A beef cattle breeding stage evaluation method and system based on big data

Abstract

This invention belongs to the field of beef cattle breeding technology, specifically relating to a method and system for assessing beef cattle breeding stages based on big data. The invention includes determining an initial time point in the time series when the fluctuations of monitored breeding parameters meet judgment conditions; determining a reference time period in reverse direction along the time axis using the initial time point as a benchmark; determining the end time point of the reference time period as a judgment node; obtaining the substitution table parameters corresponding to the judgment node; comparing the substitution table parameters with preset standard parameters to calculate deviation data; and determining the growth status of the beef cattle based on early warning conditions. This invention avoids data interference by using substitution table parameters before the occurrence of abnormal fluctuations, achieving accurate assessment of growth status and precise tracing of the root causes of abnormalities.

Description

Technical Field

[0001] This invention belongs to the field of beef cattle breeding technology, specifically relating to a method and system for evaluating the stages of beef cattle breeding based on big data. Background Technology

[0002] In the beef cattle breeding industry, scientifically classifying and managing different growth stages, from calves and young cattle to fattening cattle, is an important measure to optimize feeding, prevent diseases, and improve meat quality. Therefore, it is necessary to establish an assessment system for each growth stage.

[0003] However, current methods for assessing the growth stages of beef cattle rely primarily on the personal experience of farmers, lacking standardized scientific criteria. This leads to inconsistent assessment results, making them difficult to replicate and promote. Especially in large-scale ranches, the varying levels of experience among farmers can easily cause management chaos and reduce production efficiency.

[0004] Furthermore, in terms of data monitoring, current technologies rely solely on monitoring a few physiological indicators such as weight and feed intake, and use fixed thresholds for stage judgment. This ignores the fact that cattle's physiological indicators are easily affected by external factors such as changes in environmental temperature and short-term stress, causing normal fluctuations. This makes it difficult for current technologies to effectively distinguish between normal fluctuations and the transitions in the cattle's true growth stages, leading to misjudgments and omissions, and resulting in incorrect management interventions. The growth status of cattle is determined by a combination of physiological, behavioral, and environmental factors. Current technologies often neglect in-depth analysis of the correlations between these data points, failing to form a comprehensive understanding of the cattle's condition. Consequently, current technologies lack the ability to predict growth trends and provide early warnings of health risks.

[0005] To address the aforementioned problems, this invention provides a method and system for evaluating the stages of beef cattle farming based on big data. Summary of the Invention

[0006] The purpose of this invention is to provide a method and system for assessing beef cattle breeding stages based on big data, so as to solve the problem of low screening accuracy caused by the subjective experience-based division of beef cattle breeding stages in the existing technology.

[0007] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A big data-based method for assessing the stages of beef cattle farming involves executing the following steps when the fluctuations of preset farming parameters meet certain criteria: The method for determining the judgment node on the time series based on parameter fluctuations includes: determining the initial time point on the time series of parameter fluctuations according to the judgment conditions; determining the reference time period in the reverse direction of the time axis based on the initial time point; and defining the end time point of the reference time period as the judgment node. Retrieve the substitution table parameters corresponding to the judgment node; And the growth status of beef cattle is assessed by comparing the parameters in the substitution table with the preset standard parameters.

[0008] Preferably, the judgment conditions include judgment rules, which are used to define positive fluctuations and negative fluctuations.

[0009] Preferably, the step of determining the initial time point on the time series of parameter fluctuations based on the judgment conditions includes: When the parameter fluctuation is determined to be positive, the time point of the first effective upper limit node in the time series is determined as the initial time point.

[0010] Preferably, the steps for assessing the growth status of beef cattle based on a comparison of the parameters in the substitution table with preset standard parameters include: The parameters in the substitution table are compared with the standard parameters to calculate the deviation data; And based on the warning conditions, determine whether the deviation data has reached the warning state, so as to determine whether the growth status of beef cattle is healthy or abnormal.

[0011] Preferably, after determining that the growth status of the beef cattle is abnormal, the method further includes: Calculate the deviation between the parameters in the substitution table and the corresponding standard parameters; And the substitution table parameter corresponding to the deviation value with the largest absolute value is determined as the main deviation item.

[0012] Preferably, it further includes: For the main deviation items, calculate the area of ​​difference between their parameter values ​​and the corresponding standard parameters within the reference time period; And outliers are identified by comparing the area of ​​difference with the area of ​​difference in multiple historical time periods.

[0013] Preferably, it further includes: Set a baseline time period starting from the anomaly point; And update the standard parameters based on the parameter values ​​of aquaculture parameters collected within the baseline time period.

[0014] This invention also discloses a big data-based assessment system for beef cattle farming stages, comprising: The fluctuation monitoring module is used to monitor the fluctuations of preset aquaculture parameters; The growth status assessment module is used to determine the judgment node on the time series based on the parameter fluctuation when the parameter fluctuation detected by the fluctuation monitoring module meets the judgment conditions, obtain the substitution table parameters corresponding to the judgment node, and assess the growth status of beef cattle based on the comparison between the substitution table parameters and the preset standard parameters. And a standard parameter update module, which is used to identify outliers based on the evaluation results output by the growth status evaluation module, and update the standard parameters based on the parameter values ​​of the aquaculture parameters associated with the outliers.

[0015] Preferably, the growth status assessment module is specifically used for: The parameters in the substitution table are compared with the standard parameters to calculate the deviation data; And based on the warning conditions, determine whether the deviation data has reached the warning state in order to determine the growth status of beef cattle.

[0016] Preferably, after determining that the growth status of the beef cattle is abnormal, the deviation values ​​between the substitution table parameters and the corresponding standard parameters are calculated. The parameter in the substitution table corresponding to the deviation value with the largest absolute value is determined as the main deviation item; For the main deviation items, calculate the area of ​​difference between their parameter values ​​and the corresponding standard parameters within the reference time period; Outliers are identified by comparing the area of ​​difference with historical areas of difference across multiple historical time periods. Set a baseline time period starting from the anomaly point; The standard parameters are updated based on the parameter values ​​of aquaculture parameters collected during the baseline time period.

[0017] Beneficial effects 1. This invention determines an initial time point on a time series and uses this point as a benchmark to determine a reference time period in reverse along the time axis to obtain corresponding substitute table parameters. By using data before the occurrence of abnormal fluctuations to calculate the deviation, it avoids interference from abnormal data and ensures the stability of the benchmark compared with standard parameters. This enables accurate identification of abnormal states and overcomes the shortcomings of traditional methods that rely on instantaneous values ​​or lagging indicators, which are prone to misjudgment.

[0018] 2. After determining that the growth status of beef cattle is abnormal, this invention determines the main deviation items by calculating the deviation values ​​of the substitution table parameters, and locates the abnormal points in the time series by comparing the difference area in the reference time period with the historical difference area, thereby extending from growth status assessment to tracing the root cause of the abnormality and providing accurate diagnostic basis for livestock managers.

[0019] 3. This invention continuously learns from confirmed abnormal events and dynamically adjusts standard parameters to automatically adapt to long-term changes in factors such as cattle breed, feed, or environment, thus solving the rigidity problem of traditional fixed-base models and ensuring the effectiveness and accuracy of the evaluation model in the breeding process. Attached Figure Description

[0020] Figure 1 This is a flowchart of the method of the present invention; Figure 2 This is a system module diagram of the present invention. Detailed Implementation

[0021] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0022] Example 1 See Figure 1 This embodiment provides a big data-based method for assessing the stages of beef cattle farming, including: S1. Division of breeding stages and determination of parameters.

[0023] Based on the physiological characteristics and growth patterns of beef cattle in different life stages such as lactation, weaning, early fattening, mid-fattening and late fattening, the complete breeding cycle is divided into multiple independent breeding stages. Then, for each breeding stage, a set of breeding parameters is determined to represent the growth status of that stage. The breeding parameters specifically include feed intake, water intake, daily weight gain, body temperature, respiratory rate, and activity level. For each breeding parameter, a corresponding standard parameter is set. The standard parameter is the ideal value or ideal range derived from the statistical analysis of historical health sample data, which is used to define the health status of beef cattle at the corresponding breeding stage.

[0024] S2, Execution parameter acquisition and fluctuation calculation.

[0025] Data acquisition devices deployed in the aquaculture environment are used to continuously or in real-time collect multiple aquaculture parameters at a preset frequency, forming a time series. The preferred data acquisition devices are IoT sensors, smart feeders, and electronic scales.

[0026] The parameter fluctuations are calculated based on the collected parameter values, thus highlighting the trend of parameter changes.

[0027] Furthermore, the calculation of parameter fluctuations specifically includes: Calculate the difference between the parameter value at the current moment and the parameter value at the previous acquisition moment; Alternatively, you can calculate the difference between the current parameter value and its arithmetic mean over a preset time window; both results reflect the degree of dynamic change in the parameter.

[0028] S3. Set judgment conditions and thresholds.

[0029] Judgment conditions are set to analyze parameter fluctuations. Since the physiological indicators of beef cattle exhibit normal diurnal rhythm fluctuations, fixed thresholds are insufficient to accurately identify abnormalities. Therefore, the judgment rules adopted in the judgment conditions can dynamically adjust the upper and lower limits of judgment according to different times of the day.

[0030] The judgment rules are specifically manifested as an upper and lower threshold for judgment, both of which change according to a preset time schedule. Specifically: During the fixed feeding period each day, the upper limit threshold for judging feed intake parameters is set to a higher value, while it is set to a lower value during the nighttime rest period.

[0031] The upper and lower threshold values ​​are used to determine whether parameter fluctuations are abnormally high or low, respectively. Both are adjusted according to a preset time schedule, such as a circadian rhythm.

[0032] In addition, the judgment criteria also include the judgment time period, preferably 30 minutes.

[0033] The judgment period refers to the preset duration, which is used to filter instantaneous data jumps; only when the parameter fluctuation exceeds the threshold for a duration longer than this period is it considered a valid anomaly.

[0034] If the duration of parameter fluctuations exceeding the upper limit threshold is greater than the judgment period, the starting node of that continuous period is marked as the upper limit valid node; conversely, if the duration of fluctuations below the lower limit threshold is greater than the judgment period, it is marked as the lower limit valid node.

[0035] Setting the judgment period effectively filters out instantaneous data jumps that are not statistically significant and are caused by occasional events.

[0036] Within a preset observation period, by counting the number of upper limit valid nodes and lower limit valid nodes, if the number of upper limit valid nodes is greater than the number of lower limit valid nodes, the parameter fluctuation is judged to be abnormally high, and the parameter fluctuation within the observation period is judged to be positive fluctuation; conversely, if the parameter fluctuation is judged to be abnormally low, it is judged to be negative fluctuation.

[0037] S4. Determine the initial time point.

[0038] To accurately pinpoint the starting point of abnormal changes in the time series of parameter fluctuations, the specific operation is as follows: If the parameter fluctuation is determined to be a positive fluctuation, such as a continuous rise in body temperature, then the first valid upper limit node is found in the time series, and the time point corresponding to the valid upper limit node is determined as the initial time point.

[0039] Furthermore, the fluctuation period is defined to provide a complete analysis of the entire abnormal event.

[0040] The fluctuation period represents the range of duration of a complete abnormal event. Its starting point is the initial time point, and its ending point is the time point of the first reverse valid node after the occurrence of the abnormal event. For example, for positive fluctuation, its ending point is the time point of the first lower limit valid node.

[0041] Starting from this initial time point, search for the first valid lower limit node along the positive direction of the time axis, and determine the time point of this node as the end point of the fluctuation period.

[0042] The fluctuation period represents the complete process from the abnormal rise of the parameter to its fall back.

[0043] Furthermore, a time period to be evaluated is defined. The time period to be evaluated is a preset time interval that starts from the end point of the fluctuation period and extends in the reverse direction along the time axis. It is used to perform trend analysis on the state after the abnormal event ends.

[0044] S5. Determine the reference time period and judgment node.

[0045] Based on a defined initial time point, a continuous period of a preset duration is extracted along the reverse direction of the time axis as a reference time period to establish a personalized health status baseline for individual beef cattle before the occurrence of abnormalities. The preset duration is set based on the physiological rhythm of beef cattle and the stability of the external environment. For example, it can be set to 72 hours, which is sufficient to smooth out daily fluctuations and reflect recent health status.

[0046] Furthermore, under specific circumstances, such as encountering clear external disturbances, like heat stress caused by high temperatures, the preset duration can be shortened to 24 hours to obtain the state immediately before the disturbance occurs.

[0047] The end point of the reference time period is defined as the judgment node, which represents a snapshot of the last healthy state of the beef cattle before it entered an abnormal change in this round of evaluation.

[0048] S6. Obtain the parameters of the substitution table.

[0049] At the time of the judgment node, the parameter values ​​of all aquaculture parameters corresponding to that time are obtained. These parameter values ​​obtained at a specific time point are collectively defined as the substitution table parameters.

[0050] The substitute table parameters represent the baseline state snapshot of the beef cattle before the anomaly was about to occur, after the aforementioned steps.

[0051] S7. After obtaining the parameters of the substitution table, the deviation data is calculated.

[0052] Each parameter in the substitution table is compared one by one with the standard parameters set in S1 for the corresponding breeding stage, and the deviation data is calculated. The deviation data refers to the quantitative difference value calculated by comparing the parameter values ​​of each parameter in the substitution table with the corresponding standard parameters.

[0053] This deviation data can intuitively quantify the gap between the various physiological indicators of the beef cattle and the overall health status of the herd in the days leading up to the occurrence of the anomaly.

[0054] S8. Perform growth status determination.

[0055] Based on the preset warning conditions, the deviation data obtained by S7 is judged.

[0056] The warning conditions can be a multi-dimensional set of thresholds, for example, triggered when the absolute value of the deviation in food intake exceeds 15% or the absolute value of the deviation in body temperature exceeds 1.0 degrees Celsius. If none of the deviation data triggers any warning conditions, the growth status of the beef cattle is determined to be healthy. If any deviation data reaches or exceeds its corresponding warning condition, the growth status of the beef cattle is determined to be abnormal, and a warning message is immediately generated and sent to the terminal device of the breeding manager through the communication interface to prompt them to make manual intervention.

[0057] Furthermore, the embodiment also includes identifying key deviations to locate the core from multiple deviations.

[0058] After calculating the deviation values ​​of each of the multiple substitution table parameters, these deviation values ​​are sorted in descending order of their absolute values. The substitution table parameter corresponding to the deviation value with the largest absolute value after sorting is determined as the main deviation item, which is the most critical indicator that causes the current abnormal state.

[0059] For example, if the calculated deviation in water intake is -20% and the deviation in activity level is +5%, then water intake will be identified as the primary deviation item.

[0060] The main deviation term provides a clear anomaly reference point for subsequent historical similarity analysis.

[0061] Furthermore, this embodiment also includes historical similarity analysis using the identified major deviation items to trace the historical root causes. For the major deviation items, a difference area that quantifies the severity of the current anomaly is calculated by integrating the absolute value of the difference between the parameter value curve and the corresponding standard parameter curve over a reference time period.

[0062] Starting from the end of the reference time period, multiple historical sampling time points are selected backward along the time axis at fixed time intervals. That is, historical sampling time points refer to multiple discrete time points selected along the time axis at fixed time intervals, such as 24 hours, based on the end of the reference time period, for the purpose of historical data backtracking.

[0063] For each historical sampling time point, the historical difference area of ​​the main deviation item within a historical time period of equal length to the reference time period, with that point as the endpoint, is calculated and used for historical similarity comparison.

[0064] By comparing the area of ​​difference calculated this time with all historical areas of difference, the historical sampling time point with the smallest numerical error between the two is determined and identified as an outlier.

[0065] The anomaly point refers to the point in time among all historical sampling time points where the corresponding historical difference area is closest to the difference area value of the current event, indicating that a highly similar anomaly event has occurred in history.

[0066] Finding this anomaly means that a highly similar event has occurred in the past, providing data clues for diagnosing the cause and tracing the root of the problem.

[0067] Furthermore, based on the identified historical outliers, this embodiment can also achieve adaptive optimization of standard parameters, specifically: Starting from the anomaly points found in history, a preset time interval is set as the baseline time period, which represents the recovery process of the individual beef cattle after the last similar event.

[0068] Collect and analyze the values ​​of aquaculture parameters within the baseline time period. Based on these parameter values, which represent individual recovery patterns, update or calibrate the original standard parameters. For example: The average value of the aquaculture parameter within the baseline time period is calculated and weighted averaged with the original standard parameter to generate a new standard parameter that has been individually calibrated for subsequent deviation assessment. In this way, the standard parameter can be iteratively optimized based on the individual's historical experience, making it more personalized and accurate.

[0069] Furthermore, this embodiment also provides different analysis strategies to deal with different types of fluctuations. The judgment conditions include calculation methods for reverse or sequential calculation of parameter fluctuations. When analyzing positive fluctuations, such as when body temperature rises due to fever, the reverse calculation method can be selected, that is, starting from the peak point of the fluctuation and tracing back along the time axis, using the lower limit threshold as a benchmark, to determine the precise moment when the body temperature begins to deviate from the normal range.

[0070] When analyzing the negative fluctuations, if the decrease in feed intake is caused by disease, a sequential calculation method can be selected, that is, tracking from the moment the parameter begins to decrease, and using the judgment upper limit threshold as a benchmark, determining the moment when the feed intake recovers to the normal range, thereby accurately measuring the total duration of the abnormal event.

[0071] The selectable calculation methods provide greater targeting and flexibility for diagnostic analysis in different physiological scenarios.

[0072] This embodiment helps livestock enterprises intervene in abnormal conditions, adjust feeding methods, and prevent diseases in the early stages by monitoring and providing real-time feedback on indicators of beef cattle at various growth stages, ultimately achieving the goal of improving slaughter rate and meat quality.

[0073] Example 2 See Figure 2 This embodiment provides a big data-based assessment system for beef cattle farming stages, including: Fluctuation monitoring module It is configured to continuously monitor the fluctuations of preset aquaculture parameters.

[0074] Among them, breeding parameters are a series of data indicators that reflect the physiological and behavioral status of beef cattle, such as weight, daily weight gain, feed intake, water intake, body temperature, rumination time and activity level.

[0075] Real-time parameter values ​​of these parameters are collected from data acquisition devices or databases at a preset frequency, such as hourly or daily, and organized into a time series according to time order.

[0076] Furthermore, the parameter fluctuations are calculated based on the real-time collected parameter values, and the system also stores judgment conditions. These judgment conditions define the degree or pattern of parameter fluctuations that require in-depth evaluation. When the monitored parameter fluctuations meet these judgment conditions, for example, when the fluctuation of a certain aquaculture parameter is continuously lower than the lower limit threshold and the duration is longer than the judgment period, the subsequent growth status evaluation module is triggered, and the relevant time series containing the fluctuations is passed to the growth status evaluation module.

[0077] The growth status assessment module is activated upon receiving a trigger signal and relevant time series from the fluctuation monitoring module to assess the growth status of beef cattle. The specific workflow is as follows: Determining decision points on a time series based on parameter fluctuations. Specifically: The received parameter fluctuations are classified according to the judgment rules used to define positive and negative fluctuations in the judgment conditions.

[0078] Preferably, taking a decrease in feed intake as an example, this is a negative fluctuation. If it is a positive fluctuation, such as an abnormal increase in body temperature, then the first effective upper limit node is found in the time series, and its corresponding time point is determined as the initial time point. Using this initial time point as a benchmark, a reference time period is determined in the reverse direction of the time axis, for example, looking back 7 days. The end time point of the reference time period, i.e. the initial time point, is defined as the judgment node, thereby obtaining data from a time point where the state was relatively stable before the anomaly occurred as an evaluation benchmark.

[0079] Obtain the substitution table parameters corresponding to the judgment node. Specifically: The substitution table parameters are a set of aquaculture parameter values ​​at a specific point in time, such as a decision node. For example, if the decision node is determined to be a certain moment, the parameter values ​​of multiple aquaculture parameters at that moment, such as body weight, feed intake, and water intake, are extracted from the time series and together constitute the substitution table parameters.

[0080] The growth status of beef cattle is assessed by comparing the parameters in the substitution table with the standard parameters. Specifically, L compares the obtained substitution table parameters with the standard parameters corresponding to the breeding stage stored in the system item by item to calculate the deviation data. Based on the warning conditions, if any deviation data exceeds its threshold, or the comprehensive deviation score reaches a certain threshold, it is determined whether the deviation data has reached the warning state. If it has reached the warning state, the growth status of the beef cattle is determined to be abnormal; otherwise, it is determined to be healthy.

[0081] After determining that the growth status of the beef cattle is abnormal, the main deviation items are identified. The deviation value of each substitute table parameter from its corresponding standard parameter is calculated, and the feeding parameter corresponding to the largest absolute deviation value is identified as the main deviation item. Specifically, if the deviation value of body weight is found to be much larger than the deviation values ​​of other parameters, the feeding parameter corresponding to body weight is identified as the main deviation item. The final output includes the growth status (healthy or abnormal) and the main deviation items identified in the abnormal situation. This assessment result, along with the main deviation items and reference time period information, is then passed to the standard parameter update module.

[0082] The standard parameter update module is used to adaptively update the standard parameters based on the evaluation results output by the growth status evaluation module, thereby ensuring the accuracy and timeliness of the standard parameters. The specific operation is as follows: After receiving the main deviation item and the reference time period, calculate the difference area value of the main deviation item within the reference time period.

[0083] The difference area value is a quantitative indicator, which is calculated by integrating the absolute value of the difference between the actual parameter value curve and the standard parameter curve of the main deviation items within the reference time period. It reflects the cumulative degree and duration of the deviation.

[0084] Anomalies are identified by comparing the calculated difference area with historical difference areas stored in the database for multiple historical time periods. Historical difference areas are the difference area values ​​calculated when similar anomalies occurred in the past. By comparing the calculated difference area with all historical difference areas, the historical sampling time point with the smallest numerical error between the two is identified and determined as the anomaly. Starting from the identified anomaly point, a new baseline time period is established, for example, extending backwards from the anomaly point by a certain amount of time, such as 14 days. During this period, the cattle recover their health after intervention. The values ​​of various breeding parameters within this baseline time period are collected and statistically analyzed. Based on these parameter values ​​representing individual recovery patterns, the original standard parameters are recalculated and updated. For example, if it is found that the overall feed intake of a certain batch of cattle is generally lower than the old standard parameters but growth is normal, then this lower feed intake level is updated to the new standard parameters.

[0085] This embodiment improves the accuracy and efficiency of beef cattle farming management by detecting and issuing early warnings of abnormal states in individual or group beef cattle, and by locating key deviations and conducting in-depth analysis of historical data to optimize the standard parameters of the evaluation model itself.

Claims

1. A method for evaluating beef cattle breeding stages based on big data, characterized in that, When the fluctuation of the preset aquaculture parameters is detected to meet the judgment conditions, the following actions are executed: The method for determining the judgment node on the time series based on parameter fluctuations includes: determining the initial time point on the time series of parameter fluctuations according to the judgment conditions; determining the reference time period in the reverse direction of the time axis based on the initial time point; and defining the end time point of the reference time period as the judgment node. Retrieve the substitution table parameters corresponding to the judgment node; And the growth status of beef cattle is assessed by comparing the parameters in the substitution table with the preset standard parameters.

2. The method as claimed in claim 1, wherein, The judgment criteria include judgment rules, which are used to define positive and negative fluctuations.

3. The method for evaluating beef cattle breeding stages based on big data according to claim 2, characterized in that, Based on the judgment conditions, the steps to determine the initial time point in the time series of parameter fluctuations include: When the parameter fluctuation is determined to be positive, the time point of the first effective upper limit node in the time series is determined as the initial time point.

4. The method as claimed in claim 1, wherein, The steps for assessing the growth status of beef cattle, based on a comparison of the parameters in the substitution table with the preset standard parameters, include: The parameters in the substitution table are compared with the standard parameters to calculate the deviation data; And based on the warning conditions, determine whether the deviation data has reached the warning state, so as to determine whether the growth status of beef cattle is healthy or abnormal.

5. A method for evaluating beef cattle breeding stages based on big data according to claim 4, characterized in that, After determining that the growth status of beef cattle is abnormal, the following steps are also included: Calculate the deviation between the parameters in the substitution table and the corresponding standard parameters; And the substitution table parameter corresponding to the deviation value with the largest absolute value is determined as the main deviation item.

6. The method as claimed in claim 5, wherein, Also includes: For the main deviation items, calculate the area of ​​difference between their parameter values ​​and the corresponding standard parameters within the reference time period; And outliers are identified by comparing the area of ​​difference with the area of ​​difference in multiple historical time periods.

7. The method as claimed in claim 6, wherein, Also includes: Set a baseline time period starting from the anomaly point; And update the standard parameters based on the parameter values ​​of aquaculture parameters collected within the baseline time period. 8.A big data-based beef cattle breeding stage evaluation system, characterized by, include: The fluctuation monitoring module is used to monitor the fluctuations of preset aquaculture parameters; The growth status assessment module is used to determine the judgment node on the time series based on the parameter fluctuation when the parameter fluctuation detected by the fluctuation monitoring module meets the judgment conditions, obtain the substitution table parameters corresponding to the judgment node, and assess the growth status of beef cattle based on the comparison between the substitution table parameters and the preset standard parameters. And a standard parameter update module, which is used to identify outliers based on the evaluation results output by the growth status evaluation module, and update the standard parameters based on the parameter values ​​of the aquaculture parameters associated with the outliers.

9. A big data based beef cattle farming stage evaluation system as claimed in claim 8, wherein, The growth status assessment module is specifically used for: The parameters in the substitution table are compared with the standard parameters to calculate the deviation data; And based on the warning conditions, determine whether the deviation data has reached the warning state in order to determine the growth status of beef cattle.

10. A big data-based beef cattle breeding stage assessment system according to claim 9, characterized in that, After determining that the growth status of beef cattle is abnormal, the deviation values ​​between the substitution table parameters and the corresponding standard parameters are calculated. The parameter in the substitution table corresponding to the deviation value with the largest absolute value is determined as the main deviation item; For the main deviation items, calculate the area of ​​difference between their parameter values ​​and the corresponding standard parameters within the reference time period; Outliers are identified by comparing the area of ​​difference with historical areas of difference across multiple historical time periods. Set a baseline time period starting from the anomaly point; The standard parameters are updated based on the parameter values ​​of aquaculture parameters collected during the baseline time period.

Images