Assessment system for relevance between pig intestinal health and trace element absorption

Abstract

The invention relates to the technical field of animal husbandry, in particular to a pig intestinal health and trace element absorption relevance evaluation system, which comprises a data storage and input module, a data storage and input module, a data processing module and a trace element absorption evaluation module, the multi-source information fusion and feature extraction module is used for extracting multi-dimensional feature vectors from the multi-modal data by using a feature system; the intelligent evaluation core module adopts an ensemble learning algorithm to train a model, and outputs an intestinal health index, an absorption efficiency index and an association degree score; the adaptive decision support module generates daily ration adjustment, prebiotic addition and economic benefit prediction reports according to the evaluation result and the rule base; according to the system, a system integrating data fusion, intelligent evaluation and decision support is constructed, so that dynamic quantitative evaluation and accurate management are realized, traditional lagging, isolated and empirical defects are overcome, the production performance is improved, the breeding cost is reduced, the environmental pollution is reduced, and other comprehensive benefits are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of animal husbandry, in particular to a pig intestinal health and trace element absorption correlation evaluation system. BACKGROUND

[0002] Currently, in large-scale pig breeding, the precise supply of trace elements (such as zinc, copper, selenium, etc.) is a key link to ensure animal health and improve production performance. However, the traditional management mode has many limitations in this regard: First, the evaluation method is lagging and isolated: the current evaluation of pig intestinal health mainly relies on visual observation (such as fecal score) or postmortem dissection, while the evaluation of trace element absorption efficiency is mainly through expensive, in vitro laboratory detection (such as atomic absorption spectrometry to determine the content in feces or blood). These methods not only time-consuming and laborious, but more importantly, they separate the two highly correlated physiological processes of intestinal health and trace element absorption, and cannot reflect the internal relationship between the two in real time and dynamically.

[0003] Second, it relies on experience-based decision-making and lacks precision: the addition of trace elements in the diet is mostly based on fixed nutritional standards and production stages, or relies on the experience of breeding personnel for rough adjustment. This "one-size-fits-all" approach cannot respond to individual differences, fluctuations in health status, and environmental changes in the pig population, which can easily lead to insufficient trace element addition affecting health and production, or excessive addition causing resource waste and environmental pollution (such as high-zinc, high-copper feces polluting the soil).

[0004] Third, the data island problem is serious: breeding farms accumulate a large amount of multi-modal data daily, including production performance records, feed formulations, environmental monitoring data, etc., but these data are usually scattered in different systems or records, independent of each other, forming "data islands". Without effective technical means to fuse, analyze and refine these multi-source heterogeneous data to obtain insights with decision-making value, a large amount of data value is buried.

[0005] Fourth, the cause-and-effect relationship is difficult to quantify: although practitioners generally recognize that intestinal health affects trace element absorption, and vice versa, the strength of this mutual influence and the specific trace elements and intestinal health indicators that are most closely related are difficult to accurately quantify. Managers cannot answer the question "If intestinal health is improved by 10%, how much will the trace element absorption efficiency be improved?" This kind of precise question lacks data support for decision-making.

[0006] In view of this, a pig intestinal health and trace element absorption correlation evaluation system is proposed. SUMMARY

[0007] The present application aims to provide a pig intestinal health and trace element absorption correlation evaluation system to realize real-time, dynamic and quantitative evaluation of the correlation between pig intestinal health and trace element absorption, and to provide accurate and personalized nutrition regulation schemes based on the evaluation results.

[0008] To achieve the above technical problems, the present application provides a pig intestinal health and trace element absorption correlation evaluation system, comprising: a data storage module for storing historical and real-time pig group multi-modal data; an input module connected to the data storage module for receiving real-time pig group multi-modal data from external data sources; a multi-source information fusion and feature extraction module connected to the input module and the data storage module, respectively, for standardizing and normalizing the received multi-modal data, and extracting a multi-dimensional feature vector for correlation evaluation from the multi-modal data based on a pre-set feature system for quantifying the dynamic correlation between intestinal health and trace element absorption; the feature system includes trace element apparent absorption rate features, trace element biological enrichment features, intestinal physiological stress features and production performance features; an intelligent evaluation core module connected to the multi-source information fusion and feature extraction module, which is provided with a correlation dynamic evaluation model; the correlation dynamic evaluation model is obtained by training historical multi-dimensional feature vectors and label data verified by in-vitro detection through ensemble learning algorithm, and is used to calculate and output intestinal health index, trace element absorption efficiency index and correlation degree score representing the correlation strength between the two in real time according to the input multi-dimensional feature vector; an adaptive decision support module connected to the intelligent evaluation core module, for generating a structured report containing personalized trace element daily ration adjustment suggestions, prebiotic addition schemes and expected economic benefit forecasts according to the correlation degree score, intestinal health index, trace element absorption efficiency index and pre-set decision rule base; an output response module connected to the adaptive decision support module for visualizing the structured report and core evaluation indicators through a graphical user interface.

[0009] As a further improvement of the present technical solution, the input module comprises: a standardized data interface unit for receiving the pig group multi-modal data from production management record systems, feed formula databases, in-vitro detection devices and manual observation record terminals; an edge computing unit deployed at the data acquisition terminal for preliminary cleaning, redundancy removal and formatting of the initial data.

[0010] As a further improvement of the technical solution, the pig group multi-modal data includes production performance data, daily ration trace element composition data, fecal trace element residual content data, hair trace element enrichment content data, intestinal health visual score data, and pig house environment monitoring data.

[0011] As a further improvement of the technical solution, the correlation dynamic evaluation model is an ensemble learning model constructed based on a gradient boosting decision tree algorithm. The input real-time multi-dimensional feature vector includes daily ration zinc level, fecal copper residual rate, hair selenium enrichment concentration, diarrhea rate, average daily weight gain, and intestinal visual score; and the output of the model includes a predicted intestinal health index and trace element comprehensive utilization rate. The correlation dynamic evaluation model quantifies the contribution of each input real-time multi-dimensional feature vector to the intestinal health index and the trace element absorption efficiency index, and reveals the correlation strength between different trace elements and different intestinal health indicators in the form of a heat map.

[0012] As a further improvement of the technical solution, the system further comprises: A model continuous learning module, connected with the intelligent evaluation core module and the data storage module respectively, is used for periodically performing incremental training and optimization of the correlation dynamic evaluation model using newly added pig group multi-modal data and corresponding validation label data, so as to update the model parameters.

[0013] As a further improvement of the technical solution, the decision rule library preset in the adaptive decision support module is a combination of production rules and case-based reasoning, and the rules in the decision rule library are in the following form: IF correlation score < threshold T1 AND trace element absorption efficiency index ∈ [value range A] AND intestinal health index ∈ [value range B]; THEN execute: adjust the organic zinc addition level in the daily ration to X mg / kg, and suggest using prebiotic Y, which is expected to improve the absorption efficiency by Z%, and is expected to reduce the diarrhea rate by W%; wherein the specific values of the threshold T1, the value range A, the value range B, the parameters X, Z, and W, and the type of Y are dynamically determined based on statistical analysis of historical data sets and case-based reasoning results.

[0014] As a further improvement of the technical solution, the output response module generates a visual interface containing a correlation analysis dashboard, which displays the correlation strength between different trace elements and different intestinal health indicators revealed by the correlation dynamic evaluation model in the form of a heat map, and displays the historical changes of the core key performance indicators and the predicted trajectory based on the current decision suggestion in the form of a trend line.

[0015] As a further improvement of the technical solution, the system further comprises a warning module connected with the intelligent evaluation core module and the adaptive decision support module respectively. The warning module is configured to automatically trigger a multi-level warning signal when the correlation score is lower than a preset threshold, and push the warning information and the corresponding structured decision suggestion to the user terminal of the designated manager.

[0016] Compared with the prior art, the present application has the following advantages: 1. In the pig intestinal health and trace element absorption correlation evaluation system, by constructing a system integrating data fusion, intelligent evaluation and decision support, dynamic, quantitative evaluation and precise management of pig intestinal health and trace element absorption correlation are realized, effectively overcoming the lag, isolation and empirical defects of traditional modes, thereby producing significant comprehensive benefits in improving production performance, reducing breeding costs and reducing environmental pollution.

[0017] 2. In the pig intestinal health and trace element absorption correlation evaluation system, through the data storage module, input module and multi-source information fusion and feature extraction module, multi-modal data from production management, feed formula, in vitro detection, artificial observation and environmental monitoring can be systematically accessed, cleaned, standardized and fused, breaking the data island, and based on the specially designed feature system, high-value feature vectors for correlation evaluation are extracted, laying a solid data foundation for precise evaluation.

[0018] 3. In the pig intestinal health and trace element absorption correlation evaluation system, through the correlation dynamic evaluation model trained in the intelligent evaluation core module, the intestinal health index, trace element absorption efficiency index and the most critical correlation score representing the correlation strength between the two can be calculated synchronously and quickly. This changes the previous situation of relying on subjective experience and lag detection, realizing the technological leap from "qualitative speculation" to "quantitative evaluation".

[0019] 4. In the pig intestinal health and trace element absorption correlation evaluation system, through the adaptive decision support module and its preset decision rule library, structured reports containing specific adjustment parameters, prebiotic addition schemes and expected economic benefit forecasts can be automatically generated according to the real-time evaluation of various indexes and scores. This makes the trace elements from "group generalization" to "individual customization", greatly improving the precision of nutrient utilization. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 The overall system block diagram of the present application. DETAILED DESCRIPTION

[0021] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be clearly and completely described below, obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0022] In the current traditional breeding management, intestinal health and trace element absorption are two isolated evaluation links, which rely on experience decision and lag detection, and cannot understand the internal dynamic connection, leading to insufficient trace element addition affecting production or excessive trace element addition causing waste and pollution.

[0023] In view of this, please refer to Figure 1 The purpose of the present application is to provide a pig intestinal health and trace element absorption correlation evaluation system, which comprises: A data storage module for storing historical and real-time pig group multi-modal data; the data storage module can be a central server configured with a MySQL database and an HDFS distributed file system. MySQL is used to store structured production performance data and ration formula data, and HDFS is used to store unstructured pictures (such as intestinal visual score pictures) and time series data (such as environmental monitoring data); An input module connected with the data storage module, for receiving real-time pig group multi-modal data from external data sources; the input module is connected with various data sources through wired / wireless network, and the specific content is as follows: A RESTful API interface for receiving production data (daily weight gain, feed intake) in JSON format from a production management record system (such as PigWin); An ODBC / JDBC interface for regularly pulling ration trace element composition data in a feed formula database; a special data parser for parsing detection result files (containing fecal and hair trace element content) transmitted by an in-vitro detection device (such as an ICP-MS spectrometer) through USB or Bluetooth; A mobile APP as an artificial observation record terminal for a breeder to upload diarrhea rate, mental state score and intestinal visual score photos; A multi-source information fusion and feature extraction module connected with the input module and the data storage module, which is implemented by a Python data processing service deployed on a server, and the working process is as follows: Standardization and normalization processing is performed on the received multi-modal data (for the received multi-modal data, first data cleaning (processing missing values and abnormal values) is performed, and then all numerical features are subjected to Z-score standardization to eliminate the influence of dimension); Based on the preset characteristic system for quantifying the dynamic correlation between intestinal health and trace element absorption, a multi-dimensional feature vector for evaluating the correlation is extracted from multi-modal data; the characteristic system includes trace element apparent absorption rate characteristics, trace element biological enrichment characteristics, intestinal physiological stress characteristics, and production performance characteristics; for example, the "apparent absorption rate of zinc" is calculated from "dietary zinc level" and "fecal zinc residue"; the "selenium biological enrichment coefficient" is calculated from "hair selenium concentration"; the "intestinal physiological stress index" is extracted from "diarrhea rate" and "intestinal visual score"; the "production performance score" is extracted from "average daily gain" and "feed to meat ratio"; The intelligent evaluation core module is connected with the multi-source information fusion and feature extraction module, and an association dynamic evaluation model is arranged therein; the association dynamic evaluation model is obtained by training historical multi-dimensional feature vectors and label data (the "true intestinal health status" and "trace element true absorption rate" verified by in vitro detection) verified by in vitro detection through an ensemble learning algorithm (XGBoost algorithm, a gradient boosting decision tree library), and is used for synchronously calculating and outputting the intestinal health index (GHI, 0-100), the trace element absorption efficiency index (TEI, 0-100), and the correlation degree score (CS, 0-1) representing the correlation strength between the two, which is obtained by summing the feature importance calculated by the model, and quantifies the correlation strength between GHI and TEI; The adaptive decision support module is connected with the intelligent evaluation core module, and is used for generating a structured report including individualized trace element dietary adjustment suggestions, prebiotic addition schemes, and expected economic benefit forecasts according to the correlation degree score, the intestinal health index, the trace element absorption efficiency index, and a preset decision rule base (loaded by a Drools rule engine, and the rule base includes dozens of production rules); specifically, the process of generating the structured report is as follows: The adaptive decision support module receives the three indexes output by the intelligent evaluation core module, and matches the conditions in the rule base. For example, if a rule is matched, a decision is triggered, and a JSON format structured report is generated, which includes: "it is suggested to increase the dietary organic zinc from 80 ppm to 100 ppm", "it is suggested to add prebiotic fructo-oligosaccharide (FOS) 500 g / ton", "the expected zinc absorption rate is increased by 15%", and "the expected diarrhea rate is reduced by 5% next week"; The output response module is connected with the adaptive decision support module, and is a web application based on the Vue.js framework as a graphical user interface (GUI), which mainly includes a data dashboard, trend charts, and detailed results of this evaluation, and is used for visualizing the structured report and the core evaluation indexes through the graphical user interface.

[0024] By constructing the aforementioned system, multimodal data, feature engineering, machine learning models, and rule engines are integrated into an automated closed-loop system for the first time. This achieves end-to-end automation from data to decision-making, solving the long-standing problems of "data silos" and "decision lag." A model is trained to quantify the "correlation strength" between gut health and micronutrient absorption efficiency, and this abstract score is directly used as a trigger for precise nutritional regulation. This cross-disciplinary technological integration (livestock farming + data science + decision science) has generated a synergistic effect, resulting in significant comprehensive benefits in improving production performance, reducing breeding costs, and minimizing environmental pollution.

[0025] Example 2: Considering the inconsistent formats of external data sources (such as detection equipment and manual terminals) and the presence of noise in the raw data (such as outliers and duplicates), direct transmission to the backend would lead to low processing efficiency and decreased model accuracy; simultaneously, traditional systems lack edge processing, and all data is uploaded to the cloud, which can easily cause network congestion; therefore, the input module includes: A standardized data interface unit is used to receive the multimodal data of the pig herd from the production management record system, feed formulation database, in vitro testing equipment, and manual observation and recording terminal; specifically: The standardized data interface unit is a universal data access gateway, written in Java, integrating the aforementioned RESTful API, JDBC driver, file listening service, and an MQTT message broker (for receiving data from IoT environment sensors). All access data is first converted into a unified internal data format (Apache Avro format). Edge computing units, deployed at data acquisition terminals, are used to perform preliminary cleaning, redundancy removal, and formatting of initial data; specifically: Lightweight edge computing programs are deployed on data acquisition terminals (such as tablets with an app installed or industrial control computers connected to testing equipment). For example, on a tablet, the app calls a locally running TensorFlow Lite model to perform preliminary analysis on intestinal images before uploading them, automatically generating a preliminary visual score, compressing the image size, completing preliminary cleaning and formatting, and then uploading it to the server, greatly reducing server load and network bandwidth pressure. Through the "cloud-edge" collaborative architecture, standardized and lightweight preprocessing of data was achieved, ensuring high quality and consistency of input data and laying a solid foundation for subsequent accurate analysis.

[0026] Example 3, considering that traditional data collection only focuses on "production performance (such as ADG)" and "diet composition", ignoring "trace element bioaccumulation (such as hair content)" and "direct indicators of intestinal health (such as visual score)", resulting in single data dimension, which cannot support the correlation evaluation of the two (for example, it is difficult to judge whether "low hair selenium is poor absorption or insufficient diet"), therefore, the multi-modal data of the pig group includes production performance data, diet trace element composition data, fecal trace element residual content data, hair trace element enrichment content data, intestinal health visual score data and pig house environment monitoring data; wherein, the production performance data includes average daily gain (ADG), average daily feed intake (ADFI), feed conversion ratio (FCR); the diet trace element composition data is the addition form (inorganic / organic) and specific content (mg / kg) of Zn, Cu, Fe, Mn, Se and other elements; the fecal trace element residual content data is the dry matter content (mg / kg) of the above elements in the feces detected by ICP-MS; the hair trace element enrichment content data: the content (mg / kg) of the above elements in the pig's back hair detected by ICP-MS, reflecting the stable index of long-term absorption; the intestinal health visual score data: scored by veterinarians or trained feeders according to standard procedures on the appearance (color, elasticity, content, lymph follicles) of the intestine after slaughter, and the pictures are uploaded through the APP for evidence; the pig house environment monitoring data: the temperature, humidity and ammonia concentration (ppm) in the house collected in real time by Internet of Things sensors; By introducing hair enrichment data as a biomarker and environmental data as a stressor, the evaluation dimension is greatly enriched. The non-obviousness lies in: combining the medium and long-term index of "hair trace elements" with the short-term index of "fecal residue", and correlating with environmental stress, a more comprehensive evaluation system is constructed.

[0027] Example 4, since the machine learning model is a "black box", even if the prediction is made, the user cannot understand which factors and to what extent affect the prediction result, making it difficult to trust and adopt the decision; at the same time, the model input features are few (only 2-3), and the output is only a single index (such as absorption efficiency), which cannot quantify the correlation strength, and the result is not intuitive, therefore, the correlation dynamic evaluation model is an ensemble learning model based on gradient boosting decision tree algorithm; the input real-time multi-dimensional feature vector includes: diet zinc level, fecal copper residual rate, hair selenium enrichment concentration, diarrhea rate, average daily gain and intestinal visual score; the output of the model includes the predicted intestinal health index and trace element comprehensive utilization rate; the correlation dynamic evaluation model quantifies the contribution of each input real-time multi-dimensional feature vector to the intestinal health index and trace element absorption efficiency index, and reveals the correlation strength between different trace elements and different intestinal health indicators in the form of a heat map, specifically: Firstly, the relevance dynamic evaluation model is built using the XGBoost library of Python to construct a gradient boosting decision tree (GBDT) model; Secondly, the input features are the multi-dimensional feature vectors extracted in Embodiment 1, including but not limited to: dietary zinc level, fecal copper residual rate, hair selenium enrichment concentration, diarrhea rate, average daily gain, intestinal visual score, and more than 20 features; Then, the relevance dynamic evaluation model has two output heads, respectively predicting the intestinal health index (GHI) and the trace element comprehensive utilization rate (TEU); Finally, after training is completed, the SHAP (SHapley Additive exPlanations) library is used to calculate the contribution of each input feature to the two prediction results (SHAP value), and then the contribution relationship between the trace element related features and the intestinal health related features is visualized in the form of a heat map. The color depth in the heat map directly reveals the correlation strength between different trace elements and different intestinal health indicators, thereby visualizing the correlation strength.

[0028] Using the above relevance dynamic evaluation model, the SHAP interpretive technology opens the model black box, making the abstract "correlation score" interpretable and verifiable. This greatly enhances the user's trust in system decision-making. Advanced explainable AI (XAI) technology is applied to the breeding field to quantify the correlation strength.

[0029] In Embodiment 5, considering that the parameters of the traditional model are fixed after training, when the pig breed is updated (such as from Large White to Duroc Landrace Yorkshire) or the feed formula is adjusted (such as from inorganic zinc to organic zinc), the deviation between the model and the actual scene increases, and manual retraining is required (long cycle, high cost), leading to a decrease in evaluation accuracy. Therefore, the system further includes: A model continuous learning module is connected to the intelligent evaluation core module and the data storage module, respectively, for periodically incrementally training and optimizing the relevance dynamic evaluation model using newly added pig multi-modal data and corresponding validation label data to update the model parameters. The specific scheme is as follows: The system sets a timing task (such as once a month), and the model continuous learning module automatically collects the newly added data in the past month and the corresponding validation labels (such as a new batch of in-vitro test reports), then uses these new data to incrementally train (or fine-tune) the original model.pkl, and at the same time, the module monitors the performance indicators (such as MSE) of the model on the latest validation set. If the performance decreases by more than a threshold, it will automatically trigger the retraining process and update the model with better performance to the new model in the production environment; Through the above technical means, the system has the ability of self-evolution and continuous optimization, can adapt to the changes of the farm, and long-term maintain the accuracy of the evaluation. This is crucial in a dynamic farming environment, while achieving automated iteration of the model without human intervention.

[0030] In Example 6, considering the traditional decision rule is "fixed threshold + experience suggestion" (such as "diarrhea rate > 5% add zinc"), there is no quantitative basis, and it is not combined with "correlation score" and "economic benefit", which leads to blind decision-making (such as the zinc addition amount is set to 150 mg / kg by experience, while 120 mg / kg can meet the demand, causing cost waste); At the same time, there is no case reference, which cannot deal with complex scenarios (such as "low correlation + low absorption efficiency + medium intestinal health"), therefore, the decision rule library preset in the adaptive decision support module is a combination of production rules and case-based reasoning, the rules in the decision rule library are as follows: IF correlation score < threshold T1 AND trace element absorption efficiency index ∈ [value range A] AND intestinal health index ∈ [value range B]; For example: IF correlation score CS < 0.7 AND trace element absorption efficiency index TEI ∈ [30, 50] AND intestinal health index GHI ∈ [40, 60]; THEN execute: adjust the organic zinc addition level in the diet to X mg / kg, and suggest using prebiotic Y, which is expected to improve absorption efficiency Z%, and is expected to reduce diarrhea rate W%; For example: THEN execute: adjust the organic zinc addition level in the diet to 120 mg / kg, and suggest using prebiotic (fructo-oligosaccharide), which is expected to improve zinc absorption efficiency by 18%, and is expected to reduce diarrhea rate by 8%.

[0031] The specific values of the parameters threshold T1, value range A, value range B, parameter X, Z, W in the rule, and the type of Y are not fixed, the system has a case library in the background, which stores successful intervention cases in history. When new data is transmitted, the system will simultaneously perform case retrieval to find the most similar historical case. The threshold and parameters in the above rule will be dynamically fine-tuned according to the results of similar cases (for example, fine-tune 120 mg / kg to 115 mg / kg), so that the decision is more accurate.

[0032] Through the above design, the combination of rule-based rapid response and case-based precise optimization realizes the unity of "principle and flexibility". This hybrid decision mechanism makes the system's suggestions not only reliable, but also increasingly personalized, and its effects (improving absorption rate, reducing diarrhea rate) are predictable and verifiable.

[0033] In view of the complex evaluation results and decision report, if presented in text form, it is not intuitive and cannot quickly grasp the key points; abnormal situations need to be manually monitored on the screen to be discovered, therefore, the visualization interface generated by the output response module includes a correlation analysis dashboard, which displays the correlation strength between different trace elements and different intestinal health indicators revealed by the correlation dynamic evaluation model in the form of a heat map, and displays the historical changes of the core key performance indicators and the predicted trajectory based on the current decision suggestion in the form of a trend line; the system also includes a warning module connected with the intelligent evaluation core module and the adaptive decision support module; the warning module is configured to: when the correlation degree score is lower than the preset threshold, automatically trigger a multi-level warning signal, and push the warning information and the corresponding structured decision suggestion to the user terminal of the designated manager; specifically: The correlation analysis dashboard is developed using the ECharts library. The core components include: Heat map: directly display the SHAP value heat map generated in embodiment 4, and intuitively display the correlation strength of selenium-diarrhea rate, zinc-intestinal score, etc.

[0034] Trend line: display the historical change curve of the key indicators (such as GHI, TEI, CS) in the past 90 days, and based on the current decision suggestion, extend the predicted future trajectory with a dashed line; The warning module listens to the correlation degree score (CS) output by the intelligent evaluation core module. Set two threshold values: when CS<0.6, trigger a yellow warning, and a window prompt in the GUI; when CS<0.4, trigger a red alarm, in addition to the GUI prompt, it will also automatically call the SMS gateway API to push the alarm information and key decision suggestion ("Urgently adjust the zinc and copper scheme!") to the field manager's mobile phone in the form of a short message; Through the above technical means, the data is converted into intuitive graphics, the decision is converted into forward-looking prediction, and passive inquiry is changed into active warning, greatly improving the efficiency of human-computer interaction and the usability of the system. This active and multi-channel warning design ensures that key problems can be handled in a timely manner, reflecting the intelligence and practicality of the system.

[0035] The above shows and describes the basic principles, main features and advantages of the present application. Those skilled in the art should understand that the present application is not limited to the above embodiments, and the above embodiments and descriptions in the specification are only preferred examples of the present application and are not intended to limit the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the claimed application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A system for assessing the correlation between porcine intestinal health and trace element absorption, characterized in that, include: The data storage module is used to store historical and real-time multimodal data of the pig herd; The input module, connected to the data storage module, is used to receive real-time multimodal pig herd data from an external data source; The multi-source information fusion and feature extraction module is connected to the input module and the data storage module respectively. It is used to standardize and normalize the received multimodal data, and extract multidimensional feature vectors for evaluating the correlation from the multimodal data based on a preset feature system for quantifying the dynamic correlation between intestinal health and trace element absorption. The characteristic system includes trace element apparent absorption rate characteristics, trace element bioaccumulation characteristics, intestinal physiological stress characteristics, and production performance characteristics; The intelligent assessment core module is connected to the multi-source information fusion and feature extraction module, and it contains a correlation dynamic assessment model. The correlation dynamic assessment model is trained by an ensemble learning algorithm on historical multidimensional feature vectors and label data verified by in vitro detection. It is used to synchronously calculate and output the gut health index, the trace element absorption efficiency index and the correlation score that characterizes the correlation strength between the two based on the input real-time multidimensional feature vector. The adaptive decision support module, connected to the intelligent assessment core module, is used to generate a structured report containing personalized micronutrient diet adjustment suggestions, prebiotic addition schemes, and expected economic benefit predictions based on correlation scores, gut health index, micronutrient absorption efficiency index, and a preset decision rule base. The output response module, connected to the adaptive decision support module, is used to visualize the structured report and core evaluation indicators through a graphical user interface.

2. The system for assessing the correlation between porcine intestinal health and trace element absorption according to claim 1, characterized in that, The input module includes: A standardized data interface unit is used to receive the multimodal data of the pig herd from the production management record system, feed formula database, in vitro detection equipment and manual observation record terminal; Edge computing units, deployed at data acquisition terminals, are used to perform preliminary cleaning, redundancy removal, and formatting of initial data.

3. The system for assessing the correlation between porcine intestinal health and trace element absorption according to claim 2, characterized in that: The multimodal data of the pig herd includes production performance data, dietary trace element composition data, fecal trace element residue content data, hair trace element enrichment content data, intestinal health visual score data, and pig house environmental monitoring data.

4. The system for assessing the correlation between porcine intestinal health and trace element absorption according to claim 1, characterized in that: The correlation dynamic evaluation model is an ensemble learning model built on the gradient boosting decision tree algorithm; The real-time multidimensional feature vector input includes: dietary zinc level, fecal copper residue rate, hair selenium enrichment concentration, diarrhea rate, average daily weight gain, and intestinal visual score; the model output includes the predicted intestinal health index and the comprehensive utilization rate of trace elements. The correlation dynamic assessment model quantifies the contribution of each input's real-time multidimensional feature vector to the gut health index and trace element absorption efficiency index, and reveals the correlation strength between different trace elements and different gut health indicators in the form of a heat map.

5. The system for assessing the correlation between porcine intestinal health and trace element absorption according to claim 1, characterized in that, The system also includes: The model continuous learning module is connected to the intelligent evaluation core module and the data storage module, respectively. It is used to periodically use newly added multimodal data of pig herds and corresponding validation label data to incrementally train and optimize the correlation dynamic evaluation model in order to update the model parameters.

6. The system for assessing the correlation between porcine intestinal health and trace element absorption according to claim 1, characterized in that: The adaptive decision support module uses a pre-set decision rule base that combines production rules with case-based reasoning. The rules in the decision rule base are in the following form: IF correlation score < threshold T1 AND trace element absorption efficiency index ∈ [range A] AND gut health index ∈ [range B]; THEN Implementation: Adjust the organic zinc supplementation level in the diet to X mg / kg and recommend the use of prebiotic Y, which is expected to improve absorption efficiency by Z% and reduce diarrhea rate by W%; where the specific values ​​of threshold T1, range A, range B, parameters X, Z, and W, as well as the type of Y, are dynamically determined based on statistical analysis of historical datasets and case reasoning results.

7. The system for assessing the correlation between porcine intestinal health and trace element absorption according to claim 1, characterized in that, The visualization interface generated by the output response module includes a correlation analysis dashboard, which displays the correlation strength between different trace elements and different gut health indicators as revealed by the correlation dynamic assessment model in the form of a heat map, and displays the historical changes of core key performance indicators and the predicted trajectory based on current decision recommendations in the form of trend lines.

8. The system for assessing the correlation between porcine intestinal health and trace element absorption according to claim 1, characterized in that: The system also includes an early warning module, which is connected to the intelligent assessment core module and the adaptive decision support module, respectively; The early warning module is configured to automatically trigger multi-level early warning signals when the correlation score is lower than a preset threshold, and push the early warning information and corresponding structured decision suggestions to the user terminal of the designated manager.

Images