizing the artificial intelligent model so as to obtain the crop information and generating the decision instruction according to the crop information.
  3. 3. The agricultural planting system of claim 2, wherein the pre-treatment includes: Normalizing the multi-modal data to obtain normalized multi-modal data, establishing data association of the normalized multi-modal data through semantic web technology or federal learning technology to obtain associated multi-modal data, and determining the preprocessing data based on the associated multi-modal data.
  4. 4. The agricultural planting system of claim 3, wherein, Filtering abnormal values in the multi-modal data and filling missing values in the multi-modal data before the multi-modal data is standardized so as to obtain new multi-modal data; and/or the number of the groups of groups, The determining the pre-processed data based on the associated multi-modal data includes data denoising and feature extraction of the associated multi-modal data to obtain the pre-processed data.
  5. 5. The agricultural planting system of any one of claims 1-4, wherein the decision execution module is further configured to receive execution feedback data of the execution device and send the execution feedback data to the model deployment module, The model deployment module is further used for performing iterative training on the artificial intelligent model according to the execution feedback data and the multi-mode data newly acquired in a preset period after the execution device executes the operation task.
  6. 6. The agricultural planting system according to any one of claims 1-4, wherein the decision-making execution module is further configured to monitor an operation state of the execution device and an execution progress of the job task in real time, send out an alarm message and/or automatically switch to a standby execution device when it is determined that the execution device fails according to the operation state or the job task is abnormally executed according to the execution progress.
  7. 7. The agricultural planting system of any one of claims 1-4, wherein the decision instruction includes the job task, wherein the decision execution module generates a control signal based on the decision instruction and issues the control signal to an execution device by: And adding the job tasks into a task queue, sequencing the job tasks in the task queue according to a preset priority rule, sequentially generating the control signals by the job tasks in the task queue and issuing the control signals to the execution equipment, wherein when sequencing, if the priority of a first job task currently received is higher than that of a second job task to be executed recently, the second job task is suspended, and the first job task is inserted into the front of the second job task in the task queue.
  8. 8. The agricultural planting system of any one of claims 1-4, wherein the model deployment module is further configured to: storing the multimodal data in a distributed file system and/or, Synchronizing core data to a cloud storage server, the core data including one or more of the crop growth status information, the decision instructions, and model parameters of the artificial intelligence model.
  9. 9. The agricultural planting system of any one of claims 1-4, wherein the data acquisition module includes one or more of a first environmental sensor disposed inside the target planting area, a weather station disposed inside and/or outside the target planting area, a second environmental sensor disposed on the inspection robot, a first camera disposed on the inspection robot, a third environmental sensor disposed on the mobile execution terminal, a second camera disposed on the mobile execution terminal; The crop data comprises first crop data collected by the first camera and/or second crop data collected by the second camera, and the environment data comprises one or more of first environment data collected by the first environment sensor, second environment data collected by the second environment sensor, third environment data collected by the third environment sensor and fourth environment data collected by the weather station.
  10. 10. The agricultural planting system of any one of claims 1-4, wherein the data acquisition module and the model deployment module communicate using a first standardized interface and the model deployment module and the decision execution module communicate using a second standardized interface.

Description

Agricultural planting system based on artificial intelligence model Technical Field The invention relates to the technical field of intelligent agriculture, in particular to an artificial intelligent model-based agricultural planting system. Background Along with the acceleration of digital transformation of agriculture, the traditional planting mode faces the bottlenecks of low data utilization efficiency, decision delay, rough management and the like, and the precision and the intellectualization become the core direction of agricultural development. In the current agricultural production, the planting decision is mostly dependent on experience judgment or simple statistical analysis, the dynamic demands of crop growth cannot be accurately matched, and especially the problems of untimely response, unreasonable measures and the like are easy to occur in key links such as pest control, water and fertilizer regulation, environment adaptation and the like. In order to solve the problems, an agricultural big data platform and a decision support system appear in the prior art, but the method has the obvious limitations that the adoption of a general algorithm model has limited prediction precision, the decision support stays at the recommended level of the planting scheme, the linkage execution with the execution equipment is not realized, the manual intervention operation is needed, the efficiency is low, and the execution deviation is easy to appear. Disclosure of Invention The present invention has been made in view of the above-described problems. The invention provides an agricultural planting system based on an artificial intelligence model. According to one aspect of the invention, an agricultural planting system based on an artificial intelligent model is provided, which comprises a data acquisition module, a model deployment module and an execution device, wherein the data acquisition module is used for acquiring multi-mode data of a target planting area, the multi-mode data comprise crop data of the target crop and environment data of the target planting area, the model deployment module is used for deploying the artificial intelligent model, the model deployment module is in communication connection with the data acquisition module and is used for analyzing the multi-mode data by utilizing the artificial intelligent model to obtain crop information of the target planting area and generating decision instructions according to the crop information, the crop information comprises one or more of crop growth state information, plant disease and pest prediction information, water and fertilizer requirement information and environment adaptation information, the decision execution module is in communication connection with the model deployment module and is used for generating control signals based on the decision instructions and sending the control signals to the execution device to control the execution device to execute corresponding operation tasks, and the execution device comprises one or more of a patrol robot, a mobile execution terminal, an irrigation device, a fertilization device, a light supplementing device, a ventilation device, a sunshade device and a plant protection robot. The model deployment module comprises a cloud server and an edge node which are in communication connection with each other, wherein the edge node is in communication connection with the data acquisition module and is used for preprocessing multi-mode data to obtain preprocessed data, carrying out emergency event recognition based on the preprocessed data to obtain event recognition results, uploading the preprocessed data and the abnormal event results to the cloud server, wherein the abnormal event results are event recognition results indicating that an abnormal situation exists in a target planting area, and the cloud server is deployed with an artificial intelligent model and is used for analyzing the preprocessed data and/or the abnormal event results by utilizing the artificial intelligent model to obtain crop information and generating a decision instruction according to the crop information. Illustratively, preprocessing includes normalizing the multimodal data to obtain normalized multimodal data and establishing a data association with the normalized multimodal data via semantic web technology or federal learning technology to obtain associated multimodal data and determining preprocessing data based on the associated multimodal data. The preprocessing also illustratively includes filtering outliers in the multimodal data and filling in missing values in the multimodal data to obtain new multimodal data prior to normalizing the multimodal data and/or determining the preprocessing data based on the associated multimodal data including data denoising and feature extraction of the associated multimodal data to obtain the preprocessing data. The decision-making execution module is also used for receiving the execu