CN-121543900-B - Intelligent digital aquaculture management system and method

CN121543900BCN 121543900 BCN121543900 BCN 121543900BCN-121543900-B

Abstract

The invention discloses an intelligent digital aquaculture management system and method, which particularly relates to the technical field of digital agricultural management, and is used for solving the problem that the production process gradually deviates from an expected target due to the fact that the long-term cooperativity of local dynamic adjustment and overall production plan in the existing aquaculture management is insufficient, and realizing closed-loop self-adaptive management of the aquaculture process by acquiring and continuously monitoring aquaculture production plan, production state data and management operation data, analyzing response logic between management operation and production state to judge deviation trend, constructing and comparing a historical and current causal relationship network to identify the change of key causal relationship when deviation occurs, analyzing the uniformity change mode of the individual size in an aquaculture group, generating and executing a targeted management adjustment instruction according to the analysis result, and finally dynamically updating the aquaculture production plan according to the instruction execution effect, so that the predictability and stability of the production result are ensured.

Inventors

FANG XIU
WANG QING
Liu rongcheng
CHEN XIAOHUI

Assignees

福建闽威实业股份有限公司

Dates

Publication Date: 20260508
Application Date: 20260120

Claims (7)

1. An intelligent digital aquaculture management method, comprising: S1, acquiring a preset cultivation production plan and continuously acquiring production state data and executed management operation data in an actual cultivation process; S2, analyzing response logic between the management operation data which are actually executed and the corresponding production state data, and judging that a deviation trend occurs when the response logic is inconsistent with the preset causal logic relationship; s3, when the deviation trend is judged to occur, a causal relationship network is constructed and compared according to the history and the current production state data based on a causal relationship analysis algorithm, and causal relationships with significant changes are identified; s4, analyzing a uniformity change mode of the individual sizes in the breeding population when the deviation trend occurs; S5, generating and executing a management adjustment instruction for a subsequent stage by integrating a causal relation and uniformity change mode which are remarkably changed; s6, updating the cultivation production plan according to the execution result of the management adjustment instruction; the step S2 comprises the following steps: Based on the time sequence relation between the management operation data and the production state data, establishing a mapping relation between the management operation event and the subsequent production state change event; Extracting actual response characteristic parameters between management operation data and production state data from the mapping relation; comparing the actual response characteristic parameter with an expected response characteristic parameter in a preset causal logic relationship; when the difference between the actual response characteristic parameter and the expected response characteristic parameter exceeds a preset difference threshold value, judging that the response logic is inconsistent with the preset causal logic relationship; Analyzing management operation data and production state data in a history normal period, extracting stable time sequence association and quantitative response characteristics between a management operation event and a subsequent production state change event, and establishing a preset causal logic relationship based on the extracted time sequence association and quantitative response characteristics; The step S3 comprises the following steps: From the production state data, according to the judgment time point of the deviation trend, the historical normal period production state data and the current deviation period production state data are divided; Based on a causal relationship analysis algorithm, respectively processing the production state data of the historical normal period and the production state data of the current deviation period to obtain a historical causal relationship network reflecting causal influence relationship among production state variables of the historical period and a current causal relationship network reflecting causal influence relationship among production state variables of the current period; The method comprises the steps of comparing a current causal relationship network with a historical causal relationship network, wherein the specific comparison content comprises the steps of identifying causal relationships which exist in two causal relationship networks at the same time but the strength change of a causal edge connected with the same pair of production state variables exceeds a preset strength threshold; and identifying the causal relationship meeting the comparison condition as the causal relationship with obvious change.
2. The intelligent digital aquaculture management method of claim 1, wherein S1 comprises: Acquiring a cultivation production plan comprising a staged expected production state sequence; Continuously monitoring the culture environment parameters and the culture population biological parameters through the sensors to form production state data; continuously recording the operation types, the execution time and the operation intensity of feeding, oxygenation and water changing operations executed by the cultivation process so as to form management operation data.
3. An intelligent digital aquaculture management method according to claim 2 wherein the production status data is associated with an expected production status sequence in a aquaculture production plan and the management operation data is associated in time with the production status data.
4. The intelligent digital aquaculture management method according to claim 1, wherein S4 comprises: Acquiring sampling data of individual sizes in the breeding group at different time points before and after the departure trend appears; Calculating and forming a uniformity index sequence representing the degree of dispersion of the individual sizes in the population based on the sampling data of the individual sizes in the culture population; Analyzing the change trend of the uniformity index sequence before and after the departure trend appears; And identifying a uniformity variation mode representing the population differentiation aggravation, the stability maintenance or the uniformity trend according to the variation trend of the uniformity index sequence.
5. The intelligent digital aquaculture management method according to claim 1, wherein S5 comprises: determining potential key regulation links according to production state variables related to causal relationships with significant changes; Combining the group differentiation conditions indicated by the uniformity change mode, and aiming at key regulation links, formulating management and adjustment instructions comprising operation types, adjustment opportunities and adjustment intensity; And outputting a management adjustment instruction to the culture management system so as to drive the execution mechanism to execute corresponding feeding, oxygenation or water changing operations in a subsequent stage.
6. The intelligent digital aquaculture management method according to claim 1, wherein S6 comprises: After the management adjustment instruction is executed in the subsequent stage, acquiring production state data of the subsequent stage to evaluate the instruction execution effect; analyzing the correction degree of the instruction execution effect on the deviation trend and the improvement condition of the uniformity change mode; based on the comprehensive analysis results of the correction degree and the improvement condition, adaptively adjusting the expected production state sequence of the subsequent stage in the cultivation production plan; and updating the adjusted expected production state sequence to the cultivation production plan to form an updated cultivation production plan for guiding the subsequent cultivation process.
7. An intelligent digital aquaculture management system for implementing an intelligent digital aquaculture management method according to any one of claims 1-6, comprising: The data acquisition module is used for acquiring a preset cultivation production plan and continuously acquiring production state data and executed management operation data in an actual cultivation process; the trend judging module is used for analyzing response logic between the actually executed management operation data and the corresponding production state data, and judging that a deviation trend occurs when the response logic is inconsistent with the preset causal logic relationship; the causal relation analysis module is used for constructing and comparing a causal relation network according to the history and the current production state data based on a causal relation analysis algorithm when the deviation trend is judged to appear, and identifying a causal relation with obvious change; The pattern analysis module is used for analyzing a uniformity variation pattern of the individual sizes in the breeding group when the deviation trend occurs; the instruction generation module is used for generating and executing a management adjustment instruction for a subsequent stage by integrating a causal relation and uniformity change mode which are remarkably changed; and the plan updating module is used for updating the cultivation production plan according to the execution result of the management adjustment instruction.

Description

Intelligent digital aquaculture management system and method Technical Field The invention relates to the technical field of digital agricultural management, in particular to an intelligent digital aquaculture management system and method. Background In the existing digital management of aquaculture, a complete aquaculture production plan is usually formulated according to aquaculture varieties and conditions before aquaculture starts to achieve a preset production goal, the aquaculture production plan comprises staged operation arrangement and expected production states, in the actual execution process, a system monitors environment and aquaculture object information through sensors, and based on real-time data, frequent local adjustment and optimization are performed on feeding, environmental control and other operations to cope with short-term fluctuation, so as to strive to maintain the stability of the current production state. However, the existing method has the defects that a systematic cooperation is lacking between a preset fixed plan and a continuously performed dynamic optimization schedule, frequent local adjustment aims at real-time optimization, but long-term accumulation effect of the local adjustment gradually deviates the state change of an actual cultivation process from an expected evolution path in the plan, because the prior art mainly focuses on single-point or short-term data and plan contrast, an effective recognition and evaluation mechanism is lacking for the whole deviation of the long period and the trend, the initial plan gradually fails in execution, and the correlation between the basis of a subsequent optimization decision and the whole production target is weakened, so that the stability and the predictability of a production result are difficult to ensure. Disclosure of Invention Aiming at the technical problems existing in the prior art, the invention provides an intelligent digital aquaculture management system and method. The technical scheme for solving the technical problems is as follows: an intelligent digital aquaculture management method comprising: S1, acquiring a preset cultivation production plan and continuously acquiring production state data and executed management operation data in an actual cultivation process; S2, analyzing response logic between the management operation data which are actually executed and the corresponding production state data, and judging that a deviation trend occurs when the response logic is inconsistent with the preset causal logic relationship; s3, when the deviation trend is judged to occur, a causal relationship network is constructed and compared according to the history and the current production state data based on a causal relationship analysis algorithm, and causal relationships with significant changes are identified; s4, analyzing a uniformity change mode of the individual sizes in the breeding population when the deviation trend occurs; S5, generating and executing a management adjustment instruction for a subsequent stage by integrating a causal relation and uniformity change mode which are remarkably changed; And S6, updating the cultivation production plan according to the execution result of the management adjustment instruction. Further, S1 includes: Acquiring a cultivation production plan comprising a staged expected production state sequence; Continuously monitoring the culture environment parameters and the culture population biological parameters through the sensors to form production state data; continuously recording the operation types, the execution time and the operation intensity of feeding, oxygenation and water changing operations executed by the cultivation process so as to form management operation data. Further, the production status data is associated with an expected production status sequence in the aquaculture production plan, and the management operation data is associated with the production status data in time. Further, S2 includes: Based on the time sequence relation between the management operation data and the production state data, establishing a mapping relation between the management operation event and the subsequent production state change event; Extracting actual response characteristic parameters between management operation data and production state data from the mapping relation; comparing the actual response characteristic parameter with an expected response characteristic parameter in a preset causal logic relationship; When the difference between the actual response characteristic parameter and the expected response characteristic parameter exceeds a preset difference threshold, the response logic is judged to be inconsistent with the preset causal logic relationship. Further, the preset causal logic relationship is established by analyzing management operation data and production state data in a history normal period, extracting stable time sequence association and quantitative